Multi-View Neural Network Ensemble for Short and Mid-Term Load Forecasting

Abstract

Accurate load forecasting is essential to the operation and planning of power systems and electricity markets. In this paper, an ensemble of radial basis function neural networks (RBFNNs) is proposed which is trained by minimizing the localized generalization error for shortterm and mid-term load forecasting. Exogenous features and features extracted from load series (with long shortterm memory networks and multi-resolution wavelet transform) in various timescales are used to train the ensemble of RBFNNs. Multiple RBFNNs are fused as an ensemble model with high generalization capability using a proposed weighted fusion method based on the localized generalization error model. Experimental results on three practical datasets show that compared with other forecasting methods, the proposed method reduces the mean absolute percentage error (MAPE), mean squared error (MSE), mean absolute error (MAE) by at least 0.12%, 8.46 (MW) 2 , 0.83 MW in mid-term load forecasting (i.e., to predict the daily peak load of next month), respectively, and reduces the MAPE, MSE by at least 0.19%, 2009.69 (MW) 2 and 0.30%, 3697.18 (MW) 2 in half-hour-ahead forecasting and day-ahead forecasting, respectively.

An unsupervised data-driven approach for behind-the-meter photovoltaic power generation disaggregation

“…The most difficult part of net load disaggregation is how to disaggregate PVPG sequences from net load without historical separated sub-meter data as reference. In this section, considering the relationships between the PVPG and solar irradiation, the PVPG sensitivity model is built by employing k-nearest neighbor (KNN) [23] and LSTM [24]. Furthermore, the EC model is established fully taking the strong correlation between ambient temperature and day type by using KNN and LSTM, too.…”

MultiCycleNet: Multiple Cycles Self-Boosted Neural Network for Short-term Electric Household Load Forecasting

“…Lai et al [34] proposed a multi-view ensemble framework for short and mid-term load forecasting. Features of multi-view were first extracted from both LSTM and three-level wavelet decomposition.…”

ES-dRNN: A Hybrid Exponential Smoothing and Dilated Recurrent Neural Network Model for Short-Term Load Forecasting

“…For example, statistical methods can help in data preprocessing and reduce overfitting of ML models. Examples of model hybridization for STLF can be found in [28] where a temporal CNN is utilized to extract hidden information and long-term temporal relationships in the input data and a boosted tree model (LightGBM) is used to predict future loads based on the extracted features, and in [29] where both LSTM and wavelet decomposition extract TS features, on which an ensemble of RBF NNs is trained. The produced forecasts are aggregated by a localized generalization error model, which optimizes the ensemble member weights.…”