Load Balancing based on Node Potential Energy for Distributed Environments with limited Migration Capacity
Haipeng Zhang, Ningning Lu, Jie Li · 2019
A load balancing based on potential energy for distributed network with limited migration capacity is proposed in this paper. We first introduce a flexible abstraction of distributed network with limited migration capacity. The abstraction is generally enough to capture the essences of that the load migration is limited. The potential energy of one node is defined as the square of the load. Based on the model and the definition of node's potential energy, we prove that the system is in a load balancing state when the system's potential energy reaches the minimum. Then a load balancing algorithm based on greedy strategy is proposed to solve the problem. Finally, some experiments are designed to verify the model and the load balancing algorithm.