Knapsack-Based Approach for Optimizing Resource Management in Edge Computing

Abstract In the era of rapid internet expansion, Edge Computing has emerged as a critical field in computer science, addressing challenges posed by increasing internet data, bandwidth limitations, and the distance between cloud servers and users. The impact of Edge Computing can be observed in various domains such as IoT networks, 5G cellular networks, healthcare systems, and more. A key focus is the optimal resource management problem within Edge Computing. This problem involves efficiently allocating computational resources from edge and cloud servers to respond to user requests, aiming to minimize reliance on distant cloud servers and bring calculations nearer to the edge for task offloading. This article proposes a knapsack-based approach to optimize resource management in hybrid edge and cloud networks. The Multiple Knapsack Problem (MKP) is employed to model the resource allocation issue, defining servers as knapsacks and tasks as items. The proposed algorithm is defined in two parts: an exact solution for scenarios with a moderate number of servers and tasks, and a greedy solution for situations where the scale is too large for precise calculations within a reasonable time. Application of the proposed algorithm is demonstrated using the ECHOES simulator, designed for testing optimization methods in environments that combine both cloud and edge components. This work focuses on a new approach for offloading tasks to computational resources at edge or cloud.