Jul 2026· Scientific Journal of Intelligent Systems Research· 0 citations· 11 references
TL;DR
Comparative tests with PPO, FIFO, FAIR and HAS baselines confirm that multi-agent reinforcement learning can well capture the intrinsic scheduling patterns of complex mobile environments, providing an adaptive and energy-efficient scheduling solution for practical IoT deployments.
Abstract
Battery life remains a major constraint on the continuous operation of mobile IoT devices represented by drones. Most existing computation offloading strategies rely on static heuristic rules, which fail to deliver stable performance in dynamically changing wireless mobile environments. Targeting this problem, this paper develops a multi-agent deep reinforcement learning approach for Spark job scheduling across local devices, edge servers and cloud resources. The scheduling task is modeled as a Markov decision process: six real-time system and network metrics, including CPU utilization, memory load, handover delay, signal strength, transmission latency and congestion level, form the state space, and the reward function is built directly on actual measured energy consumption data. Based on the multi-agent deep deterministic policy gradient (MADDPG) algorithm, the proposed method adopts a centralized training and decentralized execution paradigm to realize distributed collaborative decision-making. Validation on a public MEC dataset shows that the trained policy finally converges to a hybrid scheduling mode: 57% of tasks are processed locally, 39% are offloaded to edge nodes, and less than 4% are assigned to cloud resources for specific application scenarios. Comparative tests with PPO, FIFO, FAIR and HAS baselines confirm that multi-agent reinforcement learning can well capture the intrinsic scheduling patterns of complex mobile environments, providing an adaptive and energy-efficient scheduling solution for practical IoT deployments.
This paper addresses the joint task offloading and resource allocation problem in multi-user MEC systems and proposes a decentralized control framework based on Multi-Agent Reinforcement Learning (MARL), which achieves lower total system cost and faster convergence than the full-local, full-offload, and heuristic baselines.
Youssef Oukissou, Mohamed Amine Meddaoui, Ayoub Belaidi et al.· International journal of Com...· 0 citations
An AI-enabled dynamic task scheduling framework based on Deep Reinforcement Learning (DRL) with a Deep Q-Network (DQN) model to dynamically assign tasks to virtual machines and learn the best scheduling policies by continuously interacting with the cloud environment based on system parameters such as resource availability, task queue length, and virtual machine load is introduced.
Karnam Sreenu, G. Prasadu, K. Premnadh et al.· VFAST Transactions on Softwa...· 0 citations
The rapid proliferation of Internet of Things (IoT) devices has placed unprecedented pressure on the network edge, where applications such as augmented reality, real-time analytics, and autonomous navigation demand low latency and tight energy budgets that traditional cloud-centric architectures cannot meet. Multi-access Edge Computing (MEC) addresses this gap by relocating computation closer to end users, but the core question of where and how each task should be executed remains open: rulebased and single-objective offloading strategies fail to simultaneously balance service latency, energy efficiency, and user experience under dynamic, large-scale conditions. In this paper we propose TARLOT (Two-Agent Reinforcement Learning Offloading Tasks), a cooperative framework for threetier IoT–MEC–Cloud environments. TARLOT decouples the offloading decision from the resourceallocation problem and assigns each to a dedicated Q-learning agent, so that the two subproblems are specialised independently while still being optimised jointly. The framework is evaluated on PureEdgeSim under heterogeneous IoT workloads, device densities ranging from 200 to 2,400, and diverse application profiles, and is compared against five widely-used baselines (Random, Round-Robin, Trade-Off, Pure-Edge, and Pure-Cloud). At 2,400 devices, TARLOT delivers an average service time of 1.1 s (against 4.3 s for Pure-Cloud), a Quality of Experience of 0.77 (against 0.22 for Pure-Cloud), a task-failure rate below 2 % (against nearly 14 % for Pure-Cloud), and a per-device energy consumption of only 3.6 W (against 11.2 W for Pure-Cloud) — roughly a 68 % reduction. Balanced CPU utilisation across the local, edge, and cloud tiers further confirms that TARLOT prevents resource bottlenecks, establishing it as a practical solution for next-generation large-scale IoT deployments.
Oussama Lagnfdi, Marouane Myyara, A. Darif· International journal of Com...· 0 citations
Experimental results demonstrate that DL-EATS achieves the lowest energy consumption, shortest makespan, minimal SLA violation rate, and highest resource utilization, representing an 18.5% improvement in energy efficiency over the next best method and substantial gains across all performance metrics.
Abdulmumini Adamu, A. A. Abdulwasiu· Journal of Science Research...· 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.
A reinforcement learning-based computation offloading strategy using an improved Deep Deterministic Policy Gradient (IDDPG) algorithm that outperforms greedy offloading strategies and demonstrates improved efficiency in dynamic MEC environments.
S. Alam, Sami Ud Din, Imtiaz Ali Shah et al.· International Journal of Inn...· 0 citations