Priority-Aware Resource Reallocation in Edge Computing Using Reinforcement Learning

The rapid adoption of IoT applications has led to the continuous generation of vast amounts of data, demanding efficient processing, storage, and real-time response delivery. Edge computing has emerged as a critical technology that addresses the growing need for low-latency and high-bandwidth applications in the Internet of Things (IoT) ecosystem. By processing data closer to its source, edge computing reduces dependence on centralized data centers, significantly improving response times.However, this shift introduces significant challenges in resource management, particularly in allocating limited and heterogeneous computational, storage, and network resources across distributed edge nodes. Existing solutions often fail to adapt to real-time priority shifts or enforce strict Quality of Service (QoS) guarantees for critical tasks (e.g., healthcare, real-time gaming). To address these challenges, this paper proposes two novel reinforcement learning (RL)-based resource reallocation algorithms that dynamically optimize edge resource allocation by: 1- Priority-aware task classification: Categorizing tasks into five demand-based levels (e.g., bandwidth-intensive, time-sensitive) and three priority classes (critical, important, general), enabling context-aware decision-making. 2- Dynamic preemption: Reallocating resources from low-priority tasks to high-priority ones while minimizing disruptions to ongoing processes. 3- MDP-based optimization: Formulating the NP-hard resource allocation problem as a Markov Decision Process (MDP) and solving it via Q-learning, prioritizing time-sensitive tasks.Simulations demonstrate that our approach reduces task rejection rates by up to 30% in critical tasks and 2% in important tasks compared to baseline methods, while ensuring 80% acceptance of critical tasks. Results demonstrate effective efficiency-QoS tradeoffs in a dynamic edge environment.