ABSTRACT With the rapid development of mobile cloud computing, the computational capability of edge devices has gradually attracted attention. Computation offloading is a strategy to improve computational efficiency and resource utilization by transferring computational tasks from the main device to edge devices or cloud nodes. Traditional computation offloading methods may have limitations when facing large‐scale and high‐real‐time tasks. To solve these problems, this article proposes a computation offloading method based on an improved whale optimization learning algorithm. First, the computational requirements of each device are planned using the topological sorting method, and the transmission time, energy consumption, and other parameters are determined. Then, a fitness function that considers both computation time and energy consumption is proposed, and the nonconvexity of this function is proved. Finally, the improved whale optimization learning algorithm is applied to the entire device group to solve the optimal offloading ratio. Experimental results show that our proposed strategy has good performance in reducing latency and energy consumption.

The mobile Internet of Things (IoT) has gained popularity due to the quick advancement of mobile communication and intelligent terminal technologies.Focusing on some computationally demanding activities and latency-sensitive services (like health IoT) in smart healthcare that cloud computing (CC) cannot process and respond to rapidly. This research examines the fog computing (FC) and deep reinforcement learning (DRL) strategy-based edge computing resource allocation technique. This methodology generates computational tasks for mobile users at random throughout time. The mobile user has the option to load these tasks to the fog node at the edge or carry out local activities on additional mobile devices (MDs). A proximal policy optimization approach based on DRL is proposed for allocating computational resources to achieve low latency and low system energy consumption, thereby maximizing system revenue while concurrently enhancing the system’s overall quality of service. Its core idea is to combine the advantages of FC’s low-latency processing at the edge with the adaptive decision-making capability of DRL for dynamic resource states. This is achieved by considering the processing location of the computational tasks and the interaction between the device that generates the tasks and other MDs or FC nodes (FNs). According to experimental data, this approach has successfully decreased energy usage and network latency, compared with other algorithms. When the number of candidate nodes is 3, it achieves the lowest average latency and a notably reduced average energy consumption. Moreover, as the number of MDs increases, it maintains the optimal total system overhead and yields the highest average revenue.

Task offloading, as an effective solution, provides low latency and sufficient computing resources for mobile users in the network. However, how to reasonably offload to reduce system overhead is a challenging issue today. This article takes user terminals, edge servers, and idle vehicles with resources as the network structure, and is inspired by the highly social nature of the gray wolf pack. It proposes a new offloading method of edge computing task based on hunting optimizing mechanism of gray wolf for the Internet of Vehicle (IOV). Firstly, an adaptive weight factor is proposed to balance the weight ratio of delay and energy consumption in the system cost under the constraints of delay and energy consumption. With delay and computing resources of vehicles and servers as constraints, a multi constraint minimization system cost problem is proposed. Secondly, the hunting process of the gray Wolf optimization algorithm is used to find the optimal solution of the unloading scheme, The Levy flight strategy was added to enhance the global search ability of the algorithm, and a dynamic weight strategy was introduced to improve the convergence performance of the algorithm. Finally, the improved gray Wolf optimization algorithm was used to solve the optimal unloading plan and minimum cost. The simulation results show that compared with traditional gray Wolf optimization algorithm offloading schemes, the proposed scheme in this paper requires lower system costs.

As an important branch of the Internet of Things (IoT), vehicular networks play a crucial role in the construction of intelligent transportation systems. However, due to the rapid movement of vehicles and signal obstruction, achieving high- quality and low-latency communication in vehicular networks remains a significant challenge. To address this issue, this paper proposes a novel data communication method based on interval type-2 fuzzy logic and cooperative game theory. Firstly, interval type-2 fuzzy logic is utilized to infer vehicle stability, thereby selecting high-quality backbone nodes. Concurrently, the memory and forgetfulness functions of the Gated Recurrent Unit are employed to retain critical data packets. Subsequently, a greedy algorithm and cooperative game theory model are used to describe the behavior of vehicles in Roadside-to-Vehicle (R2V) communication and Vehicle-to- Vehicle (V2V) communication, respectively. This approach encourages backbone nodes to cooperate and serve other vehicles based on a benefit function. Experimental results demonstrate that the proposed method excels in terms of transmission delay, coverage range, and data packet delivery success rate.

Mobile edge computing (MEC) provides reliable solutions for networked vehicles, mobile phones, and other mobile devices to complete intensive computing and delay-sensitive tasks. Most of the existing studies design a series of methods to achieve the expected goals based on assuming that users are absolutely rational. However, due to the subjectivity of users, the actual results will deviate from the real situation. Using the prospect theory (PT) framework, this article studies the problem of computing task offloading in real situations. Aiming at the task offloading problem in the small cellular network scenario, the artificial fish swarm algorithm is used to optimize the system energy with limited delay. Finally, the experimental tests verify the impact of user behavior on the system energy optimization and the effectiveness of the task offloading method proposed in this article.

Edge computing technology can be used to the Internet of Vehicles (IOV) to solve the mobile characteristics of vehicles and the limited communication range between roadside units and vehicles. New method of edge computing-based data adaptive return in IOV is proposed in this article. The transmission strategy can be determined by adaptive estimating the vehicle movement, the amount of data returned, the maximum transmission delay, and effective life of link. And the factors, such as speed, direction, and position of the vehicles, are comprehensively considered and these factors can be measured by the stability effect value when adaptive designing the auxiliary transmission strategy. At the same time, greedy selection method is used when constructing the data return link, and the neighbor node as the relay node with the maximum stability and efficiency value is chosen. Our experimental results show our method in terms of performance on transmission delay and packet delivery rate is better than other ones.

Mobile edge computing provides the possibility for efficient use of mobile devices, but the disclosure of user privacy is still a huge hidden danger. In order to solve the problem of user locking caused by device usage pattern, a privacy aware computing offloading method based on privacy entropy is proposed. By quantifying privacy as privacy entropy, the problem is modeled as maximizing privacy entropy and minimizing computing offloading resource consumption. The Gaussian-Cauchy operator is proposed to improve the Harris hawks optimization algorithm, to expand the search scope of the algorithm and enhance the ability to jump out of the local optimal. Experimental results show that this method can not only ensure the confusion of user information, but also minimize resource consumption and effectively solve the problem of privacy disclosure of behavior mode.

The internet of vehicles (IoVs) provides delay-sensitive services, but high-latency communication with roadside units causes service failures and high costs. Mobile edge computing (EC) is migrating cloud computing platforms from the core network to the edge of mobile networks, giving vehicles local access to numerous computing resources. The classic greedy boundary stateless routing (GPSR) method is widely used to meet the communication requirements of vehicle self-organizing networks. In order to solve the problems of GPSR’s neighbor node position acquisition lag and single routing criterion, a new routing method based on the fuzzy logic system [Geographic Routing method based on Velocity, Angle, and Density (GRVAD)] is proposed. This method gets the relative velocity between the nodes and the angle between the current node, the neighbor node and the target node, and the node density of the neighbor node as the input of fuzzy logic, and the unscented Kalman filter is used to predict the location of the neighbor node to obtain more accurate location information of neighbor nodes. Simulation results show that the routing method compensates for some of the shortcomings of the GPSR method and reasonably considers the delivery rate and end-to-end delay of data packets and is more in line with the communication requirements of the vehicle ad hoc network.

Along with the development of Internet of Vehicles (IoV) and wireless technology, the usage of applications that require low latency, such as autonomous driving and intelligent navigation, is increasing rapidly, and the demand for content is increasing greatly. This paper proposes an edge caching approach for the IoV based on multi-agent deep reinforcement learning (ECSMADRL) so as to resolve the problem of excessive response delay due to the large increase of data traffic in the IoV. The approach jointly considers content distribution and caching in dynamic environments. In other words, each moving vehicle in the IoV can be seen as an agent, and it can make decisions about content caching and content access adaptively according to the changing environment to minimize the delay in the process of content distribution. It is proved by experiments that compared with other methods, the proposed edge caching (EC) approach has better performance in reducing content distribution delay, improving content hit rate and success rate.

The privacy protection of perceptual user and their enthusiasm improvement for participating in perceptual tasks are two important problems in MCS (Mobile Crowdsensing) network. A mechanism of local differential privacy protection of attribute correlation can generate perceptual results with higher precision of attribute correlation and protect perceptual users’ privacy data. A flow compensation incentive model for perceptual users’ privacy data protection based on opportunity cooperation transmission can reduce the flow compensation expenditure of MCS and improve perceptual users’ enthusiasm. Experiments show that our approach improves the perceptual result precision, reduces MCS overhead, and reduces flow compensation cost compared with the related approaches.

Mobile management is a challenging technology in Mobile Edge Computing (MEC). When the device is moving, computation tasks need to be dynamically migrated between multiple edge servers to maintain service continuity. This paper proposes a migration optimization of distributed task in MEC by deep reinforcement learning solution to optimize delay. In Multi-agent Deep Reinforcement Learning (MADRL), we construct an adaptive weight deep deterministic policy gradient (AWDDPG) algorithm to optimize the migration cost and service delay, and adopt centralized training and distributed execution to solve the high-dimensional problem. Experiments show that our algorithm greatly reduces the service delay compared with the related algorithms.

To solve the incentive problem for MCS (Mobile Crowdsensing) users based on privacy protection, we proposed an incentive method of flow compensation for the privacy protection of users and designed a system model which combined MCS with MEC (Mobile Edge Computing). The EC (Edge Center) uploaded the perception results to the MCS diminishing MCS’s overhead. We also designed an incentive model based on Q-Learning algorithm for privacy protection of user data, which can reduce the incentive expenditure and improve users’ enthusiasm for participation. Compared with the existing incentive method based on privacy protection, our method improves the perceptual result precision, decreases MCS cloud overhead, and declines flow compensation cost.

In order to effectively predict reliability of the link between two vehicles of VANETs (Vehicular ad hoc networks) and design a reliable routing protocol to satisfy various applications requirements, we analyze the details about motion characteristics of the vehicle and the reasons that cause links disconnect in this paper. We evaluate the reliability of links and introduce it as an important parameter to design a novel routing protocol. The Q-Learning algorithm is used to dynamically adjust the routing path through interaction with the surrounding environment. Based on these, a new reliable self-adaptive routing protocol (RSAR) is proposed. The experimental results show that the performance of RSAR protocol is very good on delivery rate and delay.