Time Series Forecasting Based on Combinatorial Models and Optimization

As a key tool for understanding data changes over time, time series analysis plays a key role in a variety of disciplines and applications, and its in-depth study is of great significance. In this paper, singular spectrum analysis (SSA) is used to decompose and reconstruct the time series. Based on these decomposition data, three deep learning methods, namely, recurrent neural network (RNN), long-short-term memory neural network (LSTM), and BP neural network (BPNN), are further applied for time series prediction. The performance of these neural networks is optimized through the use of the Gray Wolf Optimization (GWO) algorithm to adjust their weights, and sensitivity analysis is performed to assess the robustness of the models. The innovation of this method lies in its combination of a variety of advanced signal processing techniques, deep learning algorithms, and optimization strategies, thus achieving significant results in wind speed prediction.