Improved butterfly optimization algorithm applied to prediction of combined cycle power plant

Abstract

The electricity output is worth monitoring because of the rising electricity demand. Ambient temperature, air pressure, relative humidity, and exhaust pressure all impact the production output of a combined cycle power plant. This study proposes the BOAPPE algorithm, which combines the butterfly optimization algorithm (BOA) with the phasmatodea population evolution algorithm (PPE) to estimate power output better and reduce excessive cost waste. When used in conjunction with a support vector regression (SVR) model, such as BOAPPE-SVR, for estimating the power output of a power plant under basic load, it not only enhances the model’s prediction accuracy but also successfully avoids the problem of the model entering local optimization too soon. The parallel strategy of the BOAPPE algorithm in this research improves convergence speed, while the random walk strategy prevents the model from sliding into local optimization. The results reveal that the model paired with the BOAPPE algorithm is more accurate and better than the other models in this research when comparing the performance of the parameters such as mean square error, relative error, and correlation coefficient. As a result, the BOAPPE-SVR model is a viable model for power load forecasting.