Reinforcement Learning approaches to Economic Dispatch problem

Abstract

a b s t r a c tThis paper presents Reinforcement Learning (RL) approaches to Economic Dispatch problem. In this paper, formulation of Economic Dispatch as a multi stage decision making problem is carried out, then two variants of RL algorithms are presented. A third algorithm which takes into consideration the transmission losses is also explained. Efficiency and flexibility of the proposed algorithms are demonstrated through different representative systems: a three generator system with given generation cost table, IEEE 30 bus system with quadratic cost functions, 10 generator system having piecewise quadratic cost functions and a 20 generator system considering transmission losses. A comparison of the computation times of different algorithms is also carried out.

Optimal integration of distributed generation (DG) resources in unbalanced distribution system considering uncertainty modelling

“…RL can handle the stochastic data and can be applied for multistage decision‐making situations without the need to formulate a precise mathematical model to start with. RL has been applied to many decision‐making situations in power system such as unit commitment, economic dispatch and automatic generation control . The application of RL for optimal integration of DG sources is partly explored in this paper.…”

Teaching learning based optimization for economic load dispatch problem considering valve point loading effect

“…To solve both complex and noncomplex economic load dispatch (ELD) problems of thermal plant, a memetic algorithm, namely, aBBOmDE, is proposed in [17]. To solve the economic load dispatch problem reinforcement learning approaches is proposed in [18]. An artificial immune system based on the clonal selection principle is proposed by Basu [19] for solving dynamic economic dispatch problem.…”

Distributed multi-step Q(λ) learning for Optimal Power Flow of large-scale power grids

“…In recent years, Reinforcement Learning techniques have been proposed for reactive power control [12], economic dispatch [13], power market [14], etc. With the rapid development of multi-agent system (MAS) technology [15,16], Distributed Reinforcement Learning (DRL) [17], as an extension of Reinforcement Learning, plays an important role as the core enabling technology to achieve the MAS's goal.…”