The deep integration of IoT and vehicular networks demands ultra-reliable, low-latency computing paradigms to support emerging applications like autonomous driving and smart traffic management. Existing Mobile Edge Computing (MEC) frameworks, however, struggle with dynamic resource heterogeneity, intermittent connectivity, and inefficient coordination among distributed nodes. To address these challenges, this paper proposes Vehicular Computing Power Networks (VCPN), an IoT-driven edge intelligence framework that orchestrates computational resources from mobile user equipments (MUEs), connected vehicles, and edge servers. We formulate a joint optimization problem to minimize end-to-end task latency by finding optimal task offloading decisions and resource allocation (e.g., CPU, bandwidth) policies under time-varying IoT channel conditions and node mobility. To enable decentralized coordination in IoT environment, we model the problem as a multi-agent Markov decision process (MDP) and propose a multi-agent deep deterministic policy gradient (MA-DDPG) algorithm in which agents (MUEs, vehicles, servers) collaboratively learn policies to optimize task scheduling and resource sharing. Furthermore, we design a robust MA-DDPG variant with error-resilient experience replay and channel-adaptive reward mechanisms to ensure reliable training under packet loss and unstable connectivity. Numerical results demonstrate that VCPN reduces average task latency and improves energy efficiency compared to federated MEC baselines. The proposed MA-DDPG algorithm achieves convergence stability in high-mobility scenarios, outperforming conventional deep reinforcement learning methods.

Taking into account the flexible deployment and Line-of-Sight (LoS) communication links of uncrewed aerial vehicles (UAVs), this article proposes a multi-UAV-assisted vehicular edge computing networks (VECNs) architecture to provide instantaneous computation support at multiple congestion road segments. Given that the computation resources of a single UAV are insufficient, and offloading tasks directly to the cloud computing center (CCC) in intelligent transportation systems (ITSs) introduces significant latency, multiple UAVs with precached service or content caching data are deployed optimally for the vehicle users. In order to address the tradeoff between system costs and service efficiency, we propose a novel cost-efficient layered optimization scheme, in which the number and deployment positions of UAVs are jointly optimized. According to the varying vehicular network environments and the dynamic requirements of vehicle users, we design a hierarchical reinforcement learning algorithm, combining double deep Q network (DDQN) and multiagent deep deterministic policy gradient (MADDPG), the former is used to optimize the number of UAVs, and the deployment of UAVs are optimized via the MADDPG. Simulation results demonstrate the effectiveness of the proposed scheme in lowering total task completed latency and increasing the system profits. The service efficiency in dealing with the vehicle users’ requirements also be improved.

The development of industry 4.0 relies on emerging technologies of digital twin, machine learning, blockchain and Internet of Things (IoT) to build autonomous self-configuring systems that maximize manufactory efficiency, precision and accuracy. In this paper, we propose a new distributed and secure digital twin driven IIoT framework that integrates federated learning and Directed Acyclic Graph (DAG) blockchain with sharding. The proposed framework includes three planes: the data plane, the blockchain plane and the digital twin plane. Specifically, the data plane performs federated learning through a set of cluster heads to train models at network edges for twin model construction. The blockchain plane, which supports sharding, utilizes a hierarchical consensus scheme based on DAG blockchain to verify both local model updates and global model updates. The digital twin plane is responsible for constructing and maintaining twin model. Then, an efficient resource scheduling scheme is designed by considering performance of both federated learning and DAG blockchain with sharding. Accordingly, an optimization problem is formulated to maximize long-term utility of the digital twin driven IIoT. To cope with mapping error in the digital twin plane, a multi-agent Proximal Policy Optimization (MAPPO) approach is developed to solve the optimization problem. Numerical results illustrate that comparing with traditional approach, the proposed MAPPO improves utility by about 37 %, and reduces time latency by about 14%. Moreover, it also can well adapt to the mapping error.

Instance-specific Algorithm Configuration (AC) methods are effective in automatically generating high-quality algorithm parameters for heterogeneous NP-hard problems from multiple sources. However, existing works rely on manually designed features to describe training instances, which are simple numerical attributes and cannot fully capture structural differences. Targeting at Mixed-Integer Programming (MIP) solvers, this paper proposes a novel instances-specific AC method based on end-to-end deep graph clustering. By representing an MIP instance as a bipartite graph, a random walk algorithm is designed to extract raw features with both numerical and structural information from the instance graph. Then an auto-encoder is designed to learn dense instance embeddings unsupervisedly, which facilitates clustering heterogeneous instances into homogeneous clusters for training instance-specific configurations. Experimental results on multiple benchmarks show that the proposed method can improve the solving efficiency of CPLEX on highly heterogeneous instances, and outperform existing instance specific AC methods.

Space–air–ground integrated edge computing is expecting to provide pervasive computation services for Internet of Things (IoT), especially in remote areas. However, the offloading process of power-limited IoT devices is a challenge issue due to unreliable communications in an aerial environment. In this article, we propose an energy-efficient space–air–ground integrated edge computing network architecture, in which the IoT devices choose the most appropriate LEO satellites or unmanned aerial vehicles (UAVs) for task offloading according to their energy level, communication conditions and computing capabilities. In order to providing efficient task offloading and energy-saving policy under an uncertainty aerial environment, a constrained Markov decision process is employed to formulate the task offloading decision problem and a deep reinforcement learning (DRL)-based algorithm is devised to solve the proposed problem. An adaptive federated DRL-based offloading method is further proposed to find suboptimal offloading decisions by considering the privacy protection and communication failure in the proposed network. Numerical results confirm the effectiveness of the proposed schemes on energy saving and computation efficiency.

This article proposes distributed demand response (DR) approaches for a multienergy residential community, which is equipped with various energy conversion and storage devices to serve multiple residential loads (e.g., electricity, natural gas, and heating loads). In the proposed DR approaches, each of the energy devices and loads is an individual decision-maker and also a node in a randomly connected communication network. The DR approaches are tolerant to incomplete information which is caused by random inaction of nodes and links in the network. At first, in order to coordinate nodes' behaviors in distributed DR, different information transmission mechanisms among nodes are employed. Particularly, Steiner tree broadcast, in which nodes are networked according to their energy types, is proposed to lower the nodes' computational complexity and the network's communication overhead. Based on the information transmission mechanisms, the initial DR problem is transformed into network problems that are solvable in a random network. Then, based on the randomized alternating direction method of multipliers, distributed algorithms are designed to optimally solve the network problems in the presence of incomplete information. In simulation, real-world datasets of multiple energy loads and prices are used, and three proposed DR approaches are compared in terms of convergence performance and communication overhead.

By providing computation and storage resources at the edge of the wireless access networks, edge computing(EC) has been regarded as a provisioning solution to enable the efficient, reliable and cost-effective two-way energy and information flows in smart grids. In this paper, we propose the framework of EC-based smart grid networks, in which EC servers are deployed at the gateways between the remote cloud center and the terminal smart meters. The EC servers perform energy scheduling and renewable energy generation(RG) output forecasting, based on the collected power demand data of terminal devices and monitoring data of RG equipments. According to the inherent collaboration features of the monitoring data offloading, that the outputs of the same size/type RG equipments in a limited area are the same in a short time, we consider an efficient cooperative task offloading and resource allocation scheme. Not all of the monitoring data should be offloaded. Then, an optimal problem is formulated, the transmission powers and channels, computation resource allocation and task offloading fraction of devices are jointly optimized. Numerical results show that our proposed schemes reduce the system cost efficiently, while the latency constraints are ensured.

This paper studies a new model of energy storage (ES) sharing in a residential community in which some homes have physical ESs (PESs) but some do not. The non-PES homes can buy ES capacity from PES homes, creating virtual ESs (VESs). Based on the transaction results between PESs and VESs, an online algorithm is developed for real-time energy management of ES sharing among the homes. During online control, non-negative long-term utilities of homes and practical charging/discharging constraints of PESs and VESs are considered. The advantage of the proposed algorithm is that system state forecasting, such as home load, renewable generation, and grid price, is not required. The algorithm only needs current system states to make a control decision. Theoretic analysis shows that the worst-case system cost under the algorithm is upper bounded, guaranteeing the online solution is near-optimal. In the simulation, real-time data of grid price and home power use is employed, and the proposed algorithm is benchmarked against a greedy algorithm and a theoretic lower bound.

In green cities, one of the most promising energy system designs is the multi-energy system, which is capable of integrating different energy resources to supply stable energy for users. To schedule diverse energy efficiently, the energy trading among different energy entities is a big issue in multi-energy systems. This paper proposes auction mechanisms for energy trading in a smart multi-energy district, in which the district manager sells electricity, natural gas, and heating energy to users and meanwhile trades with outer energy networks. Two auction mechanisms are designed under the day-ahead and real-time markets, respectively. For each auction, energy allocation is optimized by solving a social welfare maximization problem, which is strictly subject to constraints of physical multi-energy system models. It is theoretically proven that both auctions are able to guarantee the properties of economic efficiency, truthfulness, and individual rationality. With these properties, users are incentivized to participate into the auctions with fairness. Finally, real data are adopted to evaluate the performance of the proposed mechanisms. The theoretic analysis of the properties is verified as well.

One of the major advantages of smart grid is to allow a large number of electric vehicles (EVs) to participate in energy dispatch as elastic energy storage devices via vehicle-to-grid (V2G) technology. As mechanism design for V2G energy trading can stimulate energy interaction between EVs and grids, it is really significant to V2G systems. This paper focuses on efficient mechanism design for energy trading in a two-layer V2G architecture, which includes a grid-aggregator layer and aggregator-EV layer. We propose two auction mechanisms for the two layers, respectively, and discuss three essential economic properties of the mechanisms, i.e., truthfulness, individual rationality, and efficiency. Then, based on these two mechanisms, we illustrate the detailed operation procedure of the two-layer V2G energy trading architecture. Performance evaluation shows that the proposed auction mechanisms greatly reduce social costs, i.e., enhance efficiency, while guaranteeing truthfulness and individual rationality.

False data injection attacks have serious threat to the smart grid, e.g., may incur power outage or blackout. Normally, an intruder should have priori knowledge of the linear structure matrix and then control all smart meters to perform attacks. State-of-the-art studies have proven in theory that false data injection attacks can be unobservable when an intruder coordinately controls a small number of smart meters. However, there are no practical or implementable unobservable false data injection attacks with low-sparsity yet in the literature. In this paper, we propose a two-stage attacking scheme to demonstrate the practical feasibility of unobservable false data injection attacks in the smart grid. In the first stage, we explore the parallel factor analysis to derive the linear structure matrix of the smart grid using the intercepted data. In the second stage, we construct the sparse attack vector via a linear-based relaxation approach, which is used as the false data. Results indicate that we can realize highly successful attacking performance with a low detection probability.

Abstract In cognitive vehicular networks (CVNs), spectrum sensing and access are introduced as the promising technologies to fully exploit the underutilized licensed spectrum. Because the sensing ability of a single secondary vehicular user (SVU) is affected by high mobility, dynamic topology, and unreliable wireless environment, collaborative sensing is developed to increase the sensing accuracy and efficiency. Generally, the synchronization is required in the collaborative sensing in CVN. However, it is difficult to keep all SVUs synchronized with others for sensing under the high dynamic network topology, and the sensing overhead of the synchronous cooperative action may be significant. In this paper, we first propose an asynchronous cooperative sensing scheme in which each SVU provides an energy information (EI) that is tagged with location and time information. The sensing decision will be made on account of the EI. Considering the temporal and spatial diversities of each SVU, we assign different weights to each EI and formulate the probabilities of detection and false alarm as the optimization problems to find the optimal weight of each EI. Then, based on the asynchronous sensing, the specifications of the opportunistic spectrum access mechanism are elaborated in both centralized and decentralized CVNs for the sake of practical implementation. We analyze the system performance in terms of achievable throughput and transmission delay. Numerical results show that the proposed scheme is able to achieve substantially higher throughput and lower delay, as compared with existing schemes. Copyright © 2014 John Wiley & Sons, Ltd.

Providing adequate and reliable spectrum resources for unlicensed users in spectrum database-based cognitive radio networks is very challenging, mainly due to the dynamic resource availability induced by the licensed users' activities and radio environment. In this paper, we propose an adaptive spectrum access method based on spectrum database for cognitive radio (CR) networks. While making decision to access the licensed spectrum, the secondary users (SUs) not only use the spectrum information informed by the spectrum database but also use the local sensing to confirm the specific condition of the spectrum. The adaptive sensing and access process is modeled as an optimal decision process by maximizing the achievable throughput of CR networks. The dynamic programming algorithm is developed to find the optimal sensing and access policy for each SU. Simulation results show that the proposed sensing and access policies can provide reliability guarantees for finding spectrum opportunities in terms of dynamic radio environment.

A robust and resilient medium access control (MAC) protocol is crucial for numerous machine-type devices to concurrently access the channel in a machine-to-machine (M2M) network. Simplex (reservation- or contention-based) MAC protocols are studied in most literatures which may not be able to provide a scalable solution for M2M networks with large number of heterogeneous devices. In this paper, a scalable hybrid MAC protocol, which consists of a contention period and a transmission period, is designed for heterogeneous M2M networks. In this protocol, different devices with preset priorities (hierarchical contending probabilities) first contend the transmission opportunities following the convention-based$p$-persistent carrier sense multiple access (CSMA) mechanism. Only the successful devices will be assigned a time slot for transmission following the reservation-based time-division multiple access (TDMA) mechanism. If the devices failed in contention at previous frame, to ensure the fairness among all devices, their contending priorities will be raised by increasing their contending probabilities at the next frame. To balance the tradeoff between the contention and transmission period in each frame, an optimization problem is formulated to maximize the channel utility by finding the key design parameters: the contention duration, initial contending probability, and the incremental indicator. Analytical and simulation results demonstrate the effectiveness of the proposed hybrid MAC protocol.

Recently, plug-in hybrid electric vehicles (PHEVs) have attracted considerable attention as a sustainable transport system and also an essential component of the smart grid. With the rapid growth of PHEVs penetration, the charging and discharging of PHEVs will pose a significant impact on the residential electricity distribution network. For this reason, the management of PHEV charging and discharging has become one of the key issues in the research of PHEVs. In most existing work, PHEVs are supposed to operate individually for charging and discharging in the grid. However, we argue that, by leveraging the cooperation among PHEVs, the grid will efficiently stimulate PHEV users to charge in load valley and discharge in load peak. As a consequence, the electricity load is well balanced. Meanwhile, the PHEV users also achieve higher profit. The PHEV charging and discharging cooperation is a win-win strategy for both the grid and the PHEV users. We formulate and resolve the PHEV charging and discharging cooperation in the framework of coalition game. The simulation results indicate that the peak-valley difference in electricity load of the grid is significantly reduced. Besides, the PHEV users have better satisfaction in the vehicle battery status and the economic profit.

In Machine to Machine (M2M) networks, a robust Medium Access Control (MAC) protocol is crucial to enable numerous machine-type devices to concurrently access the channel. Most literatures focus on developing simplex (reservation or contention based) MAC protocols which cannot provide a scalable solution for M2M networks with large number of devices. In this paper, a frame-based Hybrid MAC scheme, which consists of a contention period and a transmission period, is proposed for M2M networks. In the proposed scheme, the devices firstly contend the transmission opportunities during the contention period, only the successful devices will be assigned a time slot for transmission during the transmission period. To balance the tradeoff between the contention and transmission period in each frame, an optimization problem is formulated to maximize the system throughput by finding the optimal contending probability during contention period and optimal number of devices that can transmit during transmission period. A practical hybrid MAC protocol is designed to implement the proposed scheme. The analytical and simulation results demonstrate the effectiveness of the proposed Hybrid MAC protocol.

Previous cooperative sensing schemes require the cooperative Secondary Users (SUs) to behave in a synchronous way. This requires each SU to start cooperations at the same time by stopping their own transmissions. In multi-hop cognitive radio networks, it is very difficult to keep all SUs synchronized with others for sensing. In this paper, we propose an asynchronous cooperative sensing scheme for multi-hop cognitive radio networks in which each SU only provides its energy information in stead of ceasing its own transmission to perform the cooperative sensing. Each energy information is assigned an appropriate weight by considering the temporal and spatial diversities of each SU. We formulate the probabilities of detection and false alarm as optimization problems to find the optimal weight for every energy information. The achievable throughput has been derived. Numerical results show that the proposed scheme is able to achieve substantially higher throughput compared with the existing schemes.

In Cognitive Radio (CR) networks, spectrum sensing is a crucial technique to discover spectrum opportunities for the Secondary Users (SUs). The Quality-of-Service (QoS) of spectrum sensing is characterized by both sensing accuracy and sensing efficiency. Here, sensing accuracy is represented by the false alarm probability and the detection probability while sensing efficiency is represented by the metrics sensing overhead and throughput. The literature has mainly focused on improving sensing accuracy while sensing efficiency has been largely ignored. In this paper, we propose a group-based cooperative Medium Access Control (MAC) protocol, which concentrates on improving sensing efficiency without degrading spectrum sensing accuracy. The MAC protocol is specified and implemented in three phases: reservation, sensing and transmission. The protocol incorporates a group-based cooperative spectrum sensing scheme. In particular, the cooperative SUs are grouped into several teams. During a sensing period, each team senses a different channel. As a consequence, multiple distinct channels can be simultaneously detected within one sensing period. Then, we formulate throughput maximization problems in both time-invariant and time-varying channel scenarios to determine the key design parameters. In addition, an SU-selecting algorithm is presented to selectively choose the cooperative SUs based on the channel dynamics and usage patterns in order to substantially reduce sensing overhead. Numerical results indicate that the proposed strategy is able to significantly decrease sensing overhead and increase throughput with guaranteed sensing accuracy.