Power Load Forecasting: A Time-Series Multi-Step Ahead and Multi-Model Analysis

Distribution System Operators and Aggregators can derive benefits from innovative approaches in Power or Energy Load Forecasting (PLF-ELF). Enhanced accuracy in PLF-ELF can support the management of energy imbalances between production and consumption or operations like Demand Response. This research aims to assess a wide range of models as potential solutions for multi-step PLF-ELF, utilizing time-series machine learning models for power consumption. The experimentation encompassed multi-step PLF-ELF across various resolutions, ranging from 15-minute intervals up to one day. Results indicate that while Long Short-Term Memory recurrent Neural Networks and Lasso Regression with Cross-Validation perform better for very short-term PLF-ELF, tree-based regressors like Gradient Boosting, Histogram Gradient Boosting, Light Gradient Boosting Machine and CatBoost outperformed other models in the upcoming steps. The optimal PLF-ELF technique proposes different algorithms per forecasting horizon.

[1]  D. Ioannidis,et al.  Energy generation forecasting: elevating performance with machine and deep learning , 2023, Computing.

[2]  D. Ioannidis,et al.  One Step Ahead Energy Load Forecasting: A Multi-model approach utilizing Machine and Deep Learning , 2022, 2022 57th International Universities Power Engineering Conference (UPEC).

[3]  D. Ioannidis,et al.  Introducing a novel approach in one-step ahead energy load forecasting , 2021, Sustain. Comput. Informatics Syst..

[4]  Seungmin Rho,et al.  A Comparative Analysis of Tree-Based Models for Day-Ahead Solar Irradiance Forecasting , 2021, 2021 International Conference on Platform Technology and Service (PlatCon).

[5]  Dimitrios Tzovaras,et al.  A Tri-Layer Optimization Framework for Day-Ahead Energy Scheduling Based on Cost and Discomfort Minimization , 2021, Energies.

[6]  Dimitrios Tzovaras,et al.  An interdisciplinary approach on efficient virtual microgrid to virtual microgrid energy balancing incorporating data preprocessing techniques , 2021, Computing.

[7]  R. Souza,et al.  Forecasting residential electricity consumption: a bottom-up approach for Brazil by region , 2020, Energy Efficiency.

[8]  Alagan Anpalagan,et al.  Joint bagged-boosted artificial neural networks: Using ensemble machine learning to improve short-term electricity load forecasting , 2020 .

[9]  Dejan Dragan,et al.  Methods and Models for Electric Load Forecasting: A Comprehensive Review , 2020, Logistics & Sustainable Transport.

[10]  Sung Wook Baik,et al.  A Two-Stage Industrial Load Forecasting Scheme for Day-Ahead Combined Cooling, Heating and Power Scheduling , 2020, Energies.

[11]  Jing Liu,et al.  Multi-step ahead forecasting of heat load in district heating systems using machine learning algorithms , 2019 .

[12]  Shalini Batra,et al.  DROpS: A demand response optimization scheme in SDN-enabled smart energy ecosystem , 2019, Inf. Sci..

[13]  S. C. Srivastava,et al.  Short Term Load Forecasting using SVM Models , 2018, 2018 IEEE 8th Power India International Conference (PIICON).

[14]  Huan Luo,et al.  Short-Term Power Load Forecasting Based on Clustering and XGBoost Method , 2018, 2018 IEEE 9th International Conference on Software Engineering and Service Science (ICSESS).

[15]  Vitaly Kuznetsov,et al.  Foundations of Sequence-to-Sequence Modeling for Time Series , 2018, AISTATS.

[16]  I. Provornaya,et al.  Analysis of energy intensity trend as a tool for long-term forecasting of energy consumption , 2018 .

[17]  Mauro Conti,et al.  Computational intelligence approaches for energy load forecasting in smart energy management grids: state of the art, future challenges, and research directionsand Research Directions , 2018 .

[18]  Ping-Huan Kuo,et al.  A High Precision Artificial Neural Networks Model for Short-Term Energy Load Forecasting , 2018 .

[19]  Tie-Yan Liu,et al.  LightGBM: A Highly Efficient Gradient Boosting Decision Tree , 2017, NIPS.

[20]  Yong Deng,et al.  A novel method for forecasting time series based on fuzzy logic and visibility graph , 2017, Advances in Data Analysis and Classification.

[21]  Konrad P. Körding,et al.  Toward an Integration of Deep Learning and Neuroscience , 2016, bioRxiv.

[22]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[23]  Abbas Khosravi,et al.  A review on artificial intelligence based load demand forecasting techniques for smart grid and buildings , 2015 .

[24]  Paul Raftery,et al.  A review of methods to match building energy simulation models to measured data , 2014 .

[25]  Michael B. Miller.  Linear Regression Analysis , 2013 .

[26]  Frédéric Magoulès,et al.  A review on the prediction of building energy consumption , 2012 .

[27]  Seohoon Jin,et al.  Decision tree approaches for zero-inflated count data , 2006 .

[28]  Pierre Geurts,et al.  Extremely randomized trees , 2006, Machine Learning.

[29]  H. Zou,et al.  Addendum: Regularization and variable selection via the elastic net , 2005 .

[30]  Hesham K. Alfares,et al.  Electric load forecasting: Literature survey and classification of methods , 2002, Int. J. Syst. Sci..

[31]  Ming-Syan Chen,et al.  Sliding-window filtering: an efficient algorithm for incremental mining , 2001, CIKM '01.

[32]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[33]  Arthur E. Hoerl,et al.  Ridge Regression: Biased Estimation for Nonorthogonal Problems , 2000, Technometrics.

[34]  S. Hochreiter,et al.  Long Short-Term Memory , 1997, Neural Computation.

[35]  F. Windmeijer,et al.  An R-squared measure of goodness of fit for some common nonlinear regression models , 1997 .

[36]  David J. C. MacKay,et al.  Bayesian Interpolation , 1992, Neural Computation.

[37]  S. Subbiah,et al.  Deep learning based short term load forecasting with hybrid feature selection , 2022, Electric Power Systems Research.

[38]  Ma Li,et al.  Research on Short-Term Load Forecasting Using XGBoost Based on Similar Days , 2019, 2019 International Conference on Intelligent Transportation, Big Data & Smart City (ICITBS).

[39]  V. Kreinovich,et al.  Why 70/30 or 80/20 Relation Between Training and Testing Sets: A Pedagogical Explanation , 2018 .

[40]  Nora El-Gohary,et al.  A review of data-driven building energy consumption prediction studies , 2018 .

[41]  L. Breiman.  Random Forests , 2001, Machine Learning.

[42]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[43]  Frederick R. Forst,et al.  On robust estimation of the location parameter , 1980 .

[44]  R. Tibshirani,et al.  Least angle regression , 2004, math/0406456.