Daily peak electrical load forecasting with a multi-resolution approach

In the context of smart grids and load balancing, daily peak load forecasting has become a critical activity for stakeholders of the energy industry. An understanding of peak magnitude and timing is paramount for the implementation of smart grid strategies such as peak shaving. The modelling approach proposed in this paper leverages high-resolution and low-resolution information to forecast daily peak demand size and timing. The resulting multi-resolution modelling framework can be adapted to different model classes. The key contributions of this paper are a) a general and formal introduction to the multi-resolution modelling approach, b) a discussion on modelling approaches at different resolutions implemented via Generalised Additive Models and Neural Networks and c) experimental results on real data from the UK electricity market. The results confirm that the predictive performance of the proposed modelling approach is competitive with that of lowand high-resolution alternatives.

[1]  M. F. Abdullah,et al.  A review on peak load shaving strategies , 2018 .

[2]  Rob J Hyndman,et al.  Density Forecasting for Long-Term Peak Electricity Demand , 2010, IEEE Transactions on Power Systems.

[3]  S. Wood.  Thin plate regression splines , 2003 .

[4]  Yacine Rezgui,et al.  Electrical load forecasting models: A critical systematic review , 2017 .

[5]  Weijun Hong,et al.  Deep ensemble learning based probabilistic load forecasting in smart grids , 2019 .

[6]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..

[7]  Kurt Hornik,et al.  Approximation capabilities of multilayer feedforward networks , 1991, Neural Networks.

[8]  Rob J Hyndman,et al.  Automatic Time Series Forecasting: The forecast Package for R , 2008 .

[9]  Shufang Li,et al.  Bayesian Deep Learning-Based Probabilistic Load Forecasting in Smart Grids , 2020, IEEE Transactions on Industrial Informatics.

[10]  Gianluca Pollastri,et al.  A neural network approach to ordinal regression , 2007, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).

[11]  Mohammad Reza Amin-Naseri,et al.  Combined use of unsupervised and supervised learning for daily peak load forecasting , 2008 .

[12]  Yannig Goude,et al.  Modeling and Forecasting Daily Electricity Load Curves: A Hybrid Approach , 2013, 1611.08632.

[13]  C. Sigauke,et al.  Prediction of daily peak electricity demand in South Africa using volatility forecasting models , 2011 .

[14]  A. Antoniadis,et al.  A functional wavelet–kernel approach for time series prediction , 2006 .

[15]  Lalit Mohan Saini,et al.  Peak load forecasting using Bayesian regularization, Resilient and adaptive backpropagation learning based artificial neural networks , 2008 .

[16]  Q. H. Wu,et al.  Forecasting electric daily peak load based on local prediction , 2009, 2009 IEEE Power & Energy Society General Meeting.

[17]  F. Diebold,et al.  Comparing Predictive Accuracy , 1994, Business Cycles.

[18]  Yi Yang,et al.  Analysis of Deep Learning Control Strategy about Peak Load Regulation and Frequency Regulation with Distribution Thermal Storage Electric Boiler , 2018, 2018 5th IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS).

[19]  Caston Sigauke,et al.  Daily peak electricity load forecasting in South Africa using a multivariate non-parametric regression approach , 2010 .

[20]  S. Wood,et al.  Smoothing Parameter and Model Selection for General Smooth Models , 2015, 1511.03864.

[21]  Rana Fayyaz Ahmad,et al.  Feature extraction and classification for EEG signals using wavelet transform and machine learning techniques , 2015, Australasian Physical & Engineering Sciences in Medicine.

[22]  A. Faruqui,et al.  Quantile Regression for Peak Demand Forecasting , 2014 .

[23]  F. Harrell,et al.  Partial Proportional Odds Models for Ordinal Response Variables , 1990 .

[24]  Katie McConky,et al.  A hybrid machine learning model for forecasting a billing period’s peak electric load days , 2019, International Journal of Forecasting.

[25]  Anestis Antoniadis,et al.  Forecasting high resolution electricity demand data with additive models including smooth and jagged components , 2021 .

[26]  S. Wood,et al.  qgam: Bayesian Nonparametric Quantile Regression Modeling in R , 2020, J. Stat. Softw..

[27]  R. Tibshirani,et al.  Generalized Additive Models , 1986 .

[28]  Benjamin McDaniel,et al.  Peak Forecasting for Battery-based Energy Optimizations in Campus Microgrids , 2020, e-Energy.

[29]  Shanlin Yang,et al.  A deep learning model for short-term power load and probability density forecasting , 2018, Energy.

[30]  Dong Hoon Kim,et al.  Peak-Load Forecasting for Small Industries: A Machine Learning Approach , 2020, Sustainability.

[31]  R. E. Abdel-Aal,et al.  Modeling and forecasting electric daily peak loads using abductive networks , 2006 .

[32]  M. Fukushige,et al.  Quantile Regression Model for Peak Load Demand Forecasting with Approximation by Triangular Distribution to Avoid Blackouts , 2018 .

[33]  Tao Hong,et al.  Probabilistic electric load forecasting: A tutorial review , 2016 .

[34]  Danica Vukadinovic Greetham,et al.  Forecasting and Assessing Risk of Individual Electricity Peaks , 2020 .

[35]  P. McSharry,et al.  Probabilistic forecasts of the magnitude and timing of peak electricity demand , 2005, IEEE Transactions on Power Systems.

[36]  Pierre Pinson,et al.  Evaluation of wind power forecasts—An up‐to‐date view , 2019, Wind Energy.

[37]  Caston Sigauke,et al.  Analysis of Extreme Peak Loads Using Point Processes: An Application Using South African Data , 2020, IEEE Access.

[38]  Moni Naor,et al.  Advances in Neural Networks - ISNN 2017 , 2017, Lecture Notes in Computer Science.

[39]  Saifur Rahman,et al.  Peak load forecasting using a fuzzy neural network , 1995 .

[40]  Wenhu Tang,et al.  Deep Learning for Daily Peak Load Forecasting–A Novel Gated Recurrent Neural Network Combining Dynamic Time Warping , 2019, IEEE Access.

[41]  M. J. Hossain,et al.  LSTM Neural Network Model for Ultra-short-term Distribution Zone Substation Peak Demand Prediction , 2020, 2020 IEEE Power & Energy Society General Meeting (PESGM).

[42]  Yannig Goude,et al.  Fast Calibrated Additive Quantile Regression , 2017, Journal of the American Statistical Association.