Millisecond-precision measurement of smart grid presents elevated demands for 6G sensing and communication capabilities. How to ensure timely, reliable, and green delivery of critical information remains a core challenge. In this paper, we address this issue by studying electric semantic short packet communication from a green integrated sensing and communication (ISAC) perspective. First, a novel information timeliness metric named peak age of incorrect semantics (PAoIS) is developed. It describes the entire lifetime of sensing, compression, encoding, transmission, and decoding. Then, a collaborative problem is formulated to jointly minimize PAoIS and ISAC energy consumption by optimizing sensing frequency and semantic compression ratio. An electric multimodal driven green collaborative optimization algorithm is proposed. It enables dynamical adjustment of sampling ratio of electric multimodal experience samples, enhancing optimization performance under sparse modes. Simulation results verify the effectiveness of the proposed algorithm.

As the proportion of renewable energy in the distribution grid continues to rise, the timely transmission of critical state information becomes essential to ensure the balance of energy flow. Existing metrics for information timeliness based on peak age of information (PAoI) and its variants fall short in fully characterizing the intricate influence of information flow on the dynamics of energy distribution. In this paper, a new information timeliness metric named energy dispatch cost-aware PAoI (EPAoI) is introduced from the perspective of integrating information and energy flows. We propose an information-energy flow integrated wireless resource scheduling algorithm based on fuzzy learning to minimize EPAoI. It exceptionally improves learning accuracy by exploiting key features of dual flows to guide resource scheduling optimization. Simulation results validate superior performances of the proposed algorithm in reducing EPAoI and energy dispatch cost.

The rapid advancement of 6G, cloud-fog computing, and internet of things (IoT) has revolutionized the control paradigm of smart grid. With the closed coupling between communication and power domains, control performance heavily relies on timely and secure sensing, transmission, and computing of grid state information. Conventional approaches which treat the four sectors as separate subsystems suffer from slow convergence and even cascading control oscillations. In this paper, we address the key research problem of sensing-transmission-computing-control integrated optimization to minimize the overall voltage deviation. A timeliness-driven integrated optimization algorithm is proposed, where proactive optimization of communication resource adaptation and power-domain control decisions is conducted based on the evolution of information timeliness loss in sensing, transmission, and computing, as well as its impact on control accuracy. Particularly, a self-penalty based cost function is developed to quantify the mismatch between communication-domain resource allocation and voltage control deviation. Moreover, a novel timeliness indicator, named age of trustworthy information (AoTI), is introduced to capture timeliness-trustworthiness performance loss on proportional-integral (PI) consensus control stability margin. Consensus weights are optimized based on AoTI to further enhance convergence speed and improve control accuracy. Simulation results demonstrate that the proposed algorithm significantly improves power-domain control stability, validating the efficiency of AoTI as a critical indicator for control information importance.

The application of multispectral image based partial discharge detection offers a dependable solution for high-voltage substations. Captured visible light and ultraviolet (UV) images are denoised, transmitted and fused to enhance detection performance. However, existing approaches separately design the sensing-layer image denoising, communication-layer image transmission, and computing-layer image fusion, and the lack of unified cooperation hinders the overall performance. To address this issue, it is crucial to integrate sensing, communication, and computing to improve detection accuracy and timeliness. In this paper, we formulate a timeliness and accuracy joint guarantee problem, which aims to minimize the weighted sum of peak age of information (AoI), false-positive detection ratio, and false-negative detection ratio by jointly optimizing sensing-layer filtering window size, communication-layer time division ratio, and computing layer wavelet decomposition level. We propose a multispectral integrated sensing, communication, and computing algorithm based on AoI and false-negative aware multi-experience replay cooperative learning to solve the problem. Simulation results demonstrate that the proposed algorithm outperforms existing methods in terms of peak AoI, false-positive detection ratio, false-negative detection ratio, and convergence speed.

The integration among 6G communication networks, power grids, and transportation systems is emerging as a promising paradigm to achieve mutual benefits among autonomous-driving electric vehicle (EV) users, communication operators, and power grids. Task offloading strategies for autonomous driving and the traveling patterns of EVs can induce communication load fluctuation within 6G network, which subsequently influences energy flow in power grid. Conversely, electricity price from the power grid affects EV charging/discharging strategies, impacting traffic flow and autonomous driving task offloading within the 6G network. Based on the interdependencies among the three networks, this paper constructs a communication-power-transportation coupling network with 6G base stations (BSs) and fast charge stations (FCSs) acting as coupling hubs. Besides, a spatio-temporal electricity price model considering spatial traffic distribution and temporal load fluctuation is developed. Moreover, the optimization problem is formulated to jointly coordinate FCS selection, bidirectional charging/discharging power regulation, task offloading decisions, and route selection strategies to maximize demand response quality of experience (QoE), grid stability and balance under the constraint of autonomous driving quality of service (QoS). Then, a knowledge transfer collaboration-based spatio-temporal EV task offloading, energy, and traffic management joint optimization algorithm is proposed, which improves the optimization performance through knowledge transfer collaboration among EV. Finally, simulation results validate the performance improvement of the proposed algorithm in demand response QoE, grid stability and balance, and autonomous driving QoS.

In this article, we address the key problem of sensing and communication integrated resource allocation for 6G-empowered distribution grid hierarchical coordinated control. First, we construct a novel information timeliness metric for electric semantic communication, namely, Peak Age of Semantics (PAoS), which covers the entire lifecycle of information sensing, semantic compression, semantic transmission, and semantic decoding. Second, we propose a sensing and semantic communication integrated resource allocation algorithm based on Top-$\text {N}^{2}$and hybrid knowledge–statistic-driven fuzzy reinforcement learning. A deep fuzzy neural network is utilized to build a knowledge model between the grid operating state and decision making. The knowledge is embedded into statistic-driven model of reinforcement learning to enhance accuracy of upper confidence bound (UCB) utility evaluation. Finally, simulations based on realistic application scenarios indicate that compared with two comparison algorithms, the proposed algorithm reduces average PAoS by 4.72% and 9.49%, and the maximum PAoS by 5.76% and 13.57%. Additionally, its end-to-end delay trend and semantic packet decoding success rate align more closely with semantic importance.

A 5G integrated smart distribution power grid brings a new paradigm shift to realize base station (BS) operation cost reduction, efficient renewable energy utilization, and stable energy supply. However, energy scheduling still faces some major challenges, such as coupling between energy sharing and energy trading, dimensionality curse, and intertwinement of social network attributes and BS load. To tackle these challenges, we propose a social-aware learning-based online energy scheduling (SNES) algorithm, which minimizes BS operation cost minimization under the constraints of energy supply stability. SNES leverages a deep neural network (DNN) to learn the action-state value of energy scheduling and intelligently adjusts purchased, sold, and shared energy based on only casual information. Moreover, SNES achieves social awareness by approximating the nonlinear interconnection between energy scheduling and quality of service (QoS) requirements of social network services. Simulation results verify the superior performance of SNES compared with state-of-the-art energy scheduling algorithms.

The concurrent availability of power-line communication, cellular and other wireless technologies, and the rapid development of concepts like multi-mode power internet of things (PIoT) and digital twin (DT) have made intelligent energy control a reality. However, information timeliness guarantee which determines DT consistency and energy control degradation is still an unsolved issue, as recent studies mainly focus on time-averaged guarantee and ignore the occurrence of extreme events. In this paper, we propose a novel metric named ultra-low age of information (ULAoI), which imposes more stringent constraints on extreme event occurrence probability and high-order statistics characteristics of excess AoI value. Moreover, we minimize energy control performance degradation by optimizing communication control, which acts as the bridge connecting information collection and utilization. A joint device scheduling and multi-mode channel allocation algorithm based on ULAoI-prioritized learning is proposed to achieve communication and control integration. Simulation results verify that the proposed algorithm can significantly reduce energy control performance degradation and achieve ULAoI guarantee.

Abstract Carbon footprint monitoring provides significant basis for computing facilities to improve the computing efficiency and reduce the energy cost, which can enable low/zero carbon computing and facilitate the construction of sustainable cites. Massive sensing devices access to 5G base station to transmit collected carbon emission data, which requires intelligent access management. Fast uplink grant possesses the advantages of reducing signalling overhead and access conflicts while facing the problems of incomplete information and difficulty in guaranteeing priority constraint. This paper examines, the maximum access queuing delay minimization problem is formulated under the long‐term service priority constraint and the short‐term access management constraint. First, Lyapunov optimization is leveraged to decouple the long‐term service priority constraint and short‐term access management optimization, and decompose the long‐term stochastic optimization problem into a series of short‐term deterministic problems. Then, a priority‐aware deep Q‐network (DQN)‐based fast uplink grant access management (PDAC) algorithm is proposed to achieve intelligent access management with differentiated service priority requirements. PDAC utilizes DQN to handle non‐convex high‐dimensional optimization problem with service priority constraint to achieve intelligent access management and priority awareness. Simulation results demonstrate that PDAC outperforms the existing algorithms in access queuing delay, buffer queue backlog, and priority deficit fluctuation.

Age of information (AoI) is an important metric of information timeliness, which determines digital twin (DT) consistency and energy management precision. However, AoI guarantee in the time-averaged sense is unreliable to avoid the occurrence of extreme event. In this paper, we propose a novel information timeliness metric named ultra-low AoI (ULAoI). Compared with AoI, ULAoI further considers the occurrence of extreme event and higher-order statistical characteristics of excess AoI value. Multi-dimensional resources of power internet of things (PIoT) are jointly allocated to achieve ULAoI guarantee from the perspective of sensing-communication-control integration. ULAoI-DT-Prioritized deep Q network (DQN) is proposed to achieve coordinated resource allocation by approximating unobservable information with the assistance of ULAoI-DT, and preventing DQN training from using samples with large AoI based on ULAoI-induced priority. Simulation results demonstrate the superior performance of the proposed algorithm in global loss function, ULAoI guarantee, and energy management optimality.

The real-time electrical equipment management, such as renewable energy, controllable loads, and storage units, plays a key role in low-carbon operation of smart industrial park. Digital twin (DT), which explores cloud-edge-device collaboration and artificial intelligence to establish accurate digital representation of physical equipment, is a cutting-edge technology to realize intelligent optimization of electrical equipment management. However, the practical implementation still faces reliability and communication efficiency problems, such as adverse impact of electromagnetic interference on DT reliability, high communication cost of DT model training, and uncoordinated resource allocation among cloud, edge, and device layers. We propose a Cloud-edge-device Collaborative reliable and Communication-efficient DT for lOW-carbon electrical equipment management named$\text{C}^{3}$-FLOW. It minimizes the long-term global loss function and time-average communication cost by jointly optimizing device scheduling, channel allocation, and computational resource allocation. Simulation results verify that$\text{C}^{3}$-FLOW performs superior in loss function, communication efficiency, and carbon emission reduction.

Space-assisted vehicular networks (SAVN) provide seamless coverage and on-demand data processing services for user vehicles (UVs). However, ultra-reliable and low-latency communication (URLLC) demands imposed by emerging vehicular applications are hard to be satisfied in SAVN by existing computation offloading techniques. Traditional deep reinforcement learning algorithms are unsuitable for highly dynamic SAVN due to the underutilization of environment observations. An AsynchronouS federaTed deep Q-learning (DQN)-basEd and URLLC-aware cOmputatIon offloaDing algorithm (ASTEROID) is presented in this paper to achieve throughput maximization considering the long-term URLLC constraints. Specifically, we first establish an extreme value theory-based URLLC constraint model. Second, the task offloading and computation resource allocation are decomposed by employing Lyapunov optimization. Finally, an asynchronous federated DQN-based (AF-DQN) algorithm is presented to address the UV-side task offloading problem. The server-side computation resource allocation is settled by an queue backlog-aware algorithm. Simulation results verify that ASTEROID achieves superior throughput and URLLC performances.

Dispatching and control information freshness conducts an important impact on the training accuracy of distributed energy dispatching and control model. Poor information freshness will increase the loss function of the training model, and reduce the reliability and economy of dispatching and control. Simplified power internet of things can provide plug-and-play and multi- mode fusion communication support, but it still faces challenges of the coupling of model training and data transmission as well as the difficulty in guaranteeing dispatching and control information freshness. In this paper, a semi-distributed federated learning- based framework for dispatching and control model training decision-making is proposed, and a dispatChing and control informAtion fReshness-aware batch size Optimization aLgorithm (CAROL) is presented. CAROL leverages deep Q network and dispatching and control information freshness awareness to learn the batch size optimization strategy. CAROL can minimize model loss function while guaranteeing long-term dispatching and control information freshness constraints. Compared with existing feder- ated learning algorithms, CAROL achieves superior performance in global loss function and information freshness.

Multi-mode power internet of things (PIoT) provides spatio-temporal coverage for low-carbon operation in smart park through combining various communication media. Heterogeneous resources are dynamically and intelligently managed to improve resource utilization and achieve anti-eavesdropping. However, resource management in multi-mode power IoT confronts challenges such as the mutual contradiction in joint communication and security quality of service (QoS) guarantee and the inadaptability to low-carbon services. In this paper, we propose an Adaptive learNing-based secure and enerGy-awarE resource management aLgorithm (ANGEL) to optimize multi-mode channel selection and power splitting for artificial noise (AN)-based anti-eavesdropping. Based on deep actor-critic (DAC) and “win or learn fast (WoLF)” mechanism, ANGEL can realize multi-attribute QoS guarantee, adaptive resource management, and security enhancement. Simulation results demonstrate its superior performance in energy consumption, secrecy capacity, and adaptability to differentiated low-carbon services.

Digital twin (DT) provides a real-time digital representation of electric device state for energy dispatching and control (EDC) model training in power system. However, the large age of information (AoI) deteriorates the consistency of DT and the precision of EDC model. In this paper, we investigate the global loss function minimization problem underthe long-term AoI constraint through coordinated resource management. The optimization problem is decoupled based on telescoping sum and Lyapunov optimization, and solved by the proposed AoI-aware DT-assisted intelligent resource management algorithm named AoI-DT. AoI-DT achievesa balanced tradeoff between AoI guarantee and EDC model precision through device scheduling and channel allocation. Simulation results verify the superior performance of AoI-DT in terms of global loss function and AoI compared withtwo state-of-the-art algorithms.

The combination of air–ground integrated power Internet of Things (AGI-PIoT) and cloud-edge-end collaboration enables flexible coverage and real-time data processing. However, how to achieve intelligent cloud-edge-end collaboration in AGI-PIoT faces several challenges such as dynamics of aerial networks, coupling of resource allocation in multiple layers, timescales, and dimensions, incomplete information, and dimensionality curse. In this article, we propose a FEderated Deep rEinforcement leaRning-based multi-lAyer multi-Timescale multi-dImensional resOurce allocatioN algorithm (FEDERATION). The multilayer multitimescale multidimensional resource allocation problem is decomposed into three subproblems based on Lyapunov optimization. For the subproblem of joint task offloading and power control, a federated deep actor-critic-based semidistributed algorithm is developed. The subproblem of admission control is solved by quadratic programming. The third subproblem is addressed through smooth approximation and Lagrange dual decomposition. Simulation results indicate that FEDERATION outperforms existing algorithms in queuing delay, energy consumption, and convergence.

Digital twin (DT) provides accurate guidance for multidimensional resource scheduling in 5G edge computing-empowered distribution grids by establishing a digital representation of the physical entities. In this article, we address the critical challenges of DT construction and DT-assisted resource scheduling such as low accuracy, large iteration delay, and security threats. We propose a federated learning-based DT framework and present a Secure and lAtency-aware dIgital twin assisted resource scheduliNg algoriThm (SAINT). SAINT achieves low-latency, accurate, and secure DT by jointly optimizing its total iteration delay and loss function, and leveraging abnormal model recognition (AMR). SAINT enables intelligent resource scheduling by using DT to improve the learning performance of deep Q-learning. SAINT supports access priority and energy consumption awareness due to the consideration of long-term constraints. Compared with state-of-the-art algorithms, SAINT has superior performance in cumulative iteration delay, DT loss function, energy consumption, and access priority deficit.

The integration of air-ground electricity internet of things (AGE-IoT) and machine learning, enables flexible network coverage and intelligent task offloading. However, dynamics of AGE-IoT networks, incomplete information, and resource allocation coupling are still major challenges in achieving intelligent AGE-IoT. In this paper, we investigate a joint multi-timescale task offloading and power control optimization problem to minimize the queuing delay of all the EIoT devices under the long-term constraint of energy consumption. We firstly decompose the joint optimization problem and transform it to large-timescale task offloading optimization and small-timescale power control optimization. Then, we propose a fed-erated deep actor-critic-based task offloading algorithm (FDAC) with two actor-critic networks for multi-timescale optimization. Numerical results show that FDAC has excellent performances in queuing delay and energy consumption compared with existing algorithms.

Air-Ground Integrated Power Internet of Things (AGI-PIoT) is a key enabler to meet the stringent communication and computing requirements of PIoT devices. In AGI-PIoT, the computation-intensive and delay-sensitive tasks can be either offloaded to edge servers through unmanned aerial vehicles (UAVs) or offloaded to cloud servers through ground base stations (GBSs), while the computational resources of edge servers and cloud servers should be jointly allocated. However, the joint optimization of task offloading and resource allocation faces several challenges such as incomplete information, dimensionality curse, and coupling between long-term constraints of queuing delay and short-term decision making. In this paper, we propose a learning-based QUeue-AwaRe Task offloading and rEsouRce allocation algorithm (QUARTER). Specifically, by exploiting Lyapunov optimization, the joint optimization problem is decomposed into task offloading and server-side resource allocation. For the first subproblem, we propose a Queue-aware Actor-Critic-based task offloading algorithm named QAC to cope with dimensionality curse. A low-complexity heuristic algorithm is developed to solve the second subproblem. Compared with existing task offloading and resource allocation algorithms, simulation results demonstrate that QUARTER has superior performances in throughput, queuing delay, and convergence.

Space-air-ground-integrated power Internet of Things (SAG-PIoT) can provide ubiquitous communication and computing services for PIoT devices deployed in remote areas. In SAG-PIoT, the tasks can be either processed locally by PIoT devices, offloaded to edge servers through unmanned aerial vehicles (UAVs), or offloaded to cloud servers through satellites. However, the joint optimization of task offloading and computational resource allocation faces several challenges, such as incomplete information, dimensionality curse, and coupling between long-term constraints of queuing delay and short-term decision making. In this article, we propose a learning-based queue-aware task offloading and resource allocation algorithm (QUARTER). Specifically, the joint optimization problem is decomposed into three deterministic subproblems: 1) device-side task splitting and resource allocation; 2) task offloading; and 3) server-side resource allocation. The first subproblem is solved by the Lagrange dual decomposition. For the second subproblem, we propose a queue-aware actor-critic-based task offloading algorithm to cope with dimensionality curse. A greedy-based low-complexity algorithm is developed to solve the third subproblem. Compared with existing algorithms, simulation results demonstrate that QUARTER has superior performances in energy consumption, queuing delay, and convergence.

In the Internet of Health Things (IoHT)-based e-Health paradigm, a large number of computational-intensive tasks have to be offloaded from resource-limited IoHT devices to proximal powerful edge servers to reduce latency and improve energy efficiency. However, the lack of global state information (GSI), the adversarial competition among multiple IoHT devices, and the ultra reliable and low latency communication (URLLC) constraints have imposed new challenges for task offloading optimization. In this article, we formulate the task offloading problem as an adversarial multi-armed bandit (MAB) problem. In addition to the average-based performance metrics, bound violation probability, occurrence probability of extreme events, and statistical properties of excess values are employed to characterize URLLC constraints. Then, we propose a URLLC-aware Task Offloading scheme based on the exponential-weight algorithm for exploration and exploitation (EXP3) named UTO-EXP3. URLLC awareness is achieved by dynamically balancing the URLLC constraint deficits and energy consumption through online learning. We provide a rigorous theoretical analysis to show that guaranteed performance with a bounded deviation can be achieved by UTO-EXP3 based on only local information. Finally, the effectiveness and reliability of UTO-EXP3 are validated through simulation results.

Vehicular fog computing has emerged as a complementary framework for edge computing by leveraging the under-utilized computational resources of vehicles. However, how to reduce task offloading delay, queuing delay, and handover cost with incomplete information while simultaneously ensuring privacy, fairness, and security remains an open issue. In this paper, we develop a secure and intelligent task offloading framework to address these challenges. We exploit blockchain and smart contract to facilitate fair task offloading and mitigate various security attacks. Then, we design a subjective logic-based trustfulness metric to quantify the possibility of task offloading success, and develop a trustfulness assessment mechanism. An online learning-based intelligent task offloading algorithm named QUeuing-delay aware, handOver-cost aware, and Trustfulness Aware Upper Confidence Bound (QUOTA-UCB) is proposed, which can learn the long-term optimal strategy and achieve a well-balanced tradeoff among task offloading delay, queuing delay, and handover cost. Finally, extensive theoretical analysis and simulations are carried out to demonstrate the reliability, feasibility, and efficiency of the proposed secure and intelligent task offloading scheme.

Existing task offloading mechanisms are developed on some single and rigid quality of service (QoS) performance metrics, which is widely apart from satisfying the true intent of a user vehicle (UV), thereby resulting in low quality of experience (QoE), large queuing latency, and poor reliability. There is an unprecedented demand for an intent-aware task offloading strategy that provides improved QoE and guarantees reliability. In this paper, we develop a novel task offloading framework for air-ground integrated vehicular edge computing (AGI-VEC), which is called the learning-based Intent-aware Upper Confidence Bound (IUCB) algorithm. IUCB enables a UV to learn the long-term optimal task offloading strategy while satisfying the long-term ultra-reliable low-latency communication (URLLC) constraints in a best effort way under information uncertainty. IUCB can achieve three-dimension intent awareness including QoE awareness, URLLC awareness, and trajectory similarity awareness. Simulation results demonstrate that IUCB significantly outperforms existing EMM, sleeping-UCB, and UCB mechanisms in terms of QoE, end-to-end delay, queuing delay, throughput, and times of task offloading failure.

In the Internet of Health Things based e-Health paradigm, a large number of computational-intensive tasks have to be offloaded from resource-limited IoHT devices to proximal powerful edge servers to reduce latency and improve energy efficiency. However, the lack of global state information (GSI), the ultra-reliable and low-latency communication (URLLC) constraints, and the adversarial competition among IoHT devices have imposed new challenges for task offloading optimization. In this paper, we formulate the task offloading problem as an adversarial multi-armed bandit (MAB) problem. In addition to the average-based performance metrics, bound violation probability of queuing delays and statistical properties of excess values are employed to characterize URLLC constraints. Then, we propose an energy-aware and URLLC-aware Task Offloading scheme based on the exponential-weight algorithm for exploration and exploitation (EXP3) named UTO-EXP3. Guaranteed performance with a bounded deviation can be achieved by UTO-EXP3 based on only local information. The effectiveness and reliability of UTO-EXP3 are validated through simulation results.

In this paper, we study the channel selection problem in edge computing-empowered cognitive machine-to-machine (CM2M) communications, where a massive number of machine type devices (MTDs) offload their computational tasks to a nearby edge server by opportunistically using the spectra that are temporarily unoccupied by primary users (PUs). We formulate the channel selection problem as an adversarial multi-armed bandit (MAB) problem, and combine the exponential-weight algorithm for exploration and exploitation (EXP3) and Lyapunov optimization to develop a learning-based energy-efficient solution named SEB-EXP3. It can find the long-term optimal channel selection strategy with guaranteed performance based on local information, while simultaneously achieving service reliability awareness, energy awareness, and data backlog awareness. Four heuristic algorithms are compared with SEB-EXP3 to demonstrate its effectiveness and reliability under various simulation settings.

Edge computing provides a promising paradigm to support the implementation of Industrial Internet of Things (IIoT) by offloading computational-intensive tasks from resource-limited machine-type devices (MTDs) to powerful edge servers. However, the performance gain of edge computing may be severely compromised due to limited spectrum resources, capacity-constrained batteries, and context unawareness. In this article, we consider the optimization of channel selection that is critical for efficient and reliable task delivery. We aim at maximizing the long-term throughput subject to long-term constraints of energy budget and service reliability. We propose a learning-based channel selection framework with service reliability awareness, energy awareness, backlog awareness, and conflict awareness, by leveraging the combined power of machine learning, Lyapunov optimization, and matching theory. We provide rigorous theoretical analysis, and prove that the proposed framework can achieve guaranteed performance with a bounded deviation from the optimal performance with global state information (GSI) based on only local and causal information. Finally, simulations are conducted under both single-MTD and multi-MTD scenarios to verify the effectiveness and reliability of the proposed framework.

With the wide development of smart devices, fog computing has emerged as a promising solution to accommodate the ever-increasing computational demands in Internet of things (IoT). However, there are two major obstacles hindering the wide deployment of IoT fog computing, i.e., how to realize server recruitment under information asymmetry and reliable task assignment under information uncertainty. In this article, we develop a robust two-stage task offloading algorithm by integrating contract theory with computational intelligence. In the first stage, we propose a contract based server recruitment scheme to motivate servers to share residual computational resources. In the second stage, by leveraging multi-armed bandit (MAB), we develop a reliable volatile upper confidence bound (RV-UCB) algorithm to minimize the long-term delay of task assignment, which takes into account task awareness, occurrence awareness and location awareness. Finally, a series of stimulation results are carried out to validate the performance of the proposed algorithm.

Vehicular fog computing (VFC) has emerged as a cost-efficient solution for task processing in vehicular networks. However, how to realize stable and reliable task offloading under information uncertainty remains a critical challenge. In this paper, we propose a matching-learning-based task offloading algorithm to address this challenge. First, a low-complexity and stable task offloading mechanism is proposed to minimize the total network delay based on the pricing-based matching. Second, we extend the work to the scenario of information uncertainty, and develop a matching-learning-based task offloading algorithm by combining matching theory and upper confidence bound (UCB) algorithm. Simulation results demonstrate that the proposed algorithm can achieve bounded deviation from the optimal performance without the global information.