نرگس سادات حسيني مونس

With the rapid growth of the Internet of Things an‎d the increasing volume of data generated by connected devices, the need for fast an‎d efficient data processing has become more critical than ever. Edge computing has emerged as a viable solution, reducing latency an‎d improving service quality by bringing computation closer to data sources. However, resource constraints an‎d load management challenges in edge environments require advanced optimization strategies. This study presents a multi-objective optimization approach for task offloading between edge an‎d cloud computing, aiming to minimize execution delay, optimize energy consumption, reduce processing costs, an‎d enhance resource utilization. The proposed method combines fuzzy logic with evolutionary algorithms to make optimal decisions in dynamic an‎d complex conditions. Simulation results demonstrate that, compared to existing methods, the proposed approach significantly improves performance. Resource utilization has increased by approximately 10 to 15 percent, while execution time has been reduced by about one millisecond in some scenarios, which has a noticeable impact on system efficiency at scale. Additionally, energy consumption has generally decreased, although there is a temporary rise in early stages. By introducing a comprehensive an‎d effective framework, this research takes a significant step toward enhancing the performance of edge an‎d cloud computing systems

محاسبات لبه , محاسبات ابري , بارسپاري محاسبات , الگوريتم‌هاي بهينه‌سازي چندهدفه , اينترنت اشيا

edge computing , cloud computing , computation offloading , multi objective optimization algorithm , IOT

narges sadat hosseini moones

mehrdad ashtiani