Black Widow Optimization Algorithm And Its Application In Time Series Prediction

Time series prediction and analysis is widely used in many fields such as engineering,finance,science and technology.In the era of big data,time series prediction and analysis has become an important research branch of artificial intelligence technology.The forecasting results of power generation and power load forecasting are usually affected by multiple variables such as temperature and humidity.The traditional single machine learning model cannot accurately approximate the predicted values.Based on this,this paper combines the black widow optimization algorithm and neural network model to predict the time series in the energy and power fields,and the prediction results are better than the single prediction model.The research content includes the following three parts:(1)Based on the basic black widow optimization algorithm,a time-varying black widow optimization algorithm is proposed;The algorithm is applied to optimize the radial basis function network,and the combined optimization model is applied to short-term photovoltaic power generation prediction.The numerical simulation results show that the proposed radial basis function network combined model has high prediction accuracy.(2)A combined optimization model based on improved black widow optimization algorithm and radial basis function network is proposed and applied to the classification of UCI data sets,nonlinear function approximation,nonlinear system identification,and short-term power load forecasting.The numerical simulation results show that the improved RBF network combination model has higher prediction accuracy.(3)Based on the short-term and short-term memory network model,a combined model based on adaptive black widow optimization algorithm and shortterm and short-term memory network is proposed and applied to short-term power load forecasting.The numerical simulation results show that the proposed combination optimization model of adaptive black widow optimization algorithm based on short-term and short-term memory network model has higher prediction accuracy in short-term power load forecasting.