Recurrent Neural Network for Nonconvex Economic Emission Dispatch

Abstract

In this paper, an economic emission dispatch (EED) model is developed to reduce fuel cost and environmental pollution emissions. Considering the development of new energy sources in recent years, the EED problem involves thermal units with the valve point effect and WTs. Meanwhile, it complies with demand constraint and generator capacity constraints. A recurrent neural network (RNN) is proposed to search for local optimal solution of the introduced nonconvex EED problem. The optimality and convergence of the proposed dynamic model are given. The RNN algorithm is verified on a power generation system for the optimization of scheduling and minimization of total cost. Moreover, a particle swarm optimization (PSO) algorithm is compared with RNN under the same problematic frame. Numerical simulation results demonstrate that the optimal scheduling given by RNN is more precise and has lower total cost than PSO. In addition, the dynamic variation of power load demand is considered and the power distribution of eight generators during 12 time periods is depicted.

A hybrid dynamic economic environmental dispatch model for balancing operating costs and pollutant emissions in renewable energy: A novel improved mayfly algorithm

“…Along with the development of computer technology, machine learning methods have been well used. Such as particle swarm algorithm (Alshammari et al, 2020), artificial neural networks (Wang et al, 2021), genetic algorithm (Ganjefar and Tofighi, 2011), differential evolution algorithm (Basu, 2011), and mothballing algorithm (Hazra and Roy, 2020). In addition, Wang et al (2021)proposed a recurrent neural network algorithm to solve the HDEED problem, which reduced randomness by strictly following the corresponding constraints at each time.…”

“…Such as particle swarm algorithm (Alshammari et al, 2020), artificial neural networks (Wang et al, 2021), genetic algorithm (Ganjefar and Tofighi, 2011), differential evolution algorithm (Basu, 2011), and mothballing algorithm (Hazra and Roy, 2020). In addition, Wang et al (2021)proposed a recurrent neural network algorithm to solve the HDEED problem, which reduced randomness by strictly following the corresponding constraints at each time. Ma et al (2018) used an improved global artificial bee colony algorithm to speed up the convergence of the algorithm to solve the HDEED problem, but lacked measures to prevent the algorithm from falling into local optimum.…”

Bus-Privacy-Preserving Distributed Economic Dispatch Method for Power Systems Using Iteration Functions

“…It further speeds up the convergence of the iteration. So the new iteration procedure (24𝑏)-(26𝑏) is called the fast fixed-point iteration procedure for bus agents to solve the economic dispatch model ( 1)- (3).…”

“…Thus, the conventional economic dispatch methods are in a centralized manner. See for example the equal incremental cost ( 𝜆 ) method and piecewise linear programming method [1], genetic algorithm approach [2], neural network method [3], convex relaxation methods [4], [5], and so forth. The conventional economic dispatch methods need a control center to collect global information and execute centralized computation.…”

Hybrid krill herd optimizer for thermal power scheduling problem

“…A meta-heuristic algorithm, which is a combination of Newton method, gradient search rule and a local operator, has been applied to solve combined economic-emission dispatch problem [37]. A recurrent neural network has been proposed to minimize fuel cost and emission of pollutants with the effect of valve point loading effects and wind turbines [38]. A polar bear optimization and variants of the chaotic population have been proposed to solve combined economy and emission dispatch problem [39].…”