An Energy-Aware Resource Allocation Framework based on Reptile Search Algorithm and Gray Wolf Optimizer for Mobile Edge Computing

Mobile edge computing (MEC) is a new networking pattern that deploys resources layer by layer to yield high-quality services. The MEC reduces the response time, energy consumption, process time, and bandwidth usage while enhancing privacy, security, and communications in real-life applications. Determining the most optimal resources from the edge, fog, and cloud layers for the requested services by the users under different quality-of-service constraints is one of the most critical challenges in MEC networks, known as the service placement problem (SPP). An optimal service placement algorithm can increase the benefits of service providers and users' satisfaction. Consequently, a novel metaheuristic-based resource allocation algorithm named ERSGWO in presented in the current paper. In the ERSGWO, the reptile search algorithm (RSA) and gray wolf optimizer (GWO) are hybridized through an innovative complementary strategy. The RSA is enhanced in the ERSGWO by increasing the number of leaders. The outcome hybrid algorithm is then discretized using an intermediate phase. Likewise, a neighborhood search procedure with two new movement strategies is introduced in the ERSGWO to augment exploration and exploitation capabilities. Besides, the local departure ability is enriched through a mechanism that detects and reinitializes the trapped search agents in local optimums. Eventually, 12 MEC environments with different specifications are designed, and the ERSGWO is applied to them. The results are compared with the ARO, AOA, FOX, GWO, MRFO, RSA, SCA, STOA, TSA, APO, and EHO algorithms numerically and visually. The experimental results reveal that the ERSGWO outperformed its competitors in 97.73% of test cases.