Hybrid K-Means and Firefly Algorithm-Based Load Balancer for Dynamic Task Scheduling in Fog Computing for Postoperative Healthcare Systems

In fog computing for postoperative healthcare systems, efficient task scheduling and load balancing are crucial for improving response time, energy efficiency, makespan, and the overall performance of the system. This manuscript introduces a novel hybrid load balancing framework that amalgamates KMeans clustering with the Firefly Algorithm (FA) to tackle the dynamic task scheduling complexities inherent in fog-based healthcare environments. The K-Means methodology is employed to categorize tasks according to their computational necessities and resource requirements, thereby establishing clusters that facilitate optimized resource distribution. The Firefly Algorithm, recognized for its proficiency in addressing optimization challenges, is harnessed to ascertain the optimal scheduling arrangement within each task cluster by adeptly modifying task allocation among fog nodes in response to light intensity, which is directly proportional to the overall performance of the system. Empirical findings indicate that the proposed mechanism markedly surpasses conventional algorithms regarding the optimization of response time, makespan, cost, and energy consumption, thereby presenting a viable solution for the management of postoperative care within healthcare systems employing fog computing infrastructure. The results substantiate that our proposed model enhances response time by 18%, makespan by 17%, energy consumption by 15%, cost by 17%, and level of load balance by 18%.