Search

The paper presents a new approach for the prediction of load active power 24 h ahead using an attended sequential encoder and stacked decoder model with Long Short-Term Memory cells. The load data are owned by the New York Independent System Operator (NYISO) and is dated from the years 2014–2017. Due to dynamics in the load patterns, multiple short pieces of training on pre-filtered data are executed in combination with the transfer learning concept. The evaluation is done by direct comparison with the results of the NYISO forecast and additionally under consideration of several benchmark methods. The results in terms of the Mean Absolute Percentage Error range from 1.5% for the highly loaded New York City zone to 3% for the Mohawk Valley zone with rather small load consumption. The execution time of a day ahead forecast including the training on a personal computer without GPU accounts to 10 s on average. [ABSTRACT FROM AUTHOR]

Urban ride-hailing demand prediction is a crucial but challenging task for intelligent transportation system construction. Predictable ride-hailing demand can facilitate more reasonable vehicle scheduling and online car-hailing platform dispatch. Conventional deep learning methods with no external structured data can be accomplished via hybrid models of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) by meshing plentiful pixel-level labeled data, but data sparsity of high grid granularity in spatial perspective and limited learning capabilities of long-term dependencies in temporal perspective are still two striking bottlenecks. To address these problems, we propose a novel virtual graph modeling approach to focus on significant demand regions and a novel Deep Multi-View Spatio-temporal Virtual Graph Neural Network (DMVST-VGNN) to strengthen the learning capabilities of spatial dynamics and long-term temporal dependencies. Specifically, DMVST-VGNN integrates structures of 1D CNN, Multi-Graph Attention Neural Network and Transformer Network, which correspond to short-term temporal dynamics view, spatial dynamics view and long-term temporal dynamics view respectively. In this paper, multiple experiments are conducted on two large-scale New York City datasets in higher granularity prediction scenes. And the experimental results demonstrate the effectiveness of DMVST-VGNN framework in ride-hailing demand prediction, no matter in spatial scale or the temporal scale. [ABSTRACT FROM AUTHOR]

• A stepwise explainable deep learning formulation using linear regression (LR) and a recurrent neural network. • Facilitate quota-based planning to balance utilization rates between for-hire vehicles (FHVs) and traditional taxis. • Data analysis from New York City Taxi & Limousine Commission to observe the correlation between FHV and regular taxis. • Real-world data sets examined for coupled LR and long short-term memory (LSTM) framework. As app-based ride-hailing services have been widely adopted within existing traditional taxi markets, researchers have been devoted to understand the important factors that influence the demand of the new mobility. Econometric models (EMs) are mainly utilized to interpret the significant factors of the demand, and deep neural networks (DNNs) have been recently used to improve the forecasting performance by capturing complex patterns in the large datasets. However, to mitigate possible (induced) traffic congestion and balance utilization rates for the current taxi drivers, an effective strategy of proactively managing a quota system for both emerging services and regular taxis is still critically needed. This paper aims to systematically design an explainable deep learning model capable of assessing the quota system balancing the demand volumes between two modes. A two-stage interpretable machine learning modeling framework was developed by a linear regression (LR) model, coupled with a neural network layered by long short-term memory (LSTM). The first stage investigates the correlation between the existing taxis and on-demand ride-hailing services while controlling for other explanatory variables. The second stage fulfills the long short-term memory (LSTM) network structure, capturing the residuals from the first estimation stage in order to enhance the forecasting performance. The proposed stepwise modeling approach (LR-LSTM) forecasts the demand of taxi rides, and it is implemented in the application of pick-up demand prediction using New York City (NYC) taxi data. The experiment result indicates that the integrated model can capture the inter-relationships between existing taxis and ride-hailing services as well as identify the influence of additional factors, namely, the day of the week, weather, and holidays. Overall, this modeling approach can be applied to construct an effective active demand management (ADM) for the short-term period as well as a quota control strategy between on-demand ride-hailing services and traditional taxis. [ABSTRACT FROM AUTHOR]

Monitoring the distribution of vehicles across the city is of great importance for urban traffic control. In particular, information on the number of vehicles entering and leaving a city, or moving between urban areas, gives a valuable estimate on potential bottlenecks and congestions. The possibility of predicting such flows in advance is even more beneficial, allowing for timely traffic management strategies and targeted congestion warnings. Our work is inserted in the context of short-term forecasting, aiming to predict rapid changes and sudden variations in the traffic volume, beyond the general trend. Moreover, it concurrently targets multiple locations in the city, providing an instant prediction outcome comprising the future distribution of vehicles across several urban locations. Specifically, we propose a multi-target deep learning regressor for simultaneous predictions of traffic volumes, in multiple entry and exit points among city neighborhoods. The experiment focuses on an hourly forecasting of the amount of vehicles accessing and moving between New York City neighborhoods through the Metropolitan Transportation Authority (MTA) bridges and tunnels. By leveraging a single training process for all location points, and an instant one-step volume inference for every location at each time update, our sequential modeling approach is able to grasp rapid variations in the time series and process the collective information of all entry and exit points, whose distinct predicted values are outputted at once. The multi-target model, based on long short-term memory (LSTM) recurrent neural network layers, was tested on a real-world dataset, achieving an average prediction error of 7% and demonstrating its feasibility for short-term spatially-distributed urban traffic forecasting. [ABSTRACT FROM AUTHOR]