The formulation of bidding strategies in a competitive energy market can be a profit-making way for power producers. With the evolution of smart grids and focus on the consumer-centric policies, companies are coming with competitive strategies so that they can provide better services to consumers and make profit from market conditions. In this chapter, an anticipator of market sentiment is proposed through the evaluation of a forecasting algorithm derived from radial basis function neural network (RBFNN) and chaotic variant of grasshopper algorithm. In the introductory part of the chapter, a critical review of literature is presented, which dealt with different market-clearing mechanisms, different strategies pertaining to make profit, and different market structures along with their evolution. After a crisp review of these, an optimization routine and supervised architecture (RBFNN-SFECGOA)-based framework for predicting the market sentiments is proposed. The anticipator receives inputs from rival bidders and models them with the help of mathematical formulation. Recently published chaotic variant of grasshopper optimization algorithm, namely, sinusoidal function–enabled chaotic grasshopper optimization algorithm (SFECGOA) is employed to serve optimization task. The results obtained from this anticipator and other approaches are evaluated and validated through the calculation of various error indices, and decisive evaluation of the profit-making strategies is carried out. Different scenarios of uncertainty are simulated to validate the proposed approach. The results reveal that proposed market anticipator can keep a close watch on market sentiments and provide profitable results for a power producer.
|Title of host publication||Uncertainties in Modern Power Systems|
|Number of pages||18|
|Publication status||Published - 1 Jan 2020|