Search

Accurate traffic prediction is essential for effective urban management and the improvement of transportation efficiency. Recently, data-driven traffic prediction methods have been widely adopted, with better performance than traditional approaches. However, they often require large amounts of data for effective training, which becomes challenging given the prevalence of data scarcity in regions with inadequate sensing infrastructures. To address this issue, we propose a Semantic-Fused Multi-Granularity Transfer Learning (SFMGTL) model to achieve knowledge transfer across cities with fused semantics at different granularities. In detail, we design a semantic fusion module to fuse various semantics while conserving static spatial dependencies via reconstruction losses. Then, a fused graph is constructed based on node features through graph structure learning. Afterwards, we implement hierarchical node clustering to generate graphs with different granularity. To extract feasible meta-knowledge, we further introduce common and private memories and obtain domain-invariant features via adversarial training. It is worth noting that our work jointly addresses semantic fusion and multi-granularity issues in transfer learning. We conduct extensive experiments on six real-world datasets to verify the effectiveness of our SFMGTL model by comparing it with other state-of-the-art baselines. Afterwards, we also perform ablation and case studies, demonstrating that our model possesses substantially fewer parameters compared to baseline models. Moreover, we illustrate how knowledge transfer aids the model in accurately predicting demands, especially during peak hours. The codes can be found at https://github.com/zeonchen/SFMGTL. © 2024

Aiming at the current dilemma of inaccurate prediction accuracy in the field of traffic flow prediction, this paper proposes a novel traffic flow prediction method using the Revised Enhanced Extreme Gray Wolf Optimizer (REEGWO) to optimize convolutional neural networks (CNNs) and combining with bi-directional long and short-term memory (BiLSTM) networks. The experimental results show that the model can effectively converge the training loss error and RMSE, and significantly outperforms the existing classical methods in terms of goodness-of-fit, average absolute error, average deviation error and average absolute percentage error, providing an efficient and accurate solution for traffic flow prediction.

Traffic forecasting plays a critical role in intelligent transportation systems (ITS) in smart cities. Travelers as well as urban managers rely on reliable traffic information to make their decisions for route choice and traffic management. However, noisy or missing traffic data poses a problem for accurate and robust traffic forecasting. While data-driven models such as deep neural networks can achieve high prediction accuracy with complete datasets, sensor malfunctions, and environmental effects degrade the performance of such models, as these models rely heavily on precise traffic measurements for model training and estimation. Consequently, incomplete traffic data poses a challenge for robust model design that can make accurate traffic forecasts with noisy/missing data. This research proposes the Robust Spatiotemporal Graph Convolutional Network (RT-GCN), a traffic prediction model that handles noise perturbations and missing data using a Gaussian distributed node representation and a variance based attention mechanism. Through experiments conducted on four real-world traffic datasets using diverse noisy and missing scenarios, the proposed RT-GCN model has demonstrated its ability to handle noise perturbations and missing values and provide high accuracy prediction.

Multi-step traffic speed prediction is a challenging issue due to the multiple spatial-temporal dependencies among roads. Some spatial dependencies, especially those formed by different traffic modes, are not fully exploited, and how to simultaneously consider spatial and temporal dependencies and effectively integrate them within a single prediction framework needs further exploration. To tackle the above issues, we propose a multi-view spatial-temporal graph convolutional framework MVSTG, which adequately exploits the multi-view spatial-temporal dependencies and their interactions to improve the accuracy of traffic prediction. Multi-view temporal learning captures the multiple temporal trends by temporal convolution from multi-granularity historical data, and multi-view spatial learning handles the multiple spatial correlations by graph convolution from multiple graphs. In addition, view-wise attention-based fusion is proposed to adaptively identify the importance of each upstream view, fuse the multi-view information, and generate integrated results for downstream views. The experiments on two real-world urban traffic datasets demonstrate that the multi-view data and the proposed model framework enhance performance on the accuracy of speed prediction, especially in mid-term and long-term prediction.

The research and innovation related to fifth-generation (5G) networks that has been carried out in recent years has decided on the fundamentals of the smart slice in radio access networks (RANs), as well as the autonomous fixed network operation. One of the most challenging objectives of beyond 5G (B5G) and sixth-generation (6G) networks is the deployment of mechanisms that enable smart end-to-end (e2e) network operation, which is required for the achievement of the stringent service requirements of the envisioned use cases to be supported in the short term. Therefore, smart actions, such as dynamic capacity allocation, flexible functional split, and dynamic slice management need to be performed in tight coordination with the autonomous capacity management of the fixed transport network infrastructure. Otherwise, the benefits of smart slice operation (i.e., cost and energy savings while ensuring per-slice service requirements) might be cancelled due to uncoordinated autonomous fixed network operation. Notably, the transport network in charge of supporting slices from the user equipment (UE) to the core expands across access and metro fixed networks. The required coordination needs to be performed while keeping the privacy of the radio and fixed network domains, which is important in multi-tenant scenarios where both network segments are managed by different operators. In this paper, we propose a novel approach that explores the concept of context-aware network operation, where the slice control anticipates the aggregated and anonymized information of the expected slice operation that is sent to the fixed network orchestrator in an asynchronous way. The context is then used as the input for the artificial intelligence (AI)-based models used by the fixed network control for the predictive capacity management of optical connections in support of RAN slices. This context-aware network operation aims at enabling accurate and reliable autonomous fixed network operation un, This work is partially supported by the SNS Joint Undertaken under grant agreement No. 101096120 (SEASON), the MICINN IBON (PID2020-114135RB-I00) project, and from the ICREA Institution., Peer Reviewed, Postprint (published version)

Accurate prediction of highway traffic is of vital importance to proactive traffic monitoring, operation and controls. In the data mining of highway traffic, abstracting temporal knowledge is often prioritized than exploring topological relationship. In this study, we propose a deep learning model, called Knowledge-Sequence-to-Sequence (K-Seq2Seq), to solve the short-term highway traffic prediction problem in two stages: representing temporal knowledge and predicting future traffic. Through computational experiment in a road section of a Swedish motorway, we show that our model outperforms the conventional Seq2Seq model significantly, more than 20% when predicting information of longer time step., QC 20240222

In general, the availability of an accurate machine learning (ML) model plays a particularly important role in the development of new networking solutions and is one of the main drivers for the development of 5G and beyond networking. Although an option is to update the model once inaccurate data is detected, such approach requires high computational effort, specially once the data history is large. In this paper, we propose an approach that combines a traffic prediction model based on Long Short-Term Memory (LSTM) with an analysis module for dynamic connection capacity allocation. Once the model is generated, re-training can be triggered after inaccuracies are detected by the analysis module. Illustrative numerical results show the benefits from the proposed decision-based re-training approach to reduce the number of re-training rounds while maintaining model accuracy., This work was partially funded by MCIN/AEI/ 10.13039/501100011033 grant PID2021-126431OB-I00 (ANEMONE), and Generalitat de Catalunya grant 2021 SGR 00770. This work also was funded by the European Commission Horizon Europe SNS JU DESIRE6G project (G.A. 101096466), from the Spanish MINECO and the European Union though the NextGeneration UNICO5G TIMING (TSI-063000-2021-145), and the AEI IBON (PID2020-114135RB-I00) projects. The authors also acknowledge the support of the French Agence Nationale de la Recherche (ANR), under grant ANR-19-CE-25-0001-01 (ARTIC project)., Peer Reviewed, Postprint (author's final draft)

This paper investigates the prediction of spectrum usage by wireless local area networks based on recurrent neural networks (RNNs). The prediction results can be used to enhance the spectrum efficiency in dynamic spectrum sharing, and accuracy of spectrum sensing in cognitive radio networks. Observed time series of duty cycle (DC), which indicates the spectrum usage trend, is utilized to predict the future DC by the RNN. At first, we reveal a drawback of prediction by a single RNN, and this approach is denoted by a conventional approach in this paper. Specifically, the prediction results may have a significant biased error if the observed DCs are biased to either high or low values. For this problem, we propose the DC prediction with two RNNs and each of them designed for high DC case and low DC case, respectively. The prediction algorithm at first identifies the state of current DC either high or low. Then, the RNN for the identified state is performed for an accurate DC prediction. Numerical evaluations based on comprehensive measurement experiments of spectrum usage have presented that the proposed DC prediction can improve the accuracy of DC prediction compared to the conventional approach.

Accurate traffic prediction is crucial for planning, management and control of intelligent transportation systems. Most state-of-the-art methods for traffic prediction effectively capture complex traffic patterns (e.g. spatial and temporal correlations of traffic data) by employing spatio-temporal neural networks as prediction models, together with graph convolution networks to learn spatial correlations of prediction objects (e.g. traffic states of road segments, as in this study). Such spatial correlations can be regarded as micro correlations. However, there are also macro correlations between regions, each of which is composed of multiple road segments or artificially partitioned areas. Macro correlations represent another type of interaction within road segments, and should be carefully considered when predicting traffic. The diversity of micro spatial correlations and corresponding macro spatial correlations (e.g. correlations based on physical proximity or traffic pattern similarity) further increases the complexity of traffic prediction. We overcome these challenges by developing a macro–micro spatio-temporal neural network model, denoted ‘MMSTNet’. MMSTNet captures spatio-temporal patterns by (a) utilizing a graph convolution network and a spatial attention network to capture micro and macro spatial correlations, respectively; (b) employing a temporal convolution network and a temporal attention network to learn temporal patterns; and (c) integrating hierarchically learned representations based on designed attention mechanisms. We perform evaluations on two real-world datasets and thereby demonstrate that MMSTNet outperforms state-of-the-art models in traffic prediction tasks. © 2023 Elsevier Ltd

Large cloud service providers have built an increasing number of geo-distributed data centers (DCs) connected by Wide Area Networks (WANs). These DC-WANs carry both high-priority traffic from interactive services and low-priority traffic from bulk transfers. Given that a DC-WAN is an expensive resource, providers often manage it via traffic engineering algorithms that rely on accurate predictions of inter-DC high-priority (delay-sensitive) traffic. In this article, we perform a large-scale measurement study of high-priority inter-DC traffic from Baidu. We measure how inter-DC traffic varies across their global DC-WAN and show that most existing traffic prediction methods either cannot capture the complex traffic dynamics or overlook traffic interrelations among DCs. Building on our measurements, we propose the Interrelated-Temporal Graph Convolutional Network (IntegNet) model for inter-DC traffic prediction. In contrast to prior efforts, our model exploits both temporal traffic patterns and inferred co-dependencies between DC pairs. IntegNet forecasts the capacity needed for high-priority traffic demands by accounting for the balance between resource provisioning (i.e., allocating resources exceeding actual demand) and QoS losses (i.e., allocating fewer resources than actual demand). Our experiments show that IntegNet can keep a very limited QoS loss, while also reducing overprovisioning by up to 42.1% compared to the state-of-the-art and up to 66.2% compared to the traditional method used in DC-WAN traffic engineering. © 1990-2012 IEEE.

Autonomous driving technology has witnessed remarkable advancements in recent years, largely due to the integration of machine learning (ML) techniques. This paper provides a comprehensive overview of ML applications in autonomous driving systems, focusing on perception and decision-making aspects. It discusses how ML models improve perception tasks such as object detection and tracking, as well as decision-making processes like path planning and traffic prediction. The paper also examines challenges and future directions in the integration of ML algorithms for achieving safer and more efficient autonomous vehicles.

Autonomous driving technology has witnessed remarkable advancements in recent years, largely due to the integration of machine learning (ML) techniques. This paper provides a comprehensive overview of ML applications in autonomous driving systems, focusing on perception and decision-making aspects. It discusses how ML models improve perception tasks such as object detection and tracking, as well as decision-making processes like path planning and traffic prediction. The paper also examines challenges and future directions in the integration of ML algorithms for achieving safer and more efficient autonomous vehicles.

Autonomous driving technology has witnessed remarkable advancements in recent years, largely due to the integration of machine learning (ML) techniques. This paper provides a comprehensive overview of ML applications in autonomous driving systems, focusing on perception and decision-making aspects. It discusses how ML models improve perception tasks such as object detection and tracking, as well as decision-making processes like path planning and traffic prediction. The paper also examines challenges and future directions in the integration of ML algorithms for achieving safer and more efficient autonomous vehicles.

The pervasiveness of GPS-enabled devices and wireless communication technologies results in a proliferation of traffic data in intelligent transportation systems, where traffic prediction is often essential to enable reliability and safety. Many recent studies target traffic prediction using deep learning techniques. They model spatio-temporal dependencies among traffic states by deep learning and achieve good overall performance. However, existing studies ignore the bias on traffic prediction models, which refers to non-uniformed performance distribution across road segments, especially the significantly poor prediction results on certain road segments. To solve this issue, we propose a framework named spatio-temporal mixture-of-experts (ST-MoE) that aims to eliminate the bias on traffic prediction. In general, we refer to any traffic prediction model as the based model, and adopt the proposed ST-MoE framework as a plug-in to debias. ST-MoE uses stacked convolution-based networks to learn spatio-temporal representations of individual patterns of road segments and then adaptively assigns appropriate expert layers (sub-networks) to different patterns through a spatio-temporal gating network. To this end, the patterns can be distinguished, and biased performance among road segments can be eliminated by experts tailored for specific patterns, which also further improves the overall prediction accuracy of the base model. Extensive experimental results on various base models and real-world datasets prove the effectiveness of ST-MoE. © 2023 Copyright held by the owner/author(s).

There is a lack of research on the analysis of peruser traffic in cellular networks, for deriving and following traffic-aware network management. In fact, the legacy design approach, in which resource provisioning and operation control are performed based on the cell-aggregated traffic scenarios, are not so energy- and cost-efficient and need to be substituted with user-centric predictive analysis of mobile network traffic and proactive network resource management. Here, we shed light on this problem by designing traffic prediction tools that utilize standard machine learning (ML) tools, including long shortterm memory (LSTM) and autoregressive integrated moving average (ARIMA) on top of per-user data. We present an expansive empirical evaluation of the designed solutions over a real network traffic dataset. Within this analysis, the impact of different parameters, such as the time granularity, the length of future predictions, and feature selection are investigated. As a potential application of these solutions, we present an ML-powered Discontinuous reception (DRX) scheme for energy saving. Towards this end, we leverage the derived ML models for dynamic DRX parameter adaptation to user traffic. The performance evaluation results demonstrate the superiority of LSTM over ARIMA in general, especially when the length of the training time series is high enough, and it is augmented by a wisely-selected set of features. Furthermore, the results show that adaptation of DRX parameters by online prediction of future traffic provides much more energy-saving at low latency cost in comparison with the legacy cell-wide DRX parameter adaptation., QC 20220603

Traffic speed prediction using deep learning has been the topic of many studies. In this paper, we analyse the performance of Graph Neural Network-based techniques during periods of traffic congestion. We first compare a selection of recently proposed techniques that claim to achieve good results using the METR-LA and PeMS-BAY data sets. We then investigate the performance of three of these approaches – GraphWaveNet, Spacetime Neural Network (STNN) and Spatio-Temporal Attention Wavenet (STAWnet) – during congested periods, using recurrent congestion patterns to set a threshold for general congestion through the entire traffic network. Our results show that performance deteriorates significantly during congested time periods, which is concerning, as traffic speed prediction is usually of most value during times of congestion. We also found that, while the above approaches perform almost equally in the absence of congestion, there are much bigger differences in performance during periods of congestion.

Participatory Sensing (PS) is a common mode of data collection where valuable data is gathered from many contributors, each providing data from the user’s or the device’s surroundings via a mobile device, such as a smartphone. This has the advantage of cost-efficiency and wide-scale data collection. One of the application areas for PS is the collection of traffic data. The cost of collecting roving sensor data, such as vehicle probe data, is significantly lower than that of traditional stationary sensors such as radar and inductive loops. The collected data could pave the way for providing accurate and high-resolution traffic information that is important to transportation planning. The problem with PS is that it is open, and anyone can register and participate in a sensing task. A malicious user is likely to submit false data without performing the sensing task for personal advantage or, even worse, to attack on a large scale with clear intentions. For example, in real-time traffic monitoring, attackers may report false alerts of traffic jams to divert traffic on the road ahead or directly interfere with the system’s observation and judgment of road conditions, triggering large-scale traffic guidance errors. An efficient method of assessing the trustworthiness of data is therefore required. The trustworthiness problem can be approximated as the problem of anomaly detection in time-series data. Traditional predictive model-based anomaly detection models include univariate models for univariate time series such as Auto Regressive Integrated Moving Average (ARIMA), hypothesis testing, and wavelet analysis, and recurrent neural networks (RNNs) for multiple time series such as Gated Recurrent Unit (GRU) and Long short-term memory (LSTM). When talking about traffic scenarios, some prediction models that consider both spatial and temporal dependencies are likely to perform better than those that only consider temporal dependencies, such as Diffusion Convolutional Recurren, Participatory Sensing (PS) är ett vanligt sätt att samla in data där värdefulla data samlas in från många bidragsgivare, som alla tillhandahåller data från användarens eller enhetens omgivning via en mobil enhet, t.ex. en smartphone. Detta har fördelen av kostnadseffektivitet och omfattande datainsamling. Ett av tillämpningsområdena för PS är insamling av trafikdata. Kostnaden för att samla in data från mobila sensorer, t.ex. data från fordonssonderingar, är betydligt lägre än kostnaden för traditionella stationära sensorer, t.ex. radar och induktiva slingor. De insamlade uppgifterna skulle kunna bana väg för att tillhandahålla exakt och högupplöst trafikinformation som är viktig för transportplaneringen. Problemet med deltagande avkänning är att den är öppen och att vem som helst kan registrera sig och delta i en avkänningsuppgift. En illasinnad användare kommer sannolikt att lämna in falska uppgifter utan att utföra avkänningsuppgiften för personlig vinning eller, ännu värre, för att angripa en stor skala med tydliga avsikter. Vid trafikövervakning i realtid kan t.ex. angripare rapportera falska varningar om trafikstockningar för att avleda trafiken på vägen framåt eller direkt störa systemets observation och bedömning av vägförhållanden, vilket kan utlösa storskaliga fel i trafikstyrningen. Det finns därför ett akut behov av en effektiv metod för att bedöma uppgifternas tillförlitlighet. Problemet med trovärdighet kan approximeras som problemet med upptäckt av anomalier i tidsserier. Traditionella modeller för anomalidetektion som bygger på prediktiva modeller omfattar univariata modeller för univariata tidsserier, t.ex. ARIMA (Autoregressive Integrated Moving Average), hypotesprövning och waveletanalys, och återkommande neurala nätverk (RNN) för flera tidsserier, t.ex. GRU (Gated Recurrent Unit) och LSTM (Long short-term memory). När man talar om trafikscenarier kommer vissa prognosmodeller som tar hänsyn till både rumsliga och tidsmässiga beroenden sannolikt at

Accurate and timely traffic flow prediction is crucial for intelligent transportation systems (ITS). Recent advances in graph-based neural networks have achieved promising prediction results. However, some challenges remain, especially regarding graph construction and the time complexity of models. In this paper, we propose a multi-stream feature fusion approach to extract and integrate rich features from traffic data and leverage a data-driven adjacent matrix instead of the distance-based matrix to construct graphs. We calculate the Spearman rank correlation coefficient between monitor stations to obtain the initial adjacent matrix and fine-tune it while training. As to the model, we construct a multi-stream feature fusion block (MFFB) module, which includes a three-channel network and the soft-attention mechanism. The three-channel networks are graph convolutional neural network (GCN), gated recurrent unit (GRU) and fully connected neural network (FNN), which are used to extract spatial, temporal and other features, respectively. The soft-attention mechanism is utilized to integrate the obtained features. The MFFB modules are stacked, and a fully connected layer and a convolutional layer are used to make predictions. We conduct experiments on two real-world traffic prediction tasks and verify that our proposed approach outperforms the state-of-the-art methods within an acceptable time complexity.

Reducing energy consumption is a pressing issue in low-power machine-type communication (MTC) networks. In this regard, the Wake-up Signal (WuS) technology, which aims to minimize the energy consumed by the radio interface of the machine-type devices (MTDs), stands as a promising solution. However, state-of-the-art WuS mechanisms use static operational parameters, so they cannot efficiently adapt to the system dynamics. To overcome this, we design a simple but efficient neural network to predict MTC traffic patterns and configure WuS accordingly. Our proposed forecasting WuS (FWuS) leverages an accurate long-short term memory (LSTM)-based traffic prediction that allows extending the sleep time of MTDs by avoiding frequent page monitoring occasions in idle state. Simulation results show the effectiveness of our approach. The traffic prediction errors are shown to be below 4%, being false alarm and miss-detection probabilities respectively below 8.8% and 1.3%. In terms of energy consumption reduction, FWuS can outperform the best benchmark mechanism in up to 32%. Finally, we certify the ability of FWuS to dynamically adapt to traffic density changes, promoting low-power MTC scalability.

The 5G Radio Access Network (RAN) virtualization aims to improve network quality and lower the operator's costs. One of its main features is the functional split, i.e., dividing the instantiation of RAN baseband functions into different units over metro-network nodes. However, its optimal placement is non-trivial: it depends on the application requirements and on the expected traffic volume, whose daily variation highly impacts the total power consumption. Current optimization solutions fail to provide a placement solution capable of handling traffic fluctuations. In fact, the standard machine learning algorithms used in the literature for planning the network resources in advance result in an allocation that is inadequate to carry the actual traffic at all the time-slots. Hence, we must reserve an artificial buffer capacity in the nodes to ensure feasibility. Instead, our proposed method exploits a fine-grained two-step multi-task algorithm that predicts the mean and quantile traffic, making the artificial capacity no longer necessary. The subsequent placement uses mixed-integer linear programming and a heuristic. The former considers the expected traffic in the objective function (to estimate costs) and the quantile in the constraints (to enforce capacity limits). The heuristic combines the mean and quantile results to minimize the power and comply with the requirements. While using sufficiently large artificial buffers guarantees robustness with a mild power increase compared to the oracle, the fine-grained multi-task model improves the results, reducing the power consumption compared to the mean and meets all constraints. The heuristic enables significant computational time reduction., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Cyber Security

Participatory Sensing (PS) is a common mode of data collection where valuable data is gathered from many contributors, each providing data from the user’s or the device’s surroundings via a mobile device, such as a smartphone. This has the advantage of cost-efficiency and wide-scale data collection. One of the application areas for PS is the collection of traffic data. The cost of collecting roving sensor data, such as vehicle probe data, is significantly lower than that of traditional stationary sensors such as radar and inductive loops. The collected data could pave the way for providing accurate and high-resolution traffic information that is important to transportation planning. The problem with PS is that it is open, and anyone can register and participate in a sensing task. A malicious user is likely to submit false data without performing the sensing task for personal advantage or, even worse, to attack on a large scale with clear intentions. For example, in real-time traffic monitoring, attackers may report false alerts of traffic jams to divert traffic on the road ahead or directly interfere with the system’s observation and judgment of road conditions, triggering large-scale traffic guidance errors. An efficient method of assessing the trustworthiness of data is therefore required. The trustworthiness problem can be approximated as the problem of anomaly detection in time-series data. Traditional predictive model-based anomaly detection models include univariate models for univariate time series such as Auto Regressive Integrated Moving Average (ARIMA), hypothesis testing, and wavelet analysis, and recurrent neural networks (RNNs) for multiple time series such as Gated Recurrent Unit (GRU) and Long short-term memory (LSTM). When talking about traffic scenarios, some prediction models that consider both spatial and temporal dependencies are likely to perform better than those that only consider temporal dependencies, such as Diffusion Convolutional Recurren, Participatory Sensing (PS) är ett vanligt sätt att samla in data där värdefulla data samlas in från många bidragsgivare, som alla tillhandahåller data från användarens eller enhetens omgivning via en mobil enhet, t.ex. en smartphone. Detta har fördelen av kostnadseffektivitet och omfattande datainsamling. Ett av tillämpningsområdena för PS är insamling av trafikdata. Kostnaden för att samla in data från mobila sensorer, t.ex. data från fordonssonderingar, är betydligt lägre än kostnaden för traditionella stationära sensorer, t.ex. radar och induktiva slingor. De insamlade uppgifterna skulle kunna bana väg för att tillhandahålla exakt och högupplöst trafikinformation som är viktig för transportplaneringen. Problemet med deltagande avkänning är att den är öppen och att vem som helst kan registrera sig och delta i en avkänningsuppgift. En illasinnad användare kommer sannolikt att lämna in falska uppgifter utan att utföra avkänningsuppgiften för personlig vinning eller, ännu värre, för att angripa en stor skala med tydliga avsikter. Vid trafikövervakning i realtid kan t.ex. angripare rapportera falska varningar om trafikstockningar för att avleda trafiken på vägen framåt eller direkt störa systemets observation och bedömning av vägförhållanden, vilket kan utlösa storskaliga fel i trafikstyrningen. Det finns därför ett akut behov av en effektiv metod för att bedöma uppgifternas tillförlitlighet. Problemet med trovärdighet kan approximeras som problemet med upptäckt av anomalier i tidsserier. Traditionella modeller för anomalidetektion som bygger på prediktiva modeller omfattar univariata modeller för univariata tidsserier, t.ex. ARIMA (Autoregressive Integrated Moving Average), hypotesprövning och waveletanalys, och återkommande neurala nätverk (RNN) för flera tidsserier, t.ex. GRU (Gated Recurrent Unit) och LSTM (Long short-term memory). När man talar om trafikscenarier kommer vissa prognosmodeller som tar hänsyn till både rumsliga och tidsmässiga beroenden sannolikt at

Traffic speed prediction using deep learning has been the topic of many studies. In this paper, we analyse the performance of Graph Neural Network-based techniques during periods of traffic congestion. We first compare a selection of recently proposed techniques that claim to achieve good results using the METR-LA and PeMS-BAY data sets. We then investigate the performance of three of these approaches – GraphWaveNet, Spacetime Neural Network (STNN) and Spatio-Temporal Attention Wavenet (STAWnet) – during congested periods, using recurrent congestion patterns to set a threshold for general congestion through the entire traffic network. Our results show that performance deteriorates significantly during congested time periods, which is concerning, as traffic speed prediction is usually of most value during times of congestion. We also found that, while the above approaches perform almost equally in the absence of congestion, there are much bigger differences in performance during periods of congestion.

The 5G Radio Access Network (RAN) virtualization aims to improve network quality and lower the operator's costs. One of its main features is the functional split, i.e., dividing the instantiation of RAN baseband functions into different units over metro-network nodes. However, its optimal placement is non-trivial: it depends on the application requirements and on the expected traffic volume, whose daily variation highly impacts the total power consumption. Current optimization solutions fail to provide a placement solution capable of handling traffic fluctuations. In fact, the standard machine learning algorithms used in the literature for planning the network resources in advance result in an allocation that is inadequate to carry the actual traffic at all the time-slots. Hence, we must reserve an artificial buffer capacity in the nodes to ensure feasibility. Instead, our proposed method exploits a fine-grained two-step multi-task algorithm that predicts the mean and quantile traffic, making the artificial capacity no longer necessary. The subsequent placement uses mixed-integer linear programming and a heuristic. The former considers the expected traffic in the objective function (to estimate costs) and the quantile in the constraints (to enforce capacity limits). The heuristic combines the mean and quantile results to minimize the power and comply with the requirements. While using sufficiently large artificial buffers guarantees robustness with a mild power increase compared to the oracle, the fine-grained multi-task model improves the results, reducing the power consumption compared to the mean and meets all constraints. The heuristic enables significant computational time reduction.

Traffic speed prediction using deep learning has been the topic of many studies. In this paper, we analyse the performance of Graph Neural Network-based techniques during periods of traffic congestion. We first compare a selection of recently proposed techniques that claim to achieve good results using the METR-LA and PeMS-BAY data sets. We then investigate the performance of three of these approaches – GraphWaveNet, Spacetime Neural Network (STNN) and Spatio-Temporal Attention Wavenet (STAWnet) – during congested periods, using recurrent congestion patterns to set a threshold for general congestion through the entire traffic network. Our results show that performance deteriorates significantly during congested time periods, which is concerning, as traffic speed prediction is usually of most value during times of congestion. We also found that, while the above approaches perform almost equally in the absence of congestion, there are much bigger differences in performance during periods of congestion.

Anomaly detection is an important part of machine learning. Detection of outliers in the field of transportation can provide valid data for future traffic predictions or traffic flow analysis. This paper builds a model based on XGBoost to detect outliers in IoT data. The data is preprocessed first, followed by model building. Then we use the grid search to adjust the parameters and substitute the optimal parameters into the building model. To validate the model, we cross-checked it with two benchmark models, iFroset and Random Forest. The final experimental results show that the model constructed in this paper can accurately detect outliers in traffic flow and the accuracy is better than that of the baseline model. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Deep learning models have been demonstrated powerful in modeling complex spatio-temporal data for traffic prediction. In practice, effective deep traffic prediction models rely on large-scale traffic data, which is not always available in real-world scenarios. To alleviate the data scarcity issue, a promising way is to use cross-city transfer learning methods to fine-tune well-trained models from source cities with abundant data. However, existing approaches overlook the divergence between source and target cities, and thus, the trained model from source cities may contain noise or even harmful source knowledge. To address the problem, we propose CrossTReS, a selective transfer learning framework for traffic prediction that adaptively re-weights source regions to assist target fine-tuning. As a general framework for fine-tuning-based cross-city transfer learning, CrossTReS consists of a feature network, a weighting network, and a prediction model. We train the feature network with node- and edge-level domain adaptation techniques to learn generalizable spatial features for both source and target cities. We further train the weighting network via source-target joint meta-learning such that source regions helpful to target fine-tuning are assigned high weights. Finally, the prediction model is selectively trained on the source city with the learned weights to initialize target fine-tuning. We evaluate CrossTReS using real-world taxi and bike data, where under the same settings, CrossTReS outperforms state-of-the-art baselines by up to 8%. Moreover, the learned region weights offer interpretable visualization. © 2022 ACM.

In this article, we propose a new protection scheme for backbone networks to guarantee high service availability. The presented scheme does not require any reconfiguration immediately after the failure (i.e., it is proactive). At the same time, it does not require any reserved backup network resources either. To achieve these seemingly contradictory goals, we utilize the recent advancements in Machine Learning (ML) to implement a network intelligence that periodically re-allocates the unused capacity as protection bandwidth to meet the service availability requirements of each connection. Our goal is achieved by two components (1) predicting the traffic for the next period on each link, and (2) intelligently selecting the best fit dedicated protection scheme for the next period depending on the estimated unused (spare) bandwidth and the previous service availability violations. Note that re-allocating protection bandwidth affects neither the operational connections nor the current best practice of operators to over-provision network bandwidth to support elephant flows. Finally, we provide a case study on the real traffic from Energy Sciences Network (ESnet), a high-speed, international scientific backbone network. The key benefit of our framework is that adaptively utilizing the over-provisioned bandwidth for spare capacity is sufficient to improve the availability from three-nines to five-nines (in ESnet for the 30 examined connections). The drawback is negligible bandwidth limitations; the user perceives a minor and very temporal bandwidth limitation in less than 0.1% of the time.

In this article, we propose a new protection scheme for backbone networks to guarantee high service availability. The presented scheme does not require any reconfiguration immediately after the failure (i.e., it is proactive). At the same time, it does not require any reserved backup network resources either. To achieve these seemingly contradictory goals, we utilize the recent advancements in Machine Learning (ML) to implement a network intelligence that periodically re-allocates the unused capacity as protection bandwidth to meet the service availability requirements of each connection. Our goal is achieved by two components (1) predicting the traffic for the next period on each link, and (2) intelligently selecting the best fit dedicated protection scheme for the next period depending on the estimated unused (spare) bandwidth and the previous service availability violations. Note that re-allocating protection bandwidth affects neither the operational connections nor the current best practice of operators to over-provision network bandwidth to support elephant flows. Finally, we provide a case study on the real traffic from Energy Sciences Network (ESnet), a high-speed, international scientific backbone network. The key benefit of our framework is that adaptively utilizing the over-provisioned bandwidth for spare capacity is sufficient to improve the availability from three-nines to five-nines (in ESnet for the 30 examined connections). The drawback is negligible bandwidth limitations; the user perceives a minor and very temporal bandwidth limitation in less than 0.1% of the time.

Wireless NoC (WiNoC) has low latency and simple wiring, which can reduce the energy consumption caused by the metal interconnection in traditional NoC architectures. However, traditional time division based media access control (MAC) mechanism in WiNoC is not aware of different wireless interfaces' (WIs) traffic demands, resulting in an unreasonable distribution of wireless communication channels and degradation in performance. Hence, in order to dynamically allocate wireless channels to the WIs based on their traffic demands, a dynamic and traffic-aware MAC mechanism is required. In this paper, we design a traffic demand predictor for each WI based on its current and history traffic conditions. According to the predicted demands, we are able to allocate access to wireless channels dynamically and switch between two kinds of time division based MAC mechanisms. Simulations under various conditions indicate that the average delay decreases by 30% and 20% on average compared with a traditional MAC mechanism and an existing dynamic time division based one, respectively. Moreover, the network with the dynamic and traffic-aware MAC enters the saturation point at a higher packet injection rate., Part of proceedings: ISBN 978-1-7281-9201-7, QC 20230117

In this paper, a novel framework is proposed to enable a predictive deployment of unmanned aerial vehicles (UAVs) as temporary base stations (BSs) to complement ground cellular systems in face of downlink traffic overload. First, a novel learning approach, based on the weighted expectation maximization (WEM) algorithm, is proposed to estimate the user distribution and the downlink traffic demand. Next, to guarantee a truthful information exchange between the BS and UAVs, using the framework of contract theory, an offload contract is developed, and the sufficient and necessary conditions for having a feasible contract are analytically derived. Subsequently, an optimization problem is formulated to deploy an optimal UAV onto the hotspot area in a way that the utility of the overloaded BS is maximized. Simulation results show that the proposed WEM approach yields a prediction error of around 10%. Compared with the expectation maximization and k-mean approaches, the WEM method shows a significant advantage on the prediction accuracy, as the traffic load in the cellular system becomes spatially uneven. Furthermore, compared with two event-driven deployment schemes based on the closest-distance and maximal-energy metrics, the proposed predictive approach enables UAV operators to provide efficient communication service for hotspot users in terms of the downlink capacity, energy consumption and service delay. Simulation results also show that the proposed method significantly improves the revenues of both the BS and UAV networks, compared with two baseline schemes.

Road traffic forecasting is crucial in Intelligent Transportation Systems (ITS). To achieve accurate results, it is necessary to model the dynamic nature and the complex non-linear dependencies governing traffic. The goal is particularly challenging when the prediction involves more than just one traffic variable. This paper proposes a novel multi-task learning model, called AST-MTL, to perform multi-horizon predictions of the traffic flow and speed at the road network scale. The strategy combines a multilayer fully-connected neural network (FNN) and a multi-head attention mechanism to learn related tasks while improving generalization performance. The model also includes the graph convolutional network (GCNs) and the gated recurrent unit network (GRUs) to extract the spatial and temporal features of traffic conditions. Our experiments employ new sets of GPS data, called OBU data, to perform traffic prediction in the freeway and urban contexts. The experimental results prove our model can effectively perform multi-horizon traffic forecasting for different types of roads and outperform state-of-the-art models., SCOPUS: ar.j, info:eu-repo/semantics/published

In this article, we focus on resolving the traffic flow prediction, robot path planning, and motion coordination problems in large-scale warehousing robotics systems with thousand-robot networks. The warehousing environment is partitioned into several sectors, and a hierarchical framework is developed, which includes a centralized prediction and planning level and a decentralized local coordination level. In the centralized level, a traffic flow prediction algorithm is first proposed to predict the evolution of the robot density distribution in a future horizon and estimate the future traffic heat value of each sector. Based on this, the sector-level robot path can be generated in the time-expended sector graph by comprehensively considering the traveling distance and the predicted traffic heat value and will be dynamically updated by considering the most recent traffic information. In the coordination level, local cooperative A* algorithm, incorporated with the conflict-based searching strategy, is implemented within each sector to generate conflict-free road-level paths for all the robots in the sector simultaneously, and the rolling planning scheme is utilized in order to immediately react to robot motion uncertainties and communication disconnections. The effectiveness and practical applicability of the proposed approach are validated by large-scale simulations with more than one 1000 robots and real laboratory experiments. IEEE

In a lot of big cities, the traffic network is overloaded, with congestion and unnecessary emissions as consequence. Therefore, different traffic control methods are useful, especially in case of an incident. One key problem for traffic control is traffic prediction and the aim of this thesis is to develop, calibrate and evaluate a route flow model using only observed travel times and travel demand as input. The route flow model was used to calculate the metric link flow destination distribution, that presents to which destinations the travelers on a link are going in percentage.

Efficient communication and computing resource allocation is becoming a fundamental issue in wireless networks. Efficiency is most often defined in terms of throughput, utilization and spectral efficiency, while the required computational effort is often overlooked. In this paper, we focus on efficient and computationally lightweight downlink scheduling, and we propose a semi-persistent scheduler based on adaptive short term traffic prediction. We evaluate the performance of the proposed scheduler in terms of throughput, fairness, latency, and scheduling complexity. Our numerical results show that scheduling with prediction is a promising approach in improving network performance. The proposed semi-persistent scheduler performs equally well in terms of throughput, fairness, and latency as traditional proportional-fair scheduling, but at a significantly reduced computational cost., QC 20210609

This paper studies the utilization of machine and statistical learning methods for predicting encrypted user traffic. To this end, a reference system model and performance metrics for traffic prediction have been defined for enabling on-line training. Based on a collection of representative traffic data sets including various video and web traffic, two different classes of predictors have been evaluated. Our results show that very good prediction performance can be achieved using long short-term memory (LSTM) recurrent neural networks at the price of a significant computational cost for training., QC 20210609

In a lot of big cities, the traffic network is overloaded, with congestion and unnecessary emissions as consequence. Therefore, different traffic control methods are useful, especially in case of an incident. One key problem for traffic control is traffic prediction and the aim of this thesis is to develop, calibrate and evaluate a route flow model using only observed travel times and travel demand as input. The route flow model was used to calculate the metric link flow destination distribution, that presents to which destinations the travelers on a link are going in percentage.

In this paper, we presented a novel methodology for learning temporal point process based on the implementation of one-dimensional numerical integration techniques. The implementation of numerical methodology is used for linearizing negative maximum likelihood (neML) function to enable backpropagation of neML derivative. The presented approach is tested on highway toll dataset. Moreover, four different wellknown point process baseline models were compared: first-order and second-order polynomial Poisson inhomogeneous process and Hawkes with exponential and Gaussian kernel. The results showed that different numerical integration techniques influence the quality of the obtained models.

In this article, we focus on resolving the traffic flow prediction, robot path planning, and motion coordination problems in large-scale warehousing robotics systems with thousand-robot networks. The warehousing environment is partitioned into several sectors, and a hierarchical framework is developed, which includes a centralized prediction and planning level and a decentralized local coordination level. In the centralized level, a traffic flow prediction algorithm is first proposed to predict the evolution of the robot density distribution in a future horizon and estimate the future traffic heat value of each sector. Based on this, the sector-level robot path can be generated in the time-expended sector graph by comprehensively considering the traveling distance and the predicted traffic heat value and will be dynamically updated by considering the most recent traffic information. In the coordination level, local cooperative A* algorithm, incorporated with the conflict-based searching strategy, is implemented within each sector to generate conflict-free road-level paths for all the robots in the sector simultaneously, and the rolling planning scheme is utilized in order to immediately react to robot motion uncertainties and communication disconnections. The effectiveness and practical applicability of the proposed approach are validated by large-scale simulations with more than one 1000 robots and real laboratory experiments. IEEE

[ES] En la actualidad, uno de los principales desafíos a los que se enfrentan las grandes áreas metropolitanas es la congestión provocada por el tráfico, la cual se ha convertido en un problema importante al que se enfrentan las autoridades de cada ciudad. Para abordar este problema es necesario implementar una solución eficiente para controlar el tráfico que genere beneficios para los ciudadanos, como reducir los tiempos de viaje de los vehículos y, en consecuencia, el consumo de combustible, el ruido, y la contaminación ambiental. De hecho, al analizar adecuadamente la demanda de tráfico, es posible predecir las condiciones futuras del tráfico, y utilizar esa información para la optimización de las rutas tomadas por los vehículos. Este enfoque puede ser especialmente efectivo si se aplica en el contexto de los vehículos autónomos, que tienen un comportamiento más predecible, lo cual permite a los administradores de la ciudad mitigar los efectos de la congestión, como es la contaminación, al mejorar el flujo de tráfico de manera totalmente centralizada. La validación de este enfoque generalmente requiere el uso de simulaciones que deberían ser lo más realistas posible. Sin embargo, lograr altos grados de realismo puede ser complejo cuando los patrones de tráfico reales, definidos a través de una matriz de Origen/Destino (O-D) para los vehículos en una ciudad, son desconocidos, como ocurre la mayoría de las veces. Por lo tanto, la primera contribución de esta tesis es desarrollar una heurística iterativa para mejorar el modelado de la congestión de tráfico; a partir de las mediciones de bucle de inducción reales hechas por el Ayuntamiento de Valencia (España), pudimos generar una matriz O-D para la simulación de tráfico que se asemeja a la distribución de tráfico real. Si fuera posible caracterizar el estado del tráfico prediciendo las condiciones futuras del tráfico para optimizar la ruta de los vehículos automatizados, y si se pudieran tomar estas medidas para mit, [CA] En l'actualitat, un dels principals desafiaments als quals s'enfronten les grans àrees metropolitanes és la congestió provocada pel trànsit, que s'ha convertit en un problema important al qual s'enfronten les autoritats de cada ciutat. Per a abordar aquest problema és necessari implementar una solució eficient per a controlar el trànsit que genere beneficis per als ciutadans, com reduir els temps de viatge dels vehicles i, en conseqüència, el consum de combustible, el soroll, i la contaminació ambiental. De fet, en analitzar adequadament la demanda de trànsit, és possible predir les condicions futures del trànsit, i utilitzar aqueixa informació per a l'optimització de les rutes preses pels vehicles. Aquest enfocament pot ser especialment efectiu si s'aplica en el context dels vehicles autònoms, que tenen un comportament més predictible, i això permet als administradors de la ciutat mitigar els efectes de la congestió, com és la contaminació, en millorar el flux de trànsit de manera totalment centralitzada. La validació d'aquest enfocament generalment requereix l'ús de simulacions que haurien de ser el més realistes possible. No obstant això, aconseguir alts graus de realisme pot ser complex quan els patrons de trànsit reals, definits a través d'una matriu d'Origen/Destinació (O-D) per als vehicles en una ciutat, són desconeguts, com ocorre la majoria de les vegades. Per tant, la primera contribució d'aquesta tesi és desenvolupar una heurística iterativa per a millorar el modelatge de la congestió de trànsit; a partir dels mesuraments de bucle d'inducció reals fetes per l'Ajuntament de València (Espanya), vam poder generar una matriu O-D per a la simulació de trànsit que s'assembla a la distribució de trànsit real. Si fóra possible caracteritzar l'estat del trànsit predient les condicions futures del trànsit per a optimitzar la ruta dels vehicles automatitzats, i si es pogueren prendre aquestes mesures per a mitigar de manera preventiva els efectes de la congest, [EN] Currently, one of the main challenges that large metropolitan areas have to face is traffic congestion, which has become an important problem faced by city authorities. To address this problem, it becomes necessary to implement an efficient solution to control traffic that generates benefits for citizens, such as reducing vehicle journey times and, consequently, use of fuel, noise and environmental pollution. In fact, by properly analyzing traffic demand, it becomes possible to predict future traffic conditions, and to use that information for the optimization of the routes taken by vehicles. Such an approach becomes especially effective if applied in the context of autonomous vehicles, which have a more predictable behavior, thus enabling city management entities to mitigate the effects of traffic congestion and pollution by improving the traffic flow in a city in a fully centralized manner. Validating this approach typically requires the use of simulations, which should be as realistic as possible. However, achieving high degrees of realism can be complex when the actual traffic patterns, defined through an Origin/Destination (O-D) matrix for the vehicles in a city, are unknown, as occurs most of the times. Thus, the first contribution of this thesis is to develop an iterative heuristic for improving traffic congestion modeling; starting from real induction loop measurements made available by the City Hall of Valencia, Spain, we were able to generate an O-D matrix for traffic simulation that resembles the real traffic distribution. If it were possible to characterize the state of traffic by predicting future traffic conditions for optimizing the route of automated vehicles, and if these measures could be taken to preventively mitigate the effects of congestion with its related problems, the overall traffic flow could be improved. Thereby, the second contribution of this thesis was to develop a Traffic Prediction Equation to characterize the different streets

City-wide travel time prediction in real-time is an important enabler for efficient use of the road network. It can be used in traveler information to enable more efficient routing of individual vehicles as well as decision support for traffic management applications such as directed information campaigns or incident management. 3D speed maps have been shown to be a promising methodology for revealing day-to-day regularities of city-level travel times and possibly also for short-term prediction. In this paper, we aim to further evaluate and benchmark the use of 3D speed maps for short-term travel time prediction and to enable scenario-based evaluation of traffic management actions we also evaluate the framework for traffic flow prediction. The 3D speed map methodology is adapted to short-term prediction and benchmarked against historical mean as well as against Probabilistic Principal Component Analysis (PPCA). The benchmarking and analysis are made using one year of travel time and traffic flow data for the city of Stockholm, Sweden. The result of the case study shows very promising results of the 3D speed map methodology for short-term prediction of both travel times and traffic flows. The modified version of the 3D speed map prediction outperforms the historical mean prediction as well as the PPCA method. Further work includes an extended evaluation of the method for different conditions in terms of underlying sensor infrastructure, preprocessing and spatio-temporal aggregation as well as benchmarking against other prediction methods., QC 20190502

City-wide travel time prediction in real-time is an important enabler for efficient use of the road network. It can be used in traveler information to enable more efficient routing of individual vehicles as well as decision support for traffic management applications such as directed information campaigns or incident management. 3D speed maps have been shown to be a promising methodology for revealing day-to-day regularities of city-level travel times and possibly also for short-term prediction. In this paper, we aim to further evaluate and benchmark the use of 3D speed maps for short-term travel time prediction and to enable scenario-based evaluation of traffic management actions we also evaluate the framework for traffic flow prediction. The 3D speed map methodology is adapted to short-term prediction and benchmarked against historical mean as well as against Probabilistic Principal Component Analysis (PPCA). The benchmarking and analysis are made using one year of travel time and traffic flow data for the city of Stockholm, Sweden. The result of the case study shows very promising results of the 3D speed map methodology for short-term prediction of both travel times and traffic flows. The modified version of the 3D speed map prediction outperforms the historical mean prediction as well as the PPCA method. Further work includes an extended evaluation of the method for different conditions in terms of underlying sensor infrastructure, preprocessing and spatio-temporal aggregation as well as benchmarking against other prediction methods., QC 20190531

City-wide travel time prediction in real-time is an important enabler for efficient use of the road network. It can be used in traveler information to enable more efficient routing of individual vehicles as well as decision support for traffic management applications such as directed information campaigns or incident management. 3D speed maps have been shown to be a promising methodology for revealing day-to-day regularities of city-level travel times and possibly also for short-term prediction. In this paper, we aim to further evaluate and benchmark the use of 3D speed maps for short-term travel time prediction and to enable scenario-based evaluation of traffic management actions we also evaluate the framework for traffic flow prediction. The 3D speed map methodology is adapted to short-term prediction and benchmarked against historical mean as well as against Probabilistic Principal Component Analysis (PPCA). The benchmarking and analysis are made using one year of travel time and traffic flow data for the city of Stockholm, Sweden. The result of the case study shows very promising results of the 3D speed map methodology for short-term prediction of both travel times and traffic flows. The modified version of the 3D speed map prediction outperforms the historical mean prediction as well as the PPCA method. Further work includes an extended evaluation of the method for different conditions in terms of underlying sensor infrastructure, preprocessing and spatio-temporal aggregation as well as benchmarking against other prediction methods., QC 20190531

[ES] En la actualidad, uno de los principales desafíos a los que se enfrentan las grandes áreas metropolitanas es la congestión provocada por el tráfico, la cual se ha convertido en un problema importante al que se enfrentan las autoridades de cada ciudad. Para abordar este problema es necesario implementar una solución eficiente para controlar el tráfico que genere beneficios para los ciudadanos, como reducir los tiempos de viaje de los vehículos y, en consecuencia, el consumo de combustible, el ruido, y la contaminación ambiental. De hecho, al analizar adecuadamente la demanda de tráfico, es posible predecir las condiciones futuras del tráfico, y utilizar esa información para la optimización de las rutas tomadas por los vehículos. Este enfoque puede ser especialmente efectivo si se aplica en el contexto de los vehículos autónomos, que tienen un comportamiento más predecible, lo cual permite a los administradores de la ciudad mitigar los efectos de la congestión, como es la contaminación, al mejorar el flujo de tráfico de manera totalmente centralizada. La validación de este enfoque generalmente requiere el uso de simulaciones que deberían ser lo más realistas posible. Sin embargo, lograr altos grados de realismo puede ser complejo cuando los patrones de tráfico reales, definidos a través de una matriz de Origen/Destino (O-D) para los vehículos en una ciudad, son desconocidos, como ocurre la mayoría de las veces. Por lo tanto, la primera contribución de esta tesis es desarrollar una heurística iterativa para mejorar el modelado de la congestión de tráfico; a partir de las mediciones de bucle de inducción reales hechas por el Ayuntamiento de Valencia (España), pudimos generar una matriz O-D para la simulación de tráfico que se asemeja a la distribución de tráfico real. Si fuera posible caracterizar el estado del tráfico prediciendo las condiciones futuras del tráfico para optimizar la ruta de los vehículos automatizados, y si se pudieran tomar estas medidas para mit, [CA] En l'actualitat, un dels principals desafiaments als quals s'enfronten les grans àrees metropolitanes és la congestió provocada pel trànsit, que s'ha convertit en un problema important al qual s'enfronten les autoritats de cada ciutat. Per a abordar aquest problema és necessari implementar una solució eficient per a controlar el trànsit que genere beneficis per als ciutadans, com reduir els temps de viatge dels vehicles i, en conseqüència, el consum de combustible, el soroll, i la contaminació ambiental. De fet, en analitzar adequadament la demanda de trànsit, és possible predir les condicions futures del trànsit, i utilitzar aqueixa informació per a l'optimització de les rutes preses pels vehicles. Aquest enfocament pot ser especialment efectiu si s'aplica en el context dels vehicles autònoms, que tenen un comportament més predictible, i això permet als administradors de la ciutat mitigar els efectes de la congestió, com és la contaminació, en millorar el flux de trànsit de manera totalment centralitzada. La validació d'aquest enfocament generalment requereix l'ús de simulacions que haurien de ser el més realistes possible. No obstant això, aconseguir alts graus de realisme pot ser complex quan els patrons de trànsit reals, definits a través d'una matriu d'Origen/Destinació (O-D) per als vehicles en una ciutat, són desconeguts, com ocorre la majoria de les vegades. Per tant, la primera contribució d'aquesta tesi és desenvolupar una heurística iterativa per a millorar el modelatge de la congestió de trànsit; a partir dels mesuraments de bucle d'inducció reals fetes per l'Ajuntament de València (Espanya), vam poder generar una matriu O-D per a la simulació de trànsit que s'assembla a la distribució de trànsit real. Si fóra possible caracteritzar l'estat del trànsit predient les condicions futures del trànsit per a optimitzar la ruta dels vehicles automatitzats, i si es pogueren prendre aquestes mesures per a mitigar de manera preventiva els efectes de la congest, [EN] Currently, one of the main challenges that large metropolitan areas have to face is traffic congestion, which has become an important problem faced by city authorities. To address this problem, it becomes necessary to implement an efficient solution to control traffic that generates benefits for citizens, such as reducing vehicle journey times and, consequently, use of fuel, noise and environmental pollution. In fact, by properly analyzing traffic demand, it becomes possible to predict future traffic conditions, and to use that information for the optimization of the routes taken by vehicles. Such an approach becomes especially effective if applied in the context of autonomous vehicles, which have a more predictable behavior, thus enabling city management entities to mitigate the effects of traffic congestion and pollution by improving the traffic flow in a city in a fully centralized manner. Validating this approach typically requires the use of simulations, which should be as realistic as possible. However, achieving high degrees of realism can be complex when the actual traffic patterns, defined through an Origin/Destination (O-D) matrix for the vehicles in a city, are unknown, as occurs most of the times. Thus, the first contribution of this thesis is to develop an iterative heuristic for improving traffic congestion modeling; starting from real induction loop measurements made available by the City Hall of Valencia, Spain, we were able to generate an O-D matrix for traffic simulation that resembles the real traffic distribution. If it were possible to characterize the state of traffic by predicting future traffic conditions for optimizing the route of automated vehicles, and if these measures could be taken to preventively mitigate the effects of congestion with its related problems, the overall traffic flow could be improved. Thereby, the second contribution of this thesis was to develop a Traffic Prediction Equation to characterize the different streets

City-wide travel time prediction in real-time is an important enabler for efficient use of the road network. It can be used in traveler information to enable more efficient routing of individual vehicles as well as decision support for traffic management applications such as directed information campaigns or incident management. 3D speed maps have been shown to be a promising methodology for revealing day-to-day regularities of city-level travel times and possibly also for short-term prediction. In this paper, we aim to further evaluate and benchmark the use of 3D speed maps for short-term travel time prediction and to enable scenario-based evaluation of traffic management actions we also evaluate the framework for traffic flow prediction. The 3D speed map methodology is adapted to short-term prediction and benchmarked against historical mean as well as against Probabilistic Principal Component Analysis (PPCA). The benchmarking and analysis are made using one year of travel time and traffic flow data for the city of Stockholm, Sweden. The result of the case study shows very promising results of the 3D speed map methodology for short-term prediction of both travel times and traffic flows. The modified version of the 3D speed map prediction outperforms the historical mean prediction as well as the PPCA method. Further work includes an extended evaluation of the method for different conditions in terms of underlying sensor infrastructure, preprocessing and spatio-temporal aggregation as well as benchmarking against other prediction methods., QC 20190531

City-wide travel time prediction in real-time is an important enabler for efficient use of the road network. It can be used in traveler information to enable more efficient routing of individual vehicles as well as decision support for traffic management applications such as directed information campaigns or incident management. 3D speed maps have been shown to be a promising methodology for revealing day-to-day regularities of city-level travel times and possibly also for short-term prediction. In this paper, we aim to further evaluate and benchmark the use of 3D speed maps for short-term travel time prediction and to enable scenario-based evaluation of traffic management actions we also evaluate the framework for traffic flow prediction. The 3D speed map methodology is adapted to short-term prediction and benchmarked against historical mean as well as against Probabilistic Principal Component Analysis (PPCA). The benchmarking and analysis are made using one year of travel time and traffic flow data for the city of Stockholm, Sweden. The result of the case study shows very promising results of the 3D speed map methodology for short-term prediction of both travel times and traffic flows. The modified version of the 3D speed map prediction outperforms the historical mean prediction as well as the PPCA method. Further work includes an extended evaluation of the method for different conditions in terms of underlying sensor infrastructure, preprocessing and spatio-temporal aggregation as well as benchmarking against other prediction methods., QC 20190531

City-wide travel time prediction in real-time is an important enabler for efficient use of the road network. It can be used in traveler information to enable more efficient routing of individual vehicles as well as decision support for traffic management applications such as directed information campaigns or incident management. 3D speed maps have been shown to be a promising methodology for revealing day-to-day regularities of city-level travel times and possibly also for short-term prediction. In this paper, we aim to further evaluate and benchmark the use of 3D speed maps for short-term travel time prediction and to enable scenario-based evaluation of traffic management actions we also evaluate the framework for traffic flow prediction. The 3D speed map methodology is adapted to short-term prediction and benchmarked against historical mean as well as against Probabilistic Principal Component Analysis (PPCA). The benchmarking and analysis are made using one year of travel time and traffic flow data for the city of Stockholm, Sweden. The result of the case study shows very promising results of the 3D speed map methodology for short-term prediction of both travel times and traffic flows. The modified version of the 3D speed map prediction outperforms the historical mean prediction as well as the PPCA method. Further work includes an extended evaluation of the method for different conditions in terms of underlying sensor infrastructure, preprocessing and spatio-temporal aggregation as well as benchmarking against other prediction methods., QC 20190531

City-wide travel time prediction in real-time is an important enabler for efficient use of the road network. It can be used in traveler information to enable more efficient routing of individual vehicles as well as decision support for traffic management applications such as directed information campaigns or incident management. 3D speed maps have been shown to be a promising methodology for revealing day-to-day regularities of city-level travel times and possibly also for short-term prediction. In this paper, we aim to further evaluate and benchmark the use of 3D speed maps for short-term travel time prediction and to enable scenario-based evaluation of traffic management actions we also evaluate the framework for traffic flow prediction. The 3D speed map methodology is adapted to short-term prediction and benchmarked against historical mean as well as against Probabilistic Principal Component Analysis (PPCA). The benchmarking and analysis are made using one year of travel time and traffic flow data for the city of Stockholm, Sweden. The result of the case study shows very promising results of the 3D speed map methodology for short-term prediction of both travel times and traffic flows. The modified version of the 3D speed map prediction outperforms the historical mean prediction as well as the PPCA method. Further work includes an extended evaluation of the method for different conditions in terms of underlying sensor infrastructure, preprocessing and spatio-temporal aggregation as well as benchmarking against other prediction methods.

City-wide travel time prediction in real-time is an important enabler for efficient use of the road network. It can be used in traveler information to enable more efficient routing of individual vehicles as well as decision support for traffic management applications such as directed information campaigns or incident management. 3D speed maps have been shown to be a promising methodology for revealing day-to-day regularities of city-level travel times and possibly also for short-term prediction. In this paper, we aim to further evaluate and benchmark the use of 3D speed maps for short-term travel time prediction and to enable scenario-based evaluation of traffic management actions we also evaluate the framework for traffic flow prediction. The 3D speed map methodology is adapted to short-term prediction and benchmarked against historical mean as well as against Probabilistic Principal Component Analysis (PPCA). The benchmarking and analysis are made using one year of travel time and traffic flow data for the city of Stockholm, Sweden. The result of the case study shows very promising results of the 3D speed map methodology for short-term prediction of both travel times and traffic flows. The modified version of the 3D speed map prediction outperforms the historical mean prediction as well as the PPCA method. Further work includes an extended evaluation of the method for different conditions in terms of underlying sensor infrastructure, preprocessing and spatio-temporal aggregation as well as benchmarking against other prediction methods., QC 20190531

Short-term traffic prediction allows Intelligent Transport Systems to proactively respond to events before they happen. With the rapid increase in the amount, quality, and detail of traffic data, new techniques are required that can exploit the information in the data in order to provide better results while being able to scale and cope with increasing amounts of data and growing cities. We propose and compare three models for short-term road traffic density prediction based on Long Short-Term Memory (LSTM) neural networks. We have trained the models using real traffic data collected by Motorway Control System in Stockholm that monitors highways and collects flow and speed data per lane every minute from radar sensors. In order to deal with the challenge of scale and to improve prediction accuracy, we propose to partition the road network into road stretches and junctions, and to model each of the partitions with one or more LSTM neural networks. Our evaluation results show that partitioning of roads improves the prediction accuracy by reducing the root mean square error by the factor of 5. We show that we can reduce the complexity of LSTM network by limiting the number of input sensors, on average to 35% of the original number, without compromising the prediction accuracy., QC 20181015

Traffic prediction is a critical task for intelligent transportation systems (ITS). Prediction at intersections is challenging as it involves various participants, such as vehicles, cyclists, and pedestrians. In this paper, we propose a novel approach for the accurate intersection traffic prediction by introducing extra data sources other than road traffic volume data into the prediction model. In particular, we take advantage of the data collected from the reports of road accidents and roadworks happening near the intersections. In addition, we investigate two types of learning schemes, namely batch learning and online learning. Three popular ensemble decision tree models are used in the batch learning scheme, including Gradient Boosting Regression Trees (GBRT), Random Forest (RF) and Extreme Gradient Boosting Trees (XGBoost), while the Fast Incremental Model Trees with Drift Detection (FIMT-DD) model is adopted for the online learning scheme. The proposed approach is evaluated using public data sets released by the Victorian Government of Australia. The results indicate that the accuracy of intersection traffic prediction can be improved by incorporating nearby accidents and roadworks information.