Jul 2026· 2026 5th International Conference on Distributed Computing and Electrical Circuits and Electronics (ICDCECE)· pp. 1-7· 0 citations· 18 references
Abstract
Traditional resource scheduling strategies fail to fully utilize the computing and storage resources of edge nodes, leading to resource waste and overload of some nodes. This paper collects network topology and edge node resource information data for preprocessing. Then, a state space and action space are defined to record all possible system states and scheduling decisions in the edge computing environment. A two-layer deep Q-network model is constructed for action selection and Q-value calculation. Using 10-fold cross-validation and averaging, the optimized resource utilization reaches 85.18%, communication latency is $\mathbf{7 9. 1 m s}$, load balancing is improved to 0.841, and energy consumption and rejection rate are reduced to varying degrees, fully demonstrating the advantages of this algorithm in optimizing communication network resource scheduling in edge computing environments.
A task scheduling method using the Deep Q-Network to determine the computation node for the computation task and a dynamic congestion-aware mechanism to determine a low-cost routing path is proposed, which gradually obtains an effective task scheduling scheme through multiple rounds of alternating iterations.
Dynamic edge networks suffer from fluctuating bandwidth, latency, and edge-node load, which weaken conventional task offloading strategies under deadline and energy constraints. This study proposes an adaptive task offloading strategy based on dynamic network states. An online broad learning system predicts short-term bandwidth, transmission delay, and load from sliding-window observations. The predictions are embedded into a model predictive control framework for rolling optimization of the local-edge task allocation ratio, while confidence-interval-guided compensation adjusts decisions under prediction uncertainty. ADMM is used for distributed solution. NS-3/Python simulations show that the proposed method achieves a $93\%$ task success rate, 1.22 W average terminal energy consumption, 3.2 switches/s, and 45 ms average completion time, outperforming local execution, reactive offloading, and DQN-based offloading. The proposed strategy improves real-time reliability, energy efficiency, and robustness in highly dynamic edge computing environments.
Jie Yang, Peng Li, Guangfu Ge et al.· 2026 5th International Confe...· 0 citations
A Mixed Integer Nonlinear Programming (MINLP) model with the objective of a weighted sum of long-term average task completion rate, total latency and energy consumption is established, which improves the task completion rate by 4% in high load scenarios and achieves a better balance between latency and energy consumption.
Edge computing has emerged as an effective paradigm for processing latency-sensitive applications by bringing computational resources closer to end users. However, efficient task scheduling remains a significant challenge due to limited computational capacity, dynamic workloads, and varying network conditions. This paper proposes an Energy-Efficient Deep Reinforcement Learning (EE-DRL) framework that optimizes task scheduling while minimizing energy consumption and execution delay. The proposed framework employs a Deep Q-Network (DQN) to dynamically allocate computational tasks among heterogeneous edge nodes. Experimental analysis demonstrates that the proposed approach reduces average task completion time by 23%, lowers energy consumption by 19%, and improves resource utilization compared with traditional scheduling algorithms. The proposed framework provides an intelligent, adaptive, and scalable solution for future edge computing infrastructures.
Sophia M. Carter, Rohan V. Iyer, Emilio J. Navarro· Journal of Computer Science· 0 citations
A new paradigm for satisfying the ever-growing demands of real-time Sixth Generation (6G) applications is Mobile Edge Computing (MEC). Additionally, base stations and Internet of Things devices that incorporate renewable energy harvesting capabilities have the potential to lower grid energy use. To maximize system potential and lower carbon emissions, it is crucial to make effective decisions about job offloading and resource allocation. A carbon-aware MEC architecture that uses both grid and renewable energy sources is proposed in this paper. Our goal is to jointly manage resource allocation and task offloading while monitoring carbon emissions and task queue delays to optimize system behavior under uncertainty, specifically for stochastic workloads and variable renewable generation. To balance these two cost components (emissions and queue length), we create a combined optimization problem. We develop a deep deterministic policy gradient (DDPG)-based joint optimization technique to address this issue in a constantly changing environment. In the optimization, we consider greedy policy (GP) and full offloading (FO), as well as time-average carbon emission (TACE) and time-average queue length (TAQL) as performance metrics, and time-average queue length (TAQL) and full execution (FE) as baseline strategies; we also evaluate normalized time-average cumulative reward (NTACR). This method uses continuous-action reinforcement learning to generate efficient, real-time control policies. For the proposed MEC network, numerical statistics show that our approach can lead to effective offloading and lower carbon emissions.
M. Saeed, Rashid A. Saeed, M. A. Ahmed et al.· 2026 6th International Confe...· 0 citations
Satellite edge computing (SEC) has emerged as a promising paradigm to enhance in-orbit data processing capabilities and reduce transmission latency. However, satellite image processing tasks in SEC environments face critical challenges in efficient data handling, resource coordination, and transmission scheduling. The dynamic network topology and time-varying resource availability in satellite constellations further degrade the quality and stability of SEC services. To address these challenges, we propose a deep learning-based Collaborative Image Feature-extraction Task Optimization (CIFTO) framework. CIFTO dynamically distributes image processing workloads across multiple Low Earth Orbit (LEO) satellites, enabling continuous temporal updates for task allocation while significantly accelerating convergence and reducing computational overhead. By integrating temporal modeling and iterative optimization, CIFTO effectively mitigates the NP-hard nature of satellite task allocation. Furthermore, a lightweight satellite image processing model is designed to meet the strict constraints of on-orbit computation, achieving efficient image inference with minimal parameters. Extensive experimental evaluations demonstrate that the proposed framework ensures timely task completion, substantially lowers system-wide energy consumption, and enhances the adaptability and training efficiency of SEC services.
Xiaoteng Yang, Jie Feng, Lei Liu et al.· IEEE transactions on compute...· 0 citations