Title: An adaptive method for the performance evaluation of a concentrating solar power system using NN and CS
Authors: Venbakkam Sendamaraikannan Srinivasan; S.Srinivasa Rao Madane
Addresses: Electrical and Electronics Engineering, Thirumalai Engineering College, Kancheepuram, India ' Department of Electronics and Communication Engineering, Adhiparasakthi College of Engineering, Kalavai, Vellore, India
Abstract: In this paper, the proposed adaptive technique is used for improving the performance of the concentrating solar power (CSP) system. Initially, the neural network (NN) generated the dataset based on the reference signal and the normal signal. Then the cuckoo search (CS) algorithm improved the effectiveness of the proposed algorithm and the weight and the biases can optimised. The novelty of this paper is to evaluate the performance of the CSP system and improve the effectiveness also of gathered maximum energy. Thereafter, to support the accuracy and efficiency of the system, parameters such as regression coefficient, root mean square error (RMSE) value and error variation are estimated. The proposed optimisation process is implemented in MATLAB/Simulink platform and also the result is estimated and analysed based on the error parameters of the CSP system. Based on these, the proposed optimisation process is evaluated and compared with other traditional methods.
Keywords: solar power system; neural network; cuckoo search; concentrated solar power; CSP; parabolic trough collectors; PTC; solar tower collectors; STC.
International Journal of Business Intelligence and Data Mining, 2017 Vol.12 No.2, pp.159 - 174
Available online: 15 May 2017 *Full-text access for editors Access for subscribers Purchase this article Comment on this article