A novel electrical net-load forecasting model based on deep neural networks and wavelet transform integration

Abstract The increasing growth of renewable energy resources (RESs) in microgrids and the uncertainty associated with their generation have led to problems in the management of smart active distribution networks. One of the main challenges in the planning for the operation of renewable power systems is net electrical load forecasting, therefore, increasing the accuracy of net-load forecasting is a vital issue. In this study, a deep neural network model is used to forecast the net-load. The structure of the deep neural network used in the proposed forecasting model has been constituted by several autoencoders and a cascade neural network. The net-load forecasting has been done in the presence of uncertainties arising from wind and photovoltaic (PV) generation and electrical load consumption. To improve the net-load forecasting precision, the wavelet transform has been applied to the inputs of the proposed model. The net-load forecast in different scenarios is conducted on an open dataset from 37 central European countries, from the perspective of different types of forecasting strategies and changes in the neural network architecture. The simulation results significantly confirm the accuracy of the proposed forecasting model by different indices.

[1]  Victor Eniola,et al.  Hour-ahead Forecasting of Photovoltaic Power Output based on Hidden Markov Model and Genetic Algorithm , 2019, International Journal of Renewable Energy Research.

[2]  Zhou Quan,et al.  RBF Neural Network and ANFIS-Based Short-Term Load Forecasting Approach in Real-Time Price Environment , 2008, IEEE Transactions on Power Systems.

[3]  Yacine Rezgui,et al.  Predictive modelling for solar thermal energy systems: A comparison of support vector regression, random forest, extra trees and regression trees , 2018, Journal of Cleaner Production.

[4]  Sharif Atique,et al.  Forecasting of total daily solar energy generation using ARIMA: A case study , 2019, 2019 IEEE 9th Annual Computing and Communication Workshop and Conference (CCWC).

[5]  W.J. Lee,et al.  Short-term load forecasting using comprehensive combination based on multi- meteorological information , 2008, 2008 IEEE/IAS Industrial and Commercial Power Systems Technical Conference.

[6]  L. Mili,et al.  Electric Load Forecasting Based on Statistical Robust Methods , 2011, IEEE Transactions on Power Systems.

[7]  Da Liu,et al.  Random forest solar power forecast based on classification optimization , 2019, Energy.

[8]  Yacine Rezgui,et al.  Tree-based ensemble methods for predicting PV power generation and their comparison with support vector regression , 2018, Energy.

[9]  Luca Massidda,et al.  Use of Multilinear Adaptive Regression Splines and numerical weather prediction to forecast the power output of a PV plant in Borkum, Germany , 2017 .

[10]  Wen-Yeau Chang,et al.  A Literature Review of Wind Forecasting Methods , 2014 .

[11]  Hasbi Yasin,et al.  Cascade Forward Neural Network for Time Series Prediction , 2018 .

[12]  J.B. Theocharis,et al.  A fuzzy model for wind speed prediction and power generation in wind parks using spatial correlation , 2004, IEEE Transactions on Energy Conversion.

[13]  Yi Wang,et al.  Using Bayesian Deep Learning to Capture Uncertainty for Residential Net Load Forecasting , 2020, IEEE Transactions on Power Systems.

[14]  Dipti Srinivasan,et al.  Automatic hourly solar forecasting using machine learning models , 2019, Renewable and Sustainable Energy Reviews.

[15]  Farshid Keynia,et al.  Short-Term Load Forecast of Microgrids by a New Bilevel Prediction Strategy , 2010, IEEE Transactions on Smart Grid.

[16]  Hamid Shaker,et al.  On comparison of two strategies in net demand forecasting using Wavelet Neural Network , 2014, 2014 North American Power Symposium (NAPS).

[17]  Amanpreet Kaur,et al.  Net load forecasts for solar-integrated operational grid feeders , 2017 .

[18]  Mohammad Ebrahim Banihabib,et al.  Hybrid DARIMA-NARX model for forecasting long-term daily inflow to Dez reservoir using the North Atlantic Oscillation (NAO) and rainfall data , 2017 .

[19]  Gary Jordan,et al.  Finding Flexibility: Cycling the Conventional Fleet , 2013, IEEE Power and Energy Magazine.

[20]  Yu Lasheng,et al.  Deep Learning Approach Combining Sparse Autoencoder With SVM for Network Intrusion Detection , 2018, IEEE Access.

[21]  Hamid Shaker,et al.  Impacts of large-scale wind and solar power integration on California׳s net electrical load , 2016 .

[22]  A. Khosravi,et al.  Time-series prediction of wind speed using machine learning algorithms: A case study Osorio wind farm, Brazil , 2018 .

[23]  Ioannis P. Panapakidis,et al.  Day-ahead natural gas demand forecasting based on the combination of wavelet transform and ANFIS/genetic algorithm/neural network model , 2017 .

[24]  Amanpreet Kaur,et al.  Net load forecasting for high renewable energy penetration grids , 2016 .

[25]  Tao Hong,et al.  Short Term Electric Load Forecasting , 2012 .

[26]  Yi Pan,et al.  An Ultrashort-Term Net Load Forecasting Model Based on Phase Space Reconstruction and Deep Neural Network , 2019 .

[27]  Rohit Bhakar,et al.  Gumbel copula based aggregated net load forecasting for modern power systems , 2018, IET Generation, Transmission & Distribution.

[28]  Adel El-Shahat,et al.  Advanced Applications for Artificial Neural Networks , 2018 .

[29]  Ping Zheng,et al.  An Easy-to-Implement Hysteresis Model Identification Method Based on Support Vector Regression , 2017, IEEE Transactions on Magnetics.

[30]  Kaoru Hirota,et al.  Softmax regression based deep sparse autoencoder network for facial emotion recognition in human-robot interaction , 2018, Inf. Sci..

[31]  Ahmad Hatata,et al.  Application of NARX neural network model for discharge prediction through lateral orifices , 2018, Alexandria Engineering Journal.

[32]  Héctor Pomares,et al.  Comparing different machine learning and mathematical regression models to evaluate multiple sequence alignments , 2015, Neurocomputing.

[33]  Ning Zhang,et al.  Data-Driven Probabilistic Net Load Forecasting With High Penetration of Behind-the-Meter PV , 2018, IEEE Transactions on Power Systems.

[34]  J. Widén,et al.  Probabilistic forecasting of solar power, electricity consumption and net load: Investigating the effect of seasons, aggregation and penetration on prediction intervals , 2018, Solar Energy.