Comparative Analysis of CPO-LSTM and PSO-LSTM for Wind Energy Power Forecasting

In this paper, long short-term memory (LSTM) neural network is integrated with the Crested Porcupine Optimizer (CPO) and Particle Swarm Optimization (PSO) respectively. Two optimization algorithms are used to optimize the initial parameters, and then construct hybrid wind energy power forecasting systems. Due to the excellent ability of CPO algorithm in finding the global optimal solution, the root mean square error of CPO-LSTM neural network is reduced from 0.1 to $\mathbf{0. 0 2 4}$. Compared with the PSO-LSTM, the accuracy is improved.