Distributed Economic Dispatch Algorithm With Quantized Communication Mechanism

Abstract

Due to the limited bandwidth and energy of communication channels among agents in practical applications, the communication-efficient distributed optimization method has emerged as a pressing research topic in recent years. The distributed economic dispatch problem with restricted data communication/finite communication bandwidth is investigated in this study, where the communication among agents can be described as a strongly connected directed network. For this purpose, a robust push-pull distributed optimization algorithm with a dynamic scaling quantization mechanism is developed based on the gradient tracking technique. A novel surplus variable is designed to prevent the accumulation of quantization errors, and then, a heavy-ball momentum is introduced to speed up convergence performance. In addition, a linear convergence rate of the developed approach is deduced for the strongly convex and Lipschitz smooth cost function. Finally, we offer two instances for illustration. Note to Practitioners—This paper proposes a robust quantization-based algorithm for the economic dispatch problem, in which the broadcasting information is quantized before sending to its neighboring generators. Therefore, this method reduces duplicate transmission of agents and improves the use of communication resources. Furthermore, the developed method can be extended to similar constrained optimization problems, such as the resource allocation problem in wireless networks, and the network utility maximization problem in the Internet.