A short-term PV power forecasting method based on cosine similarity and TSO-BP neural network

Abstract

Accurate photovoltaic （PV） output power forecasting plays a crucial role in ensuring the secure and stable operation of distribution networks. In light of this， the paper proposes a short-term PV power forecasting method using cosine similarity and a hybrid TSO （tuna swarm optimization） and BP （back propagation） neural network. Firstly， the cosine similarity algorithm is utilized to identify historical data with strong resemblance to the forecast day as training samples. Subsequently， the TSO algorithm is employed to search for optimal initial weights and thresholds for the BP neural network. The TSO-BP model is then trained for short-term PV power forecasting. Finally， the TSO-BP model is applied to predict PV output power under both stable and fluctuating weather conditions. Simulation results indicate that， the proposed method， compared to traditional forecasting methods， achieves higher accuracy in predictions for both steady and fluctuating weather scenarios.

Keywords

• pv power forecasting
• pearson correlation coefficient
• cosine similarity
• tso
• bp neural network