Delay-sensitive task offloading in a device-to-device assisted mobile edge computing (D2D-MEC) system with energy harvesting devices is a critical challenge due to the dynamic load level at edge nodes and the variability in harvested energy. In this paper, we propose a joint dynamic task offloading and CPU frequency control scheme for delay-sensitive tasks in a D2D-MEC system, taking into account the intricacies of multi-slot tasks, characterized by diverse processing speeds and data transmission rates. Our methodology involves meticulous modeling of task arrival and service processes using queuing systems, coupled with the strategic utilization of D2D communication to alleviate edge server load and prevent network congestion effectively. Central to our solution is the formulation of average task delay optimization as a challenging nonlinear integer programming problem, requiring intelligent decision making regarding task offloading for each generated task at active mobile devices and CPU frequency adjustments at discrete time slots. To navigate the intricate landscape of the extensive discrete action space, we design an efficient multi-agent DRL learning algorithm named MAOC, which is based on MAPPO, to minimize the average task delay by dynamically determining task-offloading decisions and CPU frequencies. MAOC operates within a centralized training with decentralized execution (CTDE) framework, empowering individual mobile devices to make decisions autonomously based on their unique system states. Experimental results demonstrate its swift convergence and operational efficiency, and it outperforms other baseline algorithms.

Device-to-device (D2D) is a pivotal technology in the next generation of communication, allowing for direct task offloading between mobile devices (MDs) to improve the efficient utilization of idle resources. This paper proposes a novel algorithm for dynamic task offloading between the active MDs and the idle MDs in a D2D–MEC (mobile edge computing) system by deploying multi-agent deep reinforcement learning (DRL) to minimize the long-term average delay of delay-sensitive tasks under deadline constraints. Our core innovation is a dynamic partitioning scheme for idle and active devices in the D2D–MEC system, accounting for stochastic task arrivals and multi-time-slot task execution, which has been insufficiently explored in the existing literature. We adopt a queue-based system to formulate a dynamic task offloading optimization problem. To address the challenges of large action space and the coupling of actions across time slots, we model the problem as a Markov decision process (MDP) and perform multi-agent DRL through multi-agent proximal policy optimization (MAPPO). We employ a centralized training with decentralized execution (CTDE) framework to enable each MD to make offloading decisions solely based on its local system state. Extensive simulations demonstrate the efficiency and fast convergence of our algorithm. In comparison to the existing sub-optimal results deploying single-agent DRL, our algorithm reduces the average task completion delay by 11.0% and the ratio of dropped tasks by 17.0%. Our proposed algorithm is particularly pertinent to sensor networks, where mobile devices equipped with sensors generate a substantial volume of data that requires timely processing to ensure quality of experience (QoE) and meet the service-level agreements (SLAs) of delay-sensitive applications.

Unmanned aerial vehicles (UAVs) have emerged as crucial components in advancing mobile edge computing (MEC), leveraging their proximity to edge nodes and scalable nature. This synergy holds significant promise within the Internet of Things (IoT) and Beyond 5G (B5G) domains. In this article, we concentrate on optimizing the shrinking ratio, a Quality of Experience (QoE) metric, within large-scale IoT networks empowered by UAV-enhanced MEC via joint optimizing task offloading, resource allocation, and UAV trajectories. This joint optimization problem presents significant challenges due to the intertwined nature of multiuser computing mode selection and strong coupling between user equipments (UEs) waiting time and UAV trajectory. To tackle these challenges, we formulate the problem as a mixed integer nonlinear programming (MINLP) problem and propose an iterative algorithm named BTOU by decomposing the original problem into two subproblems using the block coordinate descent (BCD) framework. For the task offloading and resource allocation subproblem, we present two algorithms: one employs a low-complexity greedy game-theoretic approach suitable for a large number of UEs, while the other leverages the penalty successive convex approximation (PSCA) technique along with first-order Taylor expansion approximation to achieve high-solution quality. For the UAV trajectory planning subproblem, we transform it into a Miller-Tucker–Zemlin (MTZ) model and devise a solution strategy. Extensive simulation results validate the effectiveness of our proposed algorithm, showcasing rapid convergence and a notable improvement in QoE of over 10% compared to benchmark methods.

Mobile edge computing (MEC) integrated with wireless power transfer (WPT) has became a promising trend to shorten task delay and prolong battery life of wireless devices (WDs). Introducing the relay technique to WPT-MEC system can improve offloading capability and energy efficiency, particularly in the scenarios of poor wireless channel conditions between the server and WDs. In this paper, we focus on maximizing the energy efficiency (EE) of a multi-user relay-aided WPT-MEC system. The joint optimization of the configuration of relay, wireless charge time fraction, and decision of WDs’ offloading strategy presents significant challenges due to the combination of multi-user computing mode selection and strong coupling of transmission time allocation for each WD. To address these challenges, we formulate the problem as a mixed integer nonlinear programming (MINLP) problem and propose an efficient iterative algorithm called MSRA to solve it. Our approach leverages Dinkelbach’s method to transform the original problem into a tractable problem. Furthermore, we employ the alternating direction method of multipliers (ADMM) technique to decompose the problem into multiple subproblems, thereby avoiding the combination of computing mode selection at each WD and hence enabling parallel computation. Within each iteration step of the ADMM-based algorithm, we develop a DAI-Based algorithm to handle the strong coupling with offloading time allocation that incorporates a Bisection Search algorithm with constant time complexity and solves a standard convex problem. Extensive simulation results demonstrate the effectiveness of our proposed algorithm as evidenced by its rapid convergence and impressive energy efficiency imporvement of over 15% compared to benchmark methods.

Capturing long-term dependency from historical behaviors is the key to the success of sequential recommendation; however, existing methods focus on extracting global sequential information while neglecting to obtain deep representations from subsequences. Previous research has revealed that the restricted inter-item transfer is fundamental to sequential modeling, and some potential substructures of sequences can help models learn more effective long-term dependency compared to the whole sequence. To automatically find better subsequences and perform efficient learning, we propose a sequential recommendation model with a gated recurrent unit and Transformers, abbreviated as GAT4Rec, which employs Transformers with shared parameters across layers to model users’ historical interaction sequences. The representation learned by the gated recurrent unit is used as the gating signal to identify the optimal substructure in user sequences. The fused representation of the subsequence and edge information is extracted by the encoding layer to make the corresponding recommendations. Experimental results on four well-known publicly available datasets demonstrate that our GAT4Rec model outperforms other recommendation models, achieving performance improvements of 5.77%, 1.35%, 11.58%, and 1.79% in the normalized discounted cumulative gain metric (NDCG@10), respectively.

Mobile Edge Computing (MEC) integrated with Wireless Power Transfer (WPT) is emerging as a promising solution to reduce task delays and extend the battery life of Mobile Devices (MDs). However, maximizing the long-term energy efficiency (EE) of a user-cooperative WPT-MEC system presents significant challenges due to uncertain load dynamics at the edge MD and the time-varying state of the wireless channel. In this paper, we propose an online control algorithm to maximize the long-term EE of a WPT-MEC system by making decisions on time allocations and transmission powers of mobile devices (MDs) for a three-node network. We formulate a stochastic programming problem considering the stability of network queues and time-coupled battery levels. By leveraging Dinkelbach’s method, we transform the fractional optimal problem into a more manageable form and then use the Lyapunov optimization technique to decouple the problem into a deterministic optimization problem for each time slot. For the sub-problem in each time slot, we use the variable substitution technique and convex optimization theory to convert the non-convex problem into a convex problem, which can be solved efficiently. Extensive simulation results demonstrate that our proposed algorithm outperforms baseline algorithms, achieving a 20% improvement in energy efficiency. Moreover, our algorithm achieves an $\left[O\right(1/V),O(V\left)\right]$ trade-off between EE and network queue stability.