Day-ahead load forecasting is an important task for the power dispatching center to formulate reasonable dispatching plans thus to ensure the safety and reliability of power system operation.However, random errors exist in time series of power loads, and the intelligent algorithm based prediction models are complex in structure and incapable of fully extracting load information enough for load calculation and load forecasting.Here, we propose a day-ahead power load forecasting approach based on Repeated Wavelet Transform-Support Vector Machine (RWT-SVM) by using the historical power load time series of distributed power grids.The approach uses wavelet transform to decompose the power load time series of distributed power grids into multiple subsequences, then applies the Mean Absolute Error (MAE) to calculate the prediction errors contributed by each subsequence, and further decomposes the sequence with the largest MAE to improve the prediction ability of the model.The simulation results show that the proposed RWT-SVM approach outperforms other methods in forecasting accuracy.