Premium
Modeling of bidding strategies in a competitive electricity market: A hybrid approach
Author(s) -
Senthilvadivu A,
Gayathri K,
Asokan K
Publication year - 2019
Publication title -
international journal of numerical modelling: electronic networks, devices and fields
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.249
H-Index - 30
eISSN - 1099-1204
pISSN - 0894-3370
DOI - 10.1002/jnm.2594
Subject(s) - bidding , electricity market , computer science , market clearing , profit (economics) , support vector machine , mathematical optimization , electricity , operations research , artificial intelligence , economics , engineering , microeconomics , electrical engineering , mathematics
In the paper, an innovative hybrid algorithm is proposed to solve bidding strategy problem in electricity market. The proposed hybrid technique is the combination of the recurrent neural network (RNN), support vector machine (SVM), and the lightning search algorithm (LSA). The main contribution of this paper is to maximize the profits of suppliers and minimize the customer payments; it is very important to create reasonable matching rule for the electricity market. LSA optimizes bidding coefficients of both the suppliers and consumers with the consideration of available power generation limit, power demand, market‐clearing price (MCP), and constraints. RNN is utilized for demand prediction at every hour, and SVM ensures the MCP based on the demand. The proposed bidding strategy ensures the maximum profit of the suppliers and consumers because of the aggregated demand model. The proposed method is tested on The Institute of Electrical and Electronics Engineers (IEEE) 30‐bus system and 75‐bus Indian practical system and compared with the existing techniques. The comparison results demonstrate the superiority of the proposed technique and confirm its potential to solve the problem. Also, the proposed model and the strategies are implemented in the MATLAB, and the performance will be studied under various demand environments.