Search

The critical nature of vehicular communications requires their extensive testing and evaluation. Analytical models can represent an attractive and cost-effective approach for such evaluation if they can adequately model all underlying effects that impact the performance of vehicular communications. Several analytical models have been proposed to date to model vehicular communications based on the IEEE 802.11p (or DSRC) standard. However, existing models normally model in detail the MAC (Medium Access Control), and generally simplify the propagation and interference effects. This reduces their value as an alternative to evaluate the performance of vehicular communications. This paper addresses this gap, and presents new analytical models that accurately model the performance of vehicle-to-vehicle communications based on the IEEE 802.11p standard. The models jointly account for a detailed modeling of the propagation and interference effects, as well as the impact of the hidden terminal problem. The model quantifies the PDR (Packet Delivery Ratio) as a function of the distance between transmitter and receiver. The paper also presents new analytical models to quantify the probability of the four different types of packet errors in IEEE 802.11p. In addition, the paper presents the first analytical model capable to accurately estimate the Channel Busy Ratio (CBR) metric even under high channel load levels. All the analytical models are validated by means of simulation for a wide range of parameters, including traffic densities, packet transmission frequencies, transmission power levels, data rates and packet sizes. An implementation of the models is provided openly to facilitate their use by the community. [ABSTRACT FROM AUTHOR]

Mobile edge computing has been an important supplement for traditional cloud computing architecture to offer low-delay computing services to mobile users. However, it is in general impossible for edge service providers to overdeploy so much edge resources to satisfy the rapidly increasing while diverse user demands. In this paper, we study a mobile edge computing system consisting of a service platform, cloudlets joining the system, and mobile users. In this study, we focus on a profit-driven perspective such that the service platform purchases computation resource from the resource-rich cloudlets and makes profit by processing tasks from user side. The design objective is to maximize the platform profit subject to budget constraint and stringent delay requirements for task processing. We formulate this problem as a mixed integer programming problem. Due to the NP-hardness of the problem, we design a logic based Benders decomposition algorithm as the offline solution. We further study the scenario where the task arrivals from user side and resource availability at the cloudlets are both stochastic and unknown in advance. We accordingly propose a Multi-Armed Bandit learning based resource purchasing and greedy task scheduling algorithm for the online scenario. Simulations results show the high performance of our proposed algorithms. [ABSTRACT FROM AUTHOR]

In vehicular networks, authentication technology provides a basic security means to achieve trusted communication between legitimate vehicles. Revocation checking for vehicle certificates is an indispensable procedure in the process of authentication to protect vehicular networks from attacks by non-legitimate vehicles. However, revocation checking introduces procedures that requires additional time to process which challenges latency-sensitive applications in vehicular networks. This challenge grows more evidently when considering the factor of privacy preservation. In this paper, we propose to offload partial revocation task to network edges to lighten the revocation process in vehicles. Particularly, we design a method to achieve decentralized Global Certificate Revocation List (GCRL) management in network edges using permissioned blockchain technologies. In the method, both tamper-proof property and quick synchronization of the GCRL are guaranteed. Besides, our method can detect illegal revocation behaviours by validation in vehicles. Finally, we build a prototype of our proposed solution based on Hyperledger Fabric, and compare with Proof-of-Work scheme in terms of blockchain synchronization latency performance. [ABSTRACT FROM AUTHOR]

Autonomous electric vehicles (AEVs) are gaining ground around the world. They are equipped with intelligent decision-making capabilities that allow them to optimize on their battery usage and engage in energy trading for profit maximization. This paper envisions a market model, where energy aggregators considers buying and selling electricity from AEVs. In this system, the aggregators reside on cloudlets at the edge of a cloud computing system for prompt communication and negotiation with AEVs. Whether they are parked or en-route, AEVs can be crowdsourced to provide energy to consumers at needed times. This study proposes double auction models to incentivize AEV agents to participate in the market based on their time preferences and energy pricing. The proposed system implements dynamic pricing structures, which are applicable to various scenarios of energy trading. To evaluate the proposed system, this paper provides extensive theoretical analysis and simulation experiments to demonstrate that the proposed auctioning models are computationally efficient, truthful, individually rational, and budget balanced. [ABSTRACT FROM AUTHOR]

The Internet of vehicles (IoV) is a large information interaction network that collects information on vehicles, roads and pedestrians. One of the important uses of vehicle networks is to meet the entertainment needs of driving users through communication between vehicles and roadside units (RSUs). Due to the limited storage space of RSUs, determining the content cached in each RSU is a key challenge. With the development of 5G and video editing technology, short video systems have become increasingly popular. Current widely used cache update methods, such as partial file precaching and content popularity- and user interest-based determination, are inefficient for such systems. To solve this problem, this paper proposes a QoE-driven edge caching method for the IoV based on deep reinforcement learning. First, a class-based user interest model is established. Compared with the traditional file popularity- and user interest distribution-based cache update methods, the proposed method is more suitable for systems with a large number of small files. Second, a quality of experience (QoE)-driven RSU cache model is established based on the proposed class-based user interest model. Third, a deep reinforcement learning method is designed to address the QoE-driven RSU cache update issue effectively. The experimental results verify the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

This paper proposes a cloud-assisted joint charging scheduling and energy management framework for unmanned aerial vehicle (UAV) networks. For charging the UAVs those are extremely power hungry, charging towers are considered for plug-and-play charging during run-time operations. The charging towers should be cost-effective, thus it is equipped with photovoltaic power generation and energy storage systems functionalities. Furthermore, the towers should be cooperative for more cost-effectiveness by intelligent energy sharing. Based on the needs and setting, this paper proposes 1) charging scheduling between UAVs and towers and 2) cooperative energy managements among towers. For charging scheduling, the UAVs and towers should be scheduled for maximizing charging energy amounts and the scheduled pairs should determine charging energy allocation amounts. Here, two decisions are correlated, i.e., it is a non-convex problem. We re-formulate the non-convex to convex for guaranteeing optimal solutions. Lastly, the cooperative energy sharing among towers is designed and implemented with multi-agent deep reinforcement learning and then intelligent energy sharing can be realized. We can observe that the two methods are related and it should be managed, coordinated, and harmonized by a centralized orchestration manager under the consideration of fairness, energy-efficiency, and cost-effectiveness. Our data-intensive performance evaluation verifies that our proposed framework achieves desired performance. [ABSTRACT FROM AUTHOR]

Resource-constrained end devices can offload computation to backend clouds. The stochastic wireless channel that an end device is connected to can introduce bursty computation demand to the cloud. Specifically, under good channel conditions, a device can transmit more data to the cloud, which consequently yields higher instantaneous computation demand. Conversely, poor channel conditions can result in lower instantaneous demand. The performance indicator for such a mobile cloud computing system is the average of the response time, which is the time span from the arrival of the computation demand at the backend cloud instance to the completion of its execution. The question we target in this paper is how resources should be provisioned for the backend cloud instance to address this bursty computation demand and guarantee a desired quality-of-service (QoS), namely, a user-specified average response time. To answer this question, we model the mobile cloud computing system as two tandem queues. We analyze this queueing network using the fluid flow analysis framework, and derive the analytical relationship between the required resource capacity at the backend cloud instance and the desired QoS, given the workload generation process at the end device and the wireless channel conditions. Having obtained the required resource capacity for a desired QoS, we then determine whether it is economical to provision this resource capacity by subscribing to the traditional static instance or the recently introduced burstable instance offered by public cloud providers. Finally, trace-driven simulations validate our theoretical results. [ABSTRACT FROM AUTHOR]

Edge computing has been regarded as an enabling technology for supporting future smart applications, such as industrial Internet of Things. In this paper, a novel computation offloading framework for edge computing is proposed. Unlike existing studies, this work considers that end users can intentionally reserve some time for local pre-processing before requesting the computation offloading service (instead of always declaring their offloading requests immediately when heavy-duty tasks are generated). By doing so, each task’s offloading cost may decrease because of less edge resource demand, while the delay cost may increase due to the later report of its offloading request. Furthermore, end users can select their preferred priority levels in the offloading scheduling by paying premium service charges. To maximize the individual utility, each end user may strategically and jointly determine its local pre-processing time-length and priority selection in computation offloading. For characterizing strategic interactions among end users and the quality-of-service (QoS) of the scheduling system with congested nature, a computation offloading game built upon a queueing model is formulated. On top of this, a revenue maximization problem for the interest of edge operator is also investigated. Simulations evaluate the performance of the proposed solution, and shows its superiority over counterparts. [ABSTRACT FROM AUTHOR]

In this paper, a new game-theoretic multi-layer computing resource and network resource allocation algorithm is proposed for computation offloading in Multi-access Edge Computing (MEC) networks. We establish a new multi-layer system model for Data Center Operators and develop resource allocation relation between the MEC data center operators and users. We also investigate the matching relationship between the cloudlets and users. Based on the proposed multi-layer allocation algorithm, a joint optimization framework is delivered to realize the allocation of computing resources and communication channels in MEC. Simulation results show that the proposed algorithm provides effective solution for the problem of cloudlets allocation in MEC networks, and can significantly improve the computing and communication capabilities in the presence of user heterogeneity. [ABSTRACT FROM AUTHOR]

The aim of the paper is to define a limit performance of highly efficient battery electric quadricycles for urban mobility. The vehicle is employed for an energy efficiency competition in which urban concepts compete. A multi-physics (thermo-electro-mechanical) Tank To Wheels (TTW) model has been developed and validated. Given the information on the track route (track map and elevation) and on the throttle input command, the model computes the vehicle power demand and cruising speed. The model is validated by means of both indoor and outdoor experimental tests. The validated model is employed for the optimization of the transmission gear ratio and of the driving strategy to minimize the overall energy consumption on a given track. Design variables are related to the transmission gear ratio and to the throttle command profile. The algorithm aims to minimize the energy consumption, including constraints on the maximum current provided by the battery and on the maximum time available to complete the lap. Comparison with some common driving strategies confirmed the effectiveness of the proposed solution, with a foreseen 9% reduction of the vehicle overall energy demand. The single seater ultra-efficient electric vehicle, compared to other urban quadricycles, has a battery capacity ten times lower and a 50% longer driving range. [ABSTRACT FROM AUTHOR]

Computation offloading is an effective method in mobile edge computing (MEC) to relieve user equipment (UE) from the limited computation resource and battery capacity. Meanwhile, simultaneous wireless information and power transmission (SWIPT) can be applied to MEC to extend the operating time of the equipment. However, in multi-user network environment, diverse computation task requirements and changeable network channel states make it challenging to obtain offloading strategy timely and accurately. To address the issue, we propose an intelligent computation offloading scheme (iCOS) based on enhanced priority deep deterministic policy gradient (EPDDPG) algorithm to minimize the energy consumption of all the UEs by jointly optimizing the offloading decision, the central processing unit (CPU) frequency and the power split ratio in a dynamic SWIPT-MEC network. In particular, we improve the traditional fully-connected network structure to obtain both discrete and continuous action outputs, and accelerate neural network parameter updates by using prioritized experience tuples. Furthermore, we use dynamic voltage and frequency scaling (DVFS) technology to dynamically adjust the CPU frequency of local computing, and employ SWIPT technology to balance the charging and communication according to the obtained strategy. Simulation results show that the algorithm proposed in this paper can effectively reduce the energy cost of UEs, and complete more computation tasks within the delay limit. [ABSTRACT FROM AUTHOR]

This paper proposes a new reentry trajectory generation method, which mainly comprises two parts: reentry profile design and trajectory optimization. Different from conventional methods that design angle-of-attack (AOA) and bank-angle profiles, a height-range profile is proposed in this paper. Using this profile, the AOA can be directly derived and the quasi-equilibrium glide condition is easily satisfied. In addition, the bank angle is analytically derived with the heading error, with only one reversal. Finally, the original problem is transformed into a parameter optimization problem and solved by an improved particle swarm optimization (PSO) method. In PSO, a comparison principle is proposed to tackle constraints and three modifications are applied to the swarm evolution to enhance the searching capacity. To conquer disturbances, an online profile updating strategy is developed based on the nominal profile, so complicated work of designing a trajectory tracker is avoided. Simulation validates the effectiveness of the proposed method and demonstrates that the improved PSO is comparable to the pseudospectral method and is better than the basic PSO. [ABSTRACT FROM AUTHOR]

The tunneling construction in underground DC Metro Systems is mainly based on the bored tunnel method and the cut-and-cover method. Therefore, the stray current assessments and mitigation actions should be tailored according to which method of tunnel construction is used. This paper presents a topologically accurate model for assessing the dynamic stray current picture in cut-and-cover sections of DC metro systems. The dynamic stray current evaluation can provide an indication to the extent of the corrosion problem in the supporting and third-party infrastructures of the system. In this paper, the dynamic evaluations are based on a combination of various ideal and realistic train operation scenarios. [ABSTRACT FROM PUBLISHER]

Characterization and linearization of RF power amplifiers (PAs) are key issues of fifth-generation wireless communication systems, especially when high peak-to-average ratio waveforms are introduced. Recently, deep learning methods have achieved great success in numerous domains including wireless physical-layer. However, there has been limited work in using deep learning for PAs behavioral modeling and linearization. In this paper, we make a bridge between memory effects of the nonlinear PAs and memory of bidirectional long short-term memory (BiLSTM) neural networks. We then build a BiLSTM-based behavioral modeling architecture and its accompanying digital predistortion (DPD) model by reconciling a non causality concern. Next, an additional model is proposed in this paper to mitigate uncertainty of the tested PA when transforming phases. The experimental results demonstrate the effectiveness of the proposed scheme, in which the adequately trained networks are capable of characterizing the PA, and the artificial intelligence-based DPD shows promising linearization performance when considering the tested PAs inherent unpredictability. [ABSTRACT FROM AUTHOR]

State of charge (SOC) estimation of lithium-ion batteries has been extensively studied and the estimation accuracy was mainly investigated through the development of various battery models and dynamic estimation algorithms. All battery models, however, contain inherent model bias due to the simplifications and assumptions, which cannot be effectively addressed through the development of various algorithms such as Kalman filtering (KF) or particle filtering (PF). Consequently, as observed in some study, battery SOC estimation using a typical extended KF in fact is not very accurate where the error could range from 5% to 10% or even more depending on the battery characteristics. This paper proposes bias characterization of the battery model, so that accuracy of the baseline model could be significantly improved and eventually SOC estimation could be much more accurate than the one only using the baseline model. This paper reports great potential for improving battery SOC estimation with the bias characterization and proposes two methods for actual bias modeling. In particular, the polynomial regression model and the Gaussian process regression model are proposed to examine the effects of the two methods on bias modeling and SOC estimation using a typical battery circuit model. Results are demonstrated in both simulation and lab testing using three battery charging/discharging profiles with the cross-validation technique. [ABSTRACT FROM AUTHOR]

Providing femto access points (FAPs) with computational capabilities will allow (either total or partial) offloading of highly demanding applications from smartphones to the so-called femto-cloud. Such offloading promises to be beneficial in terms of battery savings at the mobile terminal (MT) and/or in latency reduction in the execution of applications. However, for this promise to become a reality, the energy and/or the time required for the communication process must be compensated by the energy and/or the time savings that result from the remote computation at the FAPs. For this problem, we provide in this paper a framework for the joint optimization of the radio and computational resource usage exploiting the tradeoff between energy consumption and latency. Multiple antennas are assumed to be available at the MT and the serving FAP. As a result of the optimization, the optimal communication strategy (e.g., transmission power, rate, and precoder) is obtained, as well as the optimal distribution of the computational load between the handset and the serving FAP. This paper also establishes the conditions under which total or no offloading is optimal, determines which is the minimum affordable latency in the execution of the application, and analyzes, as a particular case, the minimization of the total consumed energy without latency constraints. [ABSTRACT FROM PUBLISHER]

Economical and environmentally friendly geocast (EEFG) uses traffic signals to communicate with approaching vehicles. The communication can be signal-to-vehicle (TLS2V) and vehicle-to-vehicle (V2V). Based on the information sent, the vehicle receiving the message adapts its speed to a recommended speed (SR ) , which helps the vehicle reduce fuel consumption and emissions. Our previous paper entitled “Optimization of Fuel Cost and Emissions Using V2V Communications” develops a model to determine the optimum SR . It also proposes heuristic expressions to compute the optimum or near-optimum SR. [ABSTRACT FROM PUBLISHER]

Although vehicles are the most commonly used means of transportation in our daily lives, their computational power and memory resources are often ignored. The new paradigm, Internet of Vehicles, has turned on-road vehicles into intelligent service providers, making full use of on-board processing and storage capabilities. With the advent of 6 G technology, e.g., millimeter wave and terahertz, fast and massive data transfers become possible between moving objects. In this paper, we consider a scenario where vehicles act as mobile edge caching nodes and form a local cloud, to provide popular contents for nearby users via 6 G communication. To maximize the efficiency of content allocation under the limitation of short communication range, we first predict the driving trajectories of vehicles with a Markov chain model and estimate the popularity level of contents in each urban area. Next, we design a scoring system based on the above predictions to compare users’ satisfaction and computational efficiency of different algorithms. Finally, we find a subset of vehicles with appropriate content to serve the demand in the area. The simulation experiments demonstrate that the proposed scheme outperforms the conventional methods by providing a cost-efficient content allocation solution with lower delay. [ABSTRACT FROM AUTHOR]

Terahertz (THz) frequency band has become one of the popular researches for the short-range broadband, high-rate data communication, reliability, and strong anti-interference ability, which can realize better performance for dense vehicular network scenario. In this paper, we introduce a cache based dense vehicular networks with THz frequency link and focus on the resource allocation optimization problem of subband and power allocation by maximizing energy efficiency (EE). In order to reduce the computational complexity, the original optimization problem is formulated as a mean-field game (MFG) problem, where each cache access point (cAP) can solve its local EE optimization problem by Dinkelbach-style method and Lagrangian dual method. Different access cells interact with MFG through mean subband power. Then a global MFG based EE optimization algorithm is proposed to associate the local strategy of each cell, which guarantee the globality of the optimized solutions. The numerical results suggest the effectiveness of the proposed scheme. [ABSTRACT FROM AUTHOR]

In this paper, a model fusion method (MFM) is proposed for online state of charge (SOC) and state of power (SOP) co-estimation of lithium-ion batteries (LIBs) in electric vehicles (EVs). Firstly, a particle swarm optimization-genetic algorithm (PSO-GA) method is cooperated with a 2-RCCPE fractional-order model (FOM) to construct battery open-circuit voltage (OCV)-SOC curve, which only relies on a part of dynamic load profile without the prior knowledge of an initial SOC. Secondly, a dual extended Kalman filter (DEKF) algorithm based on a 1-RC model is employed to identify the model parameters and estimate battery SOC with the extracted OCV-SOC curve. Furthermore, battery polarization dynamics in a SOP prediction window is analyzed from two aspects: (1) self-recovery; and (2) current excitation. They are separately simulated using 2-RCCPE FOM and 1-RC model, and then integrated through a model fusion for online SOP estimation, which enables an analytical expression of battery peak charge/discharge current in a prediction window without weakening the nonlinear characteristic of FOM. Experimental results demonstrate the improved performance of the proposed MFM for online discharge SOP estimation, where the mean absolute error and root mean square error are only 0.288 W and 0.35 W, respectively, under the urban dynamometer driving schedule profile. [ABSTRACT FROM AUTHOR]

Mobile edge computing (MEC) and millimeter wave (mmWave) communications are capable of significantly reducing the network's delay and enhancing its capacity. In this paper we investigate a mmWave and device-to-device (D2D) assisted MEC system, in which user A carries out some computational tasks and shares the results with user B with the aid of a base station (BS). We assume partial offloading model and the task can be partitioned into two portions: the first part is computed locally at user A, while the second part is transmitted to the BS and computed by the MEC server. The computational results are then sent to user B through a D2D link and via the link from the BS to user B, respectively. To support computation offloading, both the users and the BS are equipped with multiple antennas and employ analog and digital (A/D) hybrid beamforming. Moreover, we propose a novel two-timescale joint hybrid beamforming and task allocation algorithm to reduce the system latency whilst cut down the required signaling overhead. Specifically, the high-dimensional analog beamforming matrices are updated in a frame-based manner based on the channel state information (CSI) samples, where each frame consists of a number of time slots, while the low-dimensional digital beamforming matrices and the offloading ratio are optimized more frequently relied on the low-dimensional effective channel matrices in each time slot. A stochastic successive convex approximation (SSCA) based algorithm is developed to design the long-term analog beamforming matrices. As for the short-term variables, the digital beamforming matrices are optimized relying on the innovative penalty-concave convex procedure (penalty-CCCP) for handling the mmWave non-linear transmit power constraint, and the offloading ratio can be obtained via the derived closed-form solution. Simulation results verify the effectiveness of the proposed algorithm by comparing the benchmarks. [ABSTRACT FROM AUTHOR]

Control- and user-plane separation (CUPS) and network slicing are two key technologies to support increasing network traffic and diverse wireless services. However, the benefit of CUPS in decoupling the network coverage and data service functions has not been fully utilized to facilitate network slicing. In this paper, we present a novel CUPS-based end-to-end (CUPS-E2E) network slicing scheme. First, the base stations (BS) are classified into control BSs (CBS) that provide control plane (CP) coverage and traffic BSs (TBS) that deliver user plane (UP) traffic. Next, upon CBSs and TBSs being virtualized, we define four typical end-to-end (E2E) network slices: one for CP coverage, one for high-throughput services, one for computation-intensive services, and the other for delay-sensitive services. The utilities of the four E2E network slices are defined based on their coverage, throughput, computing capability and delay requirements, respectively. Then, a deep deterministic policy gradient (DDPG)-based algorithm is employed to maximize the long-term sum-utility of the four E2E network slices by jointly optimizing the allocation of communication and computing resources to the four network slices and the activation of virtual TBSs, while meeting the service requirements of all users. Simulation results show that our proposed CUPS-E2E network slicing scheme in conjunction with a DDPG-based sum-utility maximization algorithm can support the CP wide-coverage and massive access requirements as well as the UP high-throughput, computation-intensive and delay-sensitive services simultaneously, and outperforms the existing E2E network slicing schemes in terms of the sum-utility, coverage percentage, throughput and delay. [ABSTRACT FROM AUTHOR]

The accuracy of artificial intelligence (AI) models is crucial for connected and autonomous vehicles (CAVs). However, in reality, model training under less frequent weather faces the problem of insufficient sampling. Also, in the real world, weather, sunlight, etc., can only change with the speed of the real-time clock, so the traditional sampling process is very slow. Moreover, currently, collective learning, which can make up the limited experience and computing power of a single vehicle, is always introduced to cases where the data from participants have the same structure, wasting massive heterogeneous data from vehicles of different brands. Therefore, in this paper, we propose a quantum collective learning and many-to-many matching game-based scheme in the metaverse for CAVs. The environment is simulated in the metaverse, which has its own time clock system, thereby expanding sample size and speeding up the sampling process. And we quantify the quality of intelligence in collective learning from the perspective of feature diversity. It is the cornerstone of collective learning between heterogeneous vehicles, facilitating maximum utilization of data with different structures. Then, we formulate the distributed vehicles selection problem as a many-to-many matching game and use Gale–Shapely algorithm to solve it. Also, we formulate the spectrum resource allocation problem as a discrete Markov decision process (MDP) and adopt a quantum-inspired reinforcement learning (QRL) algorithm to find the optimal policy to achieve the high revenue of the system. In simulations, the performance of the proposed scheme is compared with existing methods. [ABSTRACT FROM AUTHOR]

Inductive power transfer (IPT) is becoming increasingly popular in stationary electric vehicle (EV) charging systems. In this paper, the influence of the different IPT coupler geometries on the performance factors such as efficiency, power density, misalignment tolerance, and stray field is studied. Four different coupler topologies, namely the circular, rectangular, double-D (DD-DD), and the double-D transmitter with double-D-quadrature receiver (DD-DDQ) are considered in this study. The electromagnetic behavior of the couplers is modeled using three-dimensional finite-element method, which is validated by experiments on a laboratory prototype. A multi-objective optimization (MOO) framework is developed to analyze the Pareto tradeoffs between conflicting performance metrics for the couplers. Optimization results depict that the circular topology performs best among the selected topologies regarding higher coupling coefficient, and efficiency for similar active mass and coupler area. Circular and rectangular couplers perform better than the polarized couplers like DD-DD and DD-DDQ regarding stray field exposure in both vertical and lateral direction of the coupler position in the EV. However, polarized couplers show more tolerance toward misalignment compared to circular and rectangular couplers. Thus, this study provides information regarding the specific strengths and weaknesses of different coupler topologies, which can be used during the initial design phase. [ABSTRACT FROM AUTHOR]

Autonomous and connected cars (ACCs), together with edge computing (EC), have been recognized as a promising solution to achieve green intelligent transportation for smart cities. This paper aims to address short-term traffic prediction, a fundamental enabler for the success of ACC applications, under the European Telecommunications Standards Institute multi-access EC (MEC) architecture that exhibits constraints different from conventional cloud computing. First, a data-centric experiment platform is designed and implemented to facilitate traffic prediction algorithm development. This paper further proposes a novel short-term traffic prediction model that integrates a traffic light model and a vehicle velocity model, considering limited computing resources of MEC servers. We note that the effects of traffic lights are complicated and have not been rigorously examined in most, if not all, of the related work. This work models the queueing time when a driver arrives at a road intersection and faces a red light. Moreover, to forecast the vehicle velocity, we propose a novel low-complexity semiparametric prediction model considering periodic features and spatial/temporal correlations of dynamic road events. The experiment results demonstrate that our vehicle-velocity prediction model achieves almost equivalent accuracy to the well-known Long Short-Term Memory Neural Network model, requiring much lower computational complexity. Our experiment results also confirm that since our integrated model pays attention to the traffic-light effects and the individual driver behavior, it can more effectively capture the real-time changes of traffic conditions. [ABSTRACT FROM AUTHOR]

As Vehicular Ad hoc Network (VANET) features random topology and accommodates freely connected nodes, it is important that the cooperation among the nodes exists. This paper proposes a trust model called Implicit Web of Trust in VANET (IWOT-V) to reason out the trustworthiness of vehicles. Such that untrusted nodes can be identified and avoided when we make a decision regarding whom to follow or cooperate with. Furthermore, the performance of Cooperative Intelligent Transport System (C-ITS) applications improves. The idea of IWOT-V is mainly inspired by web page ranking algorithms such as PageRank. Although there does not exist explicit link structure in VANET because of random topology and dynamic connections, social trust relationship among vehicles exists and an implicit web of trust can be derived. To accomplish the derivation, two algorithms are presented, i.e., BayesTrust and VehicleRank. They are responsible for deriving the local and global trust relationships, respectively. The simulation results show that IWOT-V can accurately identify trusted and untrusted nodes if enough local trust information is collected. The performance of IWOT-V affected by five threat models is demonstrated, and the related discussions are also given. [ABSTRACT FROM AUTHOR]

This paper investigates the performance of epidemic routing in mobile social networks considering several communities which are frequently visited by nodes. To this end, a monolithic Stochastic Reward Net (SRN) is proposed to evaluate the delivery delay and the average number of transmissions under epidemic routing by considering skewed location visiting preferences. This model is not scalable enough, in terms of the number of nodes and frequently visited locations. In order to achieve higher scalability, the folding technique is applied to the monolithic model, and an approximate folded SRN is proposed to evaluate performance of epidemic routing. Discrete-event simulation is used to validate the proposed models. Both SRN models for predicting the performance of epidemic routing exhibit high accuracy. We also propose an Ordinary Differential Equation (ODE) model for epidemic routing and compare it with the folded model. The obtained results show that the folded model is more accurate than the ODE model. Moreover, it is proved that the number of transmissions by the time of delivery follows a uniform distribution, for a general class of networks, where positions of nodes are always independent and identically distributed. [ABSTRACT FROM AUTHOR]

This paper proposes a flexible data-driven method for online estimating the State of Health (SOH) of Li-ion batteries in both charging and discharging modes. Based on comprehensive battery aging data analytics, a novel health indicator called voltage variance during equal time interval (VVETI) is extracted. The VVETI can be extracted during either charging or discharging mode. For online applications, the indicator is derived from a small segment of charge/discharging curves. Unlike existing methods, the indicator can be extracted in various voltage ranges which is highly flexible for application. Then, a hierarchical ensemble model of extreme learning machine (ELM) is proposed as the machine learning engine for accurate SOH estimation. The proposed method is tested on three open datasets and reports a very high accuracy (average RMSE below 0.5% under appropriate voltage ranges). [ABSTRACT FROM AUTHOR]

The paper presents several novel residual recurrent neural network (RNN) models for digital predistortion of radio-frequency power amplifiers. Then, unstructured and structured neural network (NN) pruning algorithms are proposed to reduce the per-sample computational complexity and the required memory, without compromising their modeling performance. The mathematical equations of the complexity and the memory are derived to analyze the hardware cost and design low cost models. An experimental platform is developed to measure the modeling performance in terms of adjacent channel leakage ratio (ACLR), normalized mean square error, error vector magnitude (EVM) and bit error rate. The platform uses an envelope tracking PA excited by 80 MHz IEEE 802.11ac signals. Compared with the state-of-the-art RNN model in (Sun et al., 2019), the proposed models reduce the per-sample complexity and required memory by $94\hbox{--}99$ %, they also improve the ACLR and EVM by at least 3 dB and 1 dB at 0.45 dB and 3.15 dB gain compression, respectively. Furthermore, an observation path with time alignment is used to remove the transmit latency in the state-of-the-art approach. At 3.15 dB gain compression, the proposed models outperform the state-of-the-art feedforward and convolutional NN models by at least 1.3 dB in EVM, outperform the general memory polynomial model by at least 3.3 dB in EVM. The above evidences indicate that the proposed RNN models can be implemented with relatively low hardware cost and achieve the best EVM in high power efficiency scenario. [ABSTRACT FROM AUTHOR]

Millimeter wave (mmW) is being deployed in hotspot scenarios for providing high bandwidths. However, the coverage of mmW cell is limited due to the rapid attenuation during the propagation and sensitivity to blockage by obstacles. In this paper, we propose a novel dynamic programming approach for automated dimensioning and appropriate placement of mmW small cells (SCs) in dense urban under the constraints of coverage and budget. Being cognizant of the blockage by city buildings, a fast search algorithm based on vector is introduced to enable most line-of-sight (LOS) communication links between base stations (BSs) and mobile stations (MSs). The analysis of time complexity is also derived in closed forms. The evaluation of our approach was carried out in both hypothetic and realistic scenarios. Results show that the studied model is effective for a real large-scaled network and 4 or 5 times faster than the conventional ones based on grid-map. [ABSTRACT FROM AUTHOR]

Roadside units (RSUs), which have strong computing capability and are close to vehicle nodes, have been widely used to process delay- and computation-intensive tasks of vehicle nodes. However, due to their high mobility, vehicles may drive out of the coverage of RSUs before receiving the task processing results. In this paper, we propose a mobile edge computing-assisted vehicular network, where vehicles can offload their tasks to a nearby vehicle via a vehicle-to-vehicle (V2V) link or a nearby RSU via a vehicle-to-infrastructure link. These tasks are also migrated by a V2V link or an infrastructure-to-infrastructure (I2I) link to avoid the scenario where the vehicles cannot receive the processed task from the RSUs. Considering mutual interference from the same link of offloading tasks and migrating tasks, we construct a vehicle offloading decision-based game to minimize the computation overhead. We prove that the game can always achieve Nash equilibrium and convergence by exploiting the finite improvement property. We then propose a task migration (TM) algorithm that includes three task-processing methods and two task-migration methods. Based on the TM algorithm, computation overhead minimization offloading (COMO) algorithm is presented. Extensive simulation results show that the proposed TM and COMO algorithms reduce the computation overhead and increase the success rate of task processing. [ABSTRACT FROM AUTHOR]

This paper investigates the multi-part collaborative task offloading with multiple servers in mobile edge computing (MEC) systems by considering server overload and long-term system performance. Our goal is to achieve the optimal user experience within the range of the network operator’s affordable cost. To this end, we design a two-layer computation offloading framework based on the multi-part offloading mode and the collaborations among small cell base station (SBS) servers. Furthermore, a multi-object constrained optimization problem is formulated, which jointly optimizes user association, channel allocation, and multi-part collaborative task offloading. To solve this problem, we propose a Genetic and Deep Deterministic Policy Gradient (GADDPG)-based computation offloading scheme, where the long-term system performance is considered. Numerical and simulation results demonstrate that the proposed GADDPG-based computation offloading scheme outperforms other methods in effectively solving the server overload and guarantees long-term system performances while ensuring the best user experience. [ABSTRACT FROM AUTHOR]

The optimization of the energy management of modern hybrid-electric or fully electric race cars for minimum lap time requires a description of the vehicle dynamics performance envelope, that is, of the tires’ grip limit in corners, braking zones and during acceleration. In this paper, we present a computationally efficient performance envelope model in the form of convex constraints on the achievable longitudinal and lateral acceleration, on the assumption that the path on the track is given. The proposed acceleration limits are modeled velocity-dependent to take into account the effect of aerodynamic downforce present in many circuit race cars. The formulation as linear equality, inequality and second-order cone constraints allows to embed the model in a convex energy management optimization framework. To showcase the approach, we identify the model with data obtained from a state-of-the-art hybrid-electric Formula 1 car and present results for the Silverstone and Spa-Francorchamps circuits. The optimal energy management strategies can be evaluated with a computational time of less than 1 s. The optimal velocity profile subject to the performance envelope constraints is close to the measured one. The good agreement between the optimal solution and the measurement data shows that the proposed model captures the vehicle dynamics accurately enough for the purposes of energy management optimization. [ABSTRACT FROM AUTHOR]

The performance of vehicular ad hoc networks (VANETs) is subject to frequent changes due to node mobility so that nonstationary/transient network behavior always exists. In addition, safety applications in VANETs are very sensitive to the real-time performance of delay and packet delivery ratio (PDR). Although there are extensive studies on the steady-state (SS) performance analysis of vehicular networks, little work exists on evaluating their time-varying behavior. In this paper, we develop a performance model to efficiently estimate the dynamic behavior of VANETs. In this paper, vehicle's transmission queue is modeled using fluid-flow (FF)-based differential equations, which are solved using numerical methods, whereas the network hearing topology is modeled by a time-varying adjacency matrix that can be determined from stochastic models, measurements, or discrete event simulations. Numerical results illustrate that our performance model is able to promptly respond to the ongoing dynamic conditions of VANETs and provide reasonably accurate performance results. [ABSTRACT FROM AUTHOR]

This paper compares three candidate large-scale propagation path loss models for use over the entire microwave and millimeter-wave (mmWave) radio spectrum: the alpha–beta–gamma (ABG) model, the close-in (CI) free-space reference distance model, and the CI model with a frequency-weighted path loss exponent (CIF). Each of these models has been recently studied for use in standards bodies such as 3rd Generation Partnership Project (3GPP) and for use in the design of fifth-generation wireless systems in urban macrocell, urban microcell, and indoor office and shopping mall scenarios. Here, we compare the accuracy and sensitivity of these models using measured data from 30 propagation measurement data sets from 2 to 73 GHz over distances ranging from 4 to 1238 m. A series of sensitivity analyses of the three models shows that the four-parameter ABG model underpredicts path loss when relatively close to the transmitter, and overpredicts path loss far from the transmitter, and that the physically based two-parameter CI model and three-parameter CIF model offer computational simplicity, have very similar goodness of fit (i.e., the shadow fading standard deviation), exhibit more stable model parameter behavior across frequencies and distances, and yield smaller prediction error in sensitivity tests across distances and frequencies, when compared to the four-parameter ABG model. Results show the CI model with a 1-m reference distance is suitable for outdoor environments, while the CIF model is more appropriate for indoor modeling. The CI and CIF models are easily implemented in existing 3GPP models by making a very subtle modification—by replacing a floating non-physically based constant with a frequency-dependent constant that represents free-space path loss in the first meter of propagation. This paper shows this subtle change does not change the mathematical form of existing ITU/3GPP models and offers much easier analysis, intuitive appeal, better model parameter stability, and better accuracy in sensitivity tests over a vast range of microwave and mmWave frequencies, scenarios, and distances, while using a simpler model with fewer parameters. [ABSTRACT FROM AUTHOR]

Simulation is a valuable way to develop cleaner transportation systems. Nevertheless, the complexity of this kind of system leads to complex models, particularly when taking into account nonlinear aspects of traction power substations (TPSs). Thus, this paper proposes different TPS models based on energetic macroscopic representation. An appropriate model is deduced from comparisons between the different models to realize energetic studies. It is finally applied to the simulation of a simple subway line, which is experimentally validated. [ABSTRACT FROM AUTHOR]

Next-generation wireless local area networks (WLANs) will support the use of wider channels, which is known as channel bonding, to achieve higher throughput. However, because both the channel center frequency and the channel width are autonomously selected by each WLAN, the use of wider channels may also increase the competition with other WLANs operating in the same area for the available channel resources. In this paper, we analyze the interactions between a group of neighboring WLANs that use channel bonding and evaluate the impact of those interactions on the achievable throughput. A continuous-time Markov network model that is able to capture the coupled dynamics of a group of overlapping WLANs is introduced and validated. The results show that the use of channel bonding can provide significant performance gains, even in scenarios with a high density of WLANs, although it may also cause unfair situations in which some WLANs receive most of the transmission opportunities while others starve. [ABSTRACT FROM PUBLISHER]

This paper focuses on external volume and power consumption optimization of an electromagnetic actuator used to move pins in a two-stage variable valve lift component within an automotive engine. This system is designed to change the valve lift at each engine cycle. To achieve this optimization, three models were developed: a magnetic, an electric, and a dynamic model. They evaluate the performances of a given actuator, check if it fulfills its role, and define the springs needed for the displacement of the pins. The optimization is made using a particle swarm method and can reduce the volume up to 20% with the same electric consumption. [ABSTRACT FROM PUBLISHER]

The 5G heterogeneous networks (HetNets) are capable of providing real-time computing services for autonomous vehicles (AVs) by deploying edge computing devices (ECDs) at macro cell base stations (MCBSs) and small cell base stations (SCBSs). With the imbalanced distribution and fast moving AVs contending intensely for computing services, how to efficiently exploit cooperations among participants in 5G HetNets to improve the service performance is therefore challenging. In this paper, we develop a game theoretic scheme for collaborative vehicular task offloading to facilitate the computing services in 5G HetNets. Specifically, we propose a two-stage vehicular task offloading mechanism to promote the cooperation among participants with the target of improving the task completion rate and the utilities of the participants, where the mechanism jointly considers the network architecture of the HetNets, the imbalanced distribution of AVs and the reuse of task results. In the first stage, an auction model is designed to help the MCBS select the optimal SCBS to execute the offloaded task based on the requirement of the task and the available computing resources of SCBSs. According to the task execution cost declared by the selected SCBS, the MCBS then bargains with the AV for the agreement of the task offloading service to maximize their utilities in the second stage. Using simulations, we show that the proposed collaborative task offloading scheme can achieve a higher task completion rate for the task offloading service and bring higher utilities to all participants than conventional schemes. [ABSTRACT FROM AUTHOR]

Unmanned Aerial Vehicles (UAVs) are becoming very popular nowadays due to the emergence of application areas such as the Internet of Drones (IoD). They are finding wide applicability in areas ranging from package delivery systems to automated military applications. Nevertheless, communication security between a UAV and its ground station (GS) is critical for completing its task without leaking sensitive information either to the adversaries or to unauthenticated users. UAVs are especially vulnerable to physical capture and node tampering attacks. Further, since UAV devices are generally equipped with small batteries and limited memory storage, lightweight security techniques are best suited for them. Addressing these issues, a lightweight mutual authentication scheme based on Physical Unclonable Functions (PUFs) for UAV-GS authentication is presented in this paper. The UAV-GS authentication scheme is extended further to support UAV-UAV authentication. We present a formal security analysis as well as old-fashioned cryptanalysis and show that our protocol provides various security features such as mutual authentication, user anonymity, etc, and is resilient against many security attacks such as masquerade, replay, node tampering, and cloning attacks, etc. We also compare the performance of our protocol with state-of-the-art authentication protocols for UAVs, based on computation, communication, and memory storage cost. [ABSTRACT FROM AUTHOR]

The Internet of Vehicles (IoV) as a promising application of Internet of Things (IoT) has played a significant role in autonomous driving, by connecting intelligent vehicles. Autonomous driving needs to process the mass environmental sensing data in coordination with surrounding vehicles, and makes an accurate driving judgment accordingly. Since the vehicles always have limited computing resources, processing these data in parallel with efficient task scheduling is one of the most important topics. Most current work focuses on formulating special scenarios and service requirements as optimization problems. However, the complicated and dynamic environment of vehicular computing is hard to model, predict and control, making those previous methods unscalable and unable to reflect the real scenario. In this paper, a Multi-task Deep reinforcement learning approach for scalable parallel Task Scheduling (MDTS) is firstly devised. For avoiding the curse of dimensionality when coping with complex parallel computing environments and jobs with diverse properties, we extend the action selection in Deep Reinforcement Learning (DRL) to a multi-task decision, where the output branches of multi- task learning are fine-matched to parallel scheduling tasks. Child tasks of a job are accordingly assigned to distributed nodes without any human knowledge while the resource competition among parallel tasks is leveraged through shared neural network layers. Moreover, we design an appropriate reward function to optimize multiple metrics simultaneously, with emphasis on specific scenarios. Extensive experiments show that the MDTS significantly increases the overall reward compared with least- connection scheduling and particle swarm optimization algorithm from −16.71, −0.67 to 2.93, respectively. [ABSTRACT FROM AUTHOR]

Connected vehicles will change the modes of future transportation management and organization, especially at an intersection without traffic light. Centralized coordination methods globally coordinate vehicles approaching the intersection from all sections by considering their states altogether. However, they need substantial computation resources since they own a centralized controller to optimize the trajectories for all approaching vehicles in real-time. In this paper, we propose a centralized coordination scheme of automated vehicles at an intersection without traffic signals using reinforcement learning (RL) to address low computation efficiency suffered by current centralized coordination methods. We first propose an RL training algorithm, model accelerated proximal policy optimization (MA-PPO), which incorporates a prior model into proximal policy optimization (PPO) algorithm to accelerate the learning process in terms of sample efficiency. Then we present the design of state, action and reward to formulate centralized coordination as an RL problem. Finally, we train a coordinate policy in a simulation setting and compare computing time and traffic efficiency with a coordination scheme based on model predictive control (MPC) method. Results show that our method spends only 1/400 of the computing time of MPC and increase the efficiency of the intersection by 4.5 times. [ABSTRACT FROM AUTHOR]

This paper mainly investigates the multi-user anti-jamming spectrum access problem. Using the idea of “converting harm into benefit,” the malicious jamming signals projected by the enemy are utilized by the users as the coordination signals to guide spectrum coordination. An “internal coordination-external confrontation” multi-user anti-jamming access game model is constructed, and the existence of Nash equilibrium (NE) as well as correlated equilibrium (CE) is demonstrated. A coordination-learning based anti-jamming spectrum access algorithm (CLASA) is designed to achieve the CE of the game. Simulation results show the convergence, and effectiveness of the proposed CLASA algorithm, and indicate that our approach can help users confront the malicious jammer, and coordinate internal spectrum access simultaneously without information exchange. Last but not least, the fairness of the proposed approach under different jamming attack patterns is analyzed, which illustrates that this approach provides fair anti-jamming spectrum access opportunities under complicated jamming pattern. [ABSTRACT FROM AUTHOR]

A microscopic fuel consumption model with respect to comprehensive fuel consumption key impact factors that can reflect dynamic engine operations and various real-world driving conditions is essential for fuel efficient model-based vehicle and powertrain control (MB-VPC). Existing microscopic fuel consumption models are mostly steady state models with limited vehicle parameters as dynamic variables. Data-driven solutions can make the model comprehensive by introducing broad impact factors. However, without the required accessible online computational capability and fast model adaptation mechanisms, those data-driven solutions cannot quickly adapt to unseen driving conditions and engine condition changes based on real-world vehicle data to support MB-VPC. In this paper, a connected vehicle-based data mining (CV-DM) framework is proposed to achieve online adaptive dynamic fuel consumption modeling through knowledge sharing over CVs and the CV remote data center. Based on the CV-DM framework, CV-supported Distributed Meta-regression (CV-DMR) algorithms are developed to realize a fast few-shot adaptation with limited training data. Extensive proof-of-concept experiments are conducted with steady-state and transient vehicle engine data. Compared to the baseline physical model and the existing non-adaptive grey-box model, prediction accuracy is improved by 47%–85% and 38%–80% respectively with only limited training data needed for the subject vehicle. Accordingly, a fuel savings of up to 9.4% can be achieved owing to the improvement of prediction accuracy. [ABSTRACT FROM AUTHOR]

Mobile edge computing (MEC) has attracted great interests as a promising approach to augment computational capabilities of mobile devices. An important issue in the MEC paradigm is computation offloading. In this paper, we propose an integrated framework for computation offloading and interference management in wireless cellular networks with MEC. In this integrated framework, we formulate the computation offloading decision, physical resource block (PRB) allocation, and MEC computation resource allocation as optimization problems. The MEC server makes the offloading decision according to the local computation overhead estimated by all user equipments (UEs) and the offloading overhead estimated by the MEC server itself. Then, the MEC server performs the PRB allocation using the graph coloring method. The outcomes of the offloading decision and PRB allocation are then used to distribute the computation resource of the MEC server to the UEs. Simulation results are presented to show the effectiveness of the proposed scheme with different system parameters. [ABSTRACT FROM AUTHOR]

In the cooperative vehicle infrastructure system, the road side unit (RSU) equipped with a mobile edge computing (MEC) server and sensors could provide vehicle infrastructure cooperation services for vehicles, such as optimization and cooperative driving, enhanced visibility, and so on. In view of this, the MEC server needs to fuse the sensing information from sensors on the vehicles and RSU, respectively. In the case of bad channel conditions, uploading the raw sensing information from the vehicles results in high uplink transmission latency. To deal with it, the vehicles can process the information locally and just deliver the results to the RSU. However, due to the limited computing resources on the vehicles, the processing accuracy of the raw information on the vehicles is lower than that on the MEC server. Besides, processing locally leads to higher vehicle energy consumption. Thus, in this paper, we aim to jointly optimize execution latency, processing accuracy, and energy consumption of the MEC-based cooperative vehicle infrastructure system. Firstly, we design the terminal machine learning task model and the edge machine learning task model on the vehicle side and RSU side, respectively. Then, we formulate a long-term multi-objective optimization problem. Owing to the stochastic traffic and time-varying communication conditions, we reformulate it as a Markov decision process and propose a two-stage deep reinforcement learning-based offloading and resource allocation (TDORA) strategy to determine the task offloading and the transmit power of each vehicle. Simulation results demonstrate the efficacy of the proposed strategy. [ABSTRACT FROM AUTHOR]

This paper presents a multi-user, multi-class and multi-layer edge computing-based framework for effective task offloading and computation processes. Important system requirements that were not captured in the existing multi-layer solutions such as offloading, computations and deadline requirements were captured in the system modeling, while both wireless communications and task computation constraints were considered. We considered three layers system, where each device offloads its generated tasks in each time slot to any selected layer for computation. On its arrival at such a selected layer, the task is only accepted if the queue size is below the pre-defined threshold, otherwise, such a task is offloaded to the next layer. Tasks were classified into class 1 and class 2 tasks following tasks’ quality of service requirements. We adopted stochastic geometry, parallel computing and queueing theory techniques to model the performance of the considered integrated edge-fog-cloud computing environment and obtained analysis for various performance metrics of interest. The obtained analyses demonstrate the importance of multi-layer and multi-class edge computing systems towards improving the experience of both delay-sensitive and mission-critical applications in any task offloading environment. [ABSTRACT FROM AUTHOR]

Due to the gap between calculation-intensive and latency-sensitive features of self-driving tasks and the vehicle's limited computation and storage resources, the development of autonomous vehicles is situated in a bottleneck. Fortunately, multi-access edge computing (MEC) architecture offers a promising measure to bridge this gap. It brings resources proximity to mobile devices at the network edge to support task offloading. Nonetheless, it introduces the problem of insecure wireless communication. Beyond that, the autonomous vehicle also has strict requirements on latency and energy consumption of task offloading technique owing to its safety-related and electricity-driven characteristics. Many scholars have studied the related problems widely. Nevertheless, few papers combine these three significant factors, namely information security, task latency and energy consumption. Thus, we put forward a mobility-ware task offloading scheme in cellular vehicle-to-everything system, which carefully considers these three requirements together. In this scheme, a time approximation algorithm is proposed to tackle the channel condition variations caused by the vehicle movement. Small-cell base station proactively sends artificial noise to debase wiretapper decoding capability and further prevent data exchanged between vehicles and MEC from being eavesdropped at the physical layer. Moreover, the optimal offloading proportion is found to minimize the weighted sum of latency and energy consumption. Experimental performances validate the effectiveness and feasibility of the proposed task offloading scheme. [ABSTRACT FROM AUTHOR]

An emerging computational paradigm, named federated edge learning (FEL), enables intelligent computing at the network edge with the feature of preserving data privacy for edge devices. Given their constrained resources, it becomes a great challenge to achieve high execution performance for FEL. Most of the state-of-the-arts concentrate on enhancing FEL from the perspective of system operation procedures, taking few precautions during the composition step of the FEL system. Though a few recent studies recognize the importance of FEL formation and propose server-centric device selection schemes, the impact of data sizes is largely overlooked. In this paper, we take advantage of game theory to depict the decision dilemma among edge devices regarding whether to participate in FEL or not given their heterogeneous sizes of local datasets. For realizing both the individual and global optimization, the server is employed to solve the participation dilemma, which requires accurate information collection for devices’ local datasets. Hence, we utilize mechanism design to enable truthful information solicitation. With the help of correlated equilibrium, we derive a decision making strategy for devices from the global perspective, which can achieve the long-term stability and efficacy of FEL. For scalability consideration, we optimize the computational complexity of the basic solution to the polynomial level. Lastly, extensive experiments based on both real and synthetic data are conducted to evaluate our proposed mechanisms, with experimental results demonstrating the performance advantages. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI)-powered autonomous vehicles (AVs) can integrate different machine learning (ML) techniques to build up a complex autonomous driving system. However, single AV intelligence is not enough to cope with ever-changing driving environments. The underlying reason is that, with current neural network design and training algorithms, it is challenging for the driving model to generalize to diverse driving environments all at once due to sample inefficiency and the curse of dimensionality. Powerful computing resources and massive amount of data can be used to train a good driving model offline. However, the driving model obtained offline might fail in corner case scenarios. In this paper, we propose an intelligence networking framework among AVs assisted by multi-access edge computing (MEC) with end-to-end learning for demonstration. In this framework, driving road is divided into segments and data is collected for each road segment separately. Assisted by MEC networks, a continuously updated driving model is produced in near real-time for each road segment when the environment changes. By dividing the road into segments, we aim to reduce the burden of generalization since a single model only needs to adapt to a specific road segment. Simulation results show that our solutions can produce updated driving model for each road segment to adapt to environmental changes better than the existing scheme. Upcoming AVs can then adapt to changing environments by downloading the updated driving model. [ABSTRACT FROM AUTHOR]