With the rapid advancement of Internet of Things (IoT), there is a growing demand for intelligent applications with varying requirements (e.g. delay, reliability, and energy). Mobile Edge Computing (MEC) can enhance the responsiveness of these applications by caching specific computing services on edge servers. However, the efficiency of task offloading and service caching at MEC servers is often hindered by the diversity of user preferences and privacy across different edge node service regions, especially in heterogeneous networks. To this end, we introduce a personalized computation offloading and service caching method that integrates Deep Reinforcement Learning (DRL) with Personalized Federated Learning (PFL), termed DPFL, aimed at optimizing computation performances in a distributed and privacy-preserving manner. The DPFL employs DRL to jointly optimize computation offloading and service caching placement, reducing task latency and energy consumption. Simultaneously, it leverages personalized federated learning to develop local service prediction models, offering tailored service caching policies for users in heterogeneous regions while safeguarding data privacy. Simulation results demonstrate that our algorithm surpasses existing policies in reducing application delay, energy consumption, and improving system cache hit ratio.

The multi-access edge computing (MEC) and ultra-dense network (UDN) are regarded as essential and complementary technologies in the age of Internet of Things (IoT). Deploying MEC servers at the macro-cell and small-cell stations can significantly improve user experience as well as increase network capacity. Nevertheless, there still remain many obstacles in practical MEC-enabled UDNs. Among them, a unique challenge is how to coordinate computing and networking to fit the diverse offloading demands of IoT applications in dynamic network environments. To this end, this paper first investigates a distributed delay-constrained computation offloading methodology based on computing and networking coordination in the UDN. An extended game-theoretic approach based on the Lyapunov optimization theory is designed to achieve adaptive task offloading and computing power management in time-varying environments. Furthermore, considering the uncertainty in users' mobility and limited edge resources, distributed two-stage and multi-stage stochastic programming algorithms under various uncertainties are proposed. The proposed algorithms take posterior recourse actions to compensate for inaccurate predicted network information. Extensive simulations validate the effectiveness and rationality of the proposed algorithms and their superior performance over several benchmark schemes.

Mobile edge computing (MEC) enables various services to be cached in close proximity to the user equipments (UEs), thereby reducing the service delay of many emerging applications. However, the limitation of storage, computation, and radio resources, the dynamics of the decentralized MEC environment, and the complex spatial relationships of service request types and wireless network states between edge nodes make it difficult to realize efficient edge computing services. To address these challenges, this paper integrates the digital twin (DT) technology with a multi-cell MEC network to study an intelligent cooperative task offloading and service caching scheme, aiming at maximizing a quality of services (QoE)-based system utility. Specifically, we first construct a digital twin edge network (DITEN) to reflect the physical MEC system in real-time and provide data for training. With the help of DT technology, it is easy to access data resources in the DITEN to improve the simulation ability and reduce the communication cost. Then, we propose a graph attention-based multi-agent reinforcement learning (GatMARL) algorithm to learn the optimal task offloading and service caching strategies in the DITEN. The GatMARL employs a graph attention-based value decomposition network to capture the potential spatial relationships between edge nodes to learn better attentive cooperation policy. Simulation results demonstrate that the proposed GatMARL algorithm exhibits an effective performance improvement compared with state-of-the-art benchmarks.

Accurate spatial-temporal traffic modeling and prediction play an important role in intelligent transportation systems (ITS). Recently, various deep learning methods such as graph convolutional networks (GCNs) and recurrent neural networks (RNNs) have been widely adopted in traffic prediction tasks to extract spatial-temporal dependencies based on a large volume of high-quality training data. However, there exist data scarcity problems in some transportation networks, and in these cases, the performance of traditional GCNs and RNNs based approaches will degrade sharply. To address this problem, this paper proposes an adversarial domain adaptation with spatial-temporal graph convolutional network (Ada-STGCN) model to predict traffic indicators for a data-scarce target road network by transferring the knowledge from a data-sufficient source road network. Specifically, Ada-STGCN first develops a spatial-temporal graph convolutional network that combines the GCN and gated recurrent unit (GRU) to extract spatial-temporal dependencies from source and target road networks. Then, the technique of adversarial domain adaptation is integrated with the spatial-temporal graph convolutional network to learn discriminative and domain-invariant features to facilitate knowledge transfer. Experimental results on the real-world traffic datasets in the traffic flow prediction task demonstrate that our model yields the best prediction performance compared to state-of-the-art baseline methods.

Mobile edge computing (MEC) enables various services to be cached in close proximity to the user equipments (UEs), thereby reducing the computing delay of many emerging applications. Nevertheless, The limited storage capacity of edge servers requires judicious design of service caching as well as task offloading to maximize edge computing performances. In this paper, we formulate a cooperative task offloading, service caching, and transmit power allocation problem to minimize the cost of computing delay and energy consumption of UEs. To address this problem, we propose a graph attention based multi-agent deep deterministic policy gradient (GAT-MADDPG) algorithm, in which a multi-headed graph attention mechanism is incorporated into the centralized critic network to learn the attentive cooperation policies. Simulation results show that the proposed GAT-MADDPG algorithm exhibits an effective performance improvement.

With the rapid advancement of the Internet of Vehicles and artificial intelligence (AI) technologies, the cooperative intelligent transportation system (C-ITS) has drawn great attention in recent years. To provide an ultra-reliable, low-latency computation experience of C-ITS, computation offloading is deemed indispensable by working with edge-cloud servers. In this paper, we first investigate a distributed dynamic computation offloading model for multi-access edge computing (MEC) enabled C-ITS under a heterogeneous road network, in which the multiple and heterogeneous computing power sources cooperatively provide computation offloading services for vehicles. Considering the autonomous offloading manner of the vehicles, we formulate the task offloading and computing power allocation as a distributed Stackelberg game, where the MEC servers as the leader to allocate computing resources and manage local energy, and the vehicles as the followers to offload local computation task. Since the observable states in the game is incomplete, the problem of resolving the optimal strategies for each game player is modeled as a partially observable Markov decision process (POMDP) to maximize the long-term cumulative reward. Then we develop a computation offloading algorithm using Stackelberg game-based multi-agent deep deterministic policy gradient (SG-MADDPG), which uses a centralized training and decentralized execution method to learn the optimal computing power allocation and computation offloading policies. Finally, extensive simulations are carried out and show the rationality and effectiveness of the proposed algorithm.

With the rapid development and convergence of the mobile Internet and the Internet of Things (IoT), computing-intensive and delay-sensitive IoT applications (APPs) are proliferating with an unprecedented speed in recent years. Mobile edge computing (MEC) and energy harvesting (EH) technologies can significantly improve the user experience by offloading computation tasks to edge-cloud servers as well as achieving green and durable operation. Traditional centralized strategies require precise information of system states, which may not be feasible in the era of big data and artificial intelligence. To this end, how to allocate limited edge-cloud computing resource on demand, and how to develop heterogeneous task offloading strategies with EH in a more flexible manner are remaining challenges. In this paper, we investigate an EH-enabled MEC offloading system, and propose an online distributed optimization algorithm based on game theory and perturbed Lyapunov optimization theory. The proposed algorithm works online and jointly determines heterogeneous task offloading, on-demand computing resource allocation, and battery energy management. Furthermore, to reduce the unnecessary communication overhead and improve the processing efficiency, an offloading pre-screening criterion is designed by balancing battery energy level, latency, and revenue. Extensive simulations are carried out to validate the effectiveness and rationality of the proposed approach.

With the rapid development of Internet of Things (IoT) on e-Health, the role of Mobile Edge Computing (MEC) has been increasingly effective in providing high-performance, lowlatency computing services. In this work, we consider the problem of task offloading and computing resource allocation in dynamic environment, wherein heterogeneous IoT devices or e-Health applications with diverse requirements in latency and energy constraint. Taking into account the different traffic characteristics and spatio-temporally varying distributed environment, we formulate the offloading problem as a dynamic game and a Stackelberg Equilibrium (SE) based distributed online offloading manner is proposed. And then, to allocate computing resource on demand, a dynamic quote price mechanism is designed by invoking Lyapunov optimization. Furthermore, to improve processing efficiency and reduce unnecessary communication overhead, a “first-rank” servers selection criteria is proposed by balancing revenue and latency. Finally, the effectiveness and rationality of the algorithm are verified by experimental simulation.