Short-term electric load and temperature forecasting using wavelet echo state networks with neural reconstruction

• The proposed WESN-based forecaster contains a novel ESN-based reconstruction stage.
• Proposed forecasters are applied for 1-h & 24-h ahead load & temperature forecasting.
• A modified SFL algorithm is used to find the best design of ESNs in proposed forecasters.
• Proposed forecasters significantly improve accuracy and outperform other compared models.

In this paper, WESN (wavelet echo state network) with a novel ESN-based reconstruction stage is applied to both STLF (short-term load forecasting) and STTF (short-term temperature forecasting). Wavelet transform is used as the front stage for multi-resolution decomposition of load or temperature time series. ESNs function as forecasters for decomposed components. A modified shuffled frog leaping algorithm is used for optimizing ESNs. Both one-hour and 24-h ahead predictions are studied where the number of inputs are kept minimum. The performance of the proposed WESN-based load forecasters are investigated for three cases as the predicted temperature input is fed by actual temperatures, output of the WESN-based temperature forecasters and noisy temperatures. Effects of temperature errors on load forecasts are studied locally by sensitivity analysis. Hourly loads and temperatures of a North-American electric utility are used for this study. First, results of the proposed forecasters are compared with those of ESN-based forecasters that have previously shown high capability as stand-alone forecasters. Next, the WESN-based forecasters are compared with other models either previously tested on the data used here or to be rebuilt for testing on these data. Comparisons reveal significant improvements on accuracy of both STLF and STTF using the proposed forecasters.