Segmenting Residential Smart Meter Data for Short-Term Load Forecasting

In order to reliably generate electricity to meet the demands of the customer base, it is essential to match supply with demand. Short-term load forecasting is utilised in both real-time scheduling of electricity, and load-frequency control. This paper aims to improve the accuracy of load-forecasting by using machine learning techniques to predict 30 minutes ahead using smart meter data. We utilised the k-means clustering algorithm to cluster similar individual consumers and fit distinct models per cluster. Public holidays were taken into consideration for changing customer behaviour, as was periodicity of the day, week and year. We evaluated a number of approaches for predicting future energy demands including; Random Forests, Neural Networks, Long Short-Term Memory Neural Networks and Support Vector Regression models. We found that Random Forests performed best at each clustering level, and that clustering similar consumers and aggregating their predictions outperformed a single model in each case. These findings suggest that clustering smart meter data prior to forecasting is an important step in improving accuracy when using machine learning techniques.

[1]  Ming-Wei Chang,et al.  Load Forecasting Using Support Vector Machines: A Study on EUNITE Competition 2001 , 2004, IEEE Transactions on Power Systems.

[2]  Hossein Shayeghi,et al.  A Neural Network Based Short Term Load Forecasting , 2007, IC-AI.

[3]  Francisco C. Pereira,et al.  Using pattern recognition to identify habitual behavior in residential electricity consumption , 2012 .

[4]  Chih-Jen Lin,et al.  Training and Testing Low-degree Polynomial Data Mappings via Linear SVM , 2010, J. Mach. Learn. Res..

[5]  H. Akaike.  A new look at the statistical model identification , 1974 .

[6]  E. Forgy.  Cluster analysis of multivariate data : efficiency versus interpretability of classifications , 1965 .

[7]  S. Talukdar,et al.  Trends in the history of large blackouts in the United States , 2008, 2008 IEEE Power and Energy Society General Meeting - Conversion and Delivery of Electrical Energy in the 21st Century.

[8]  James W. Taylor.  An evaluation of methods for very short-term load forecasting using minute-by-minute British data , 2008 .

[9]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[10]  Marcus O'Connor,et al.  Artificial neural network models for forecasting and decision making , 1994 .

[11]  Sergios Theodoridis,et al.  Pattern Recognition, Third Edition , 2006 .

[12]  Yan Li,et al.  Short-term electricity demand forecasting with MARS, SVR and ARIMA models using aggregated demand data in Queensland, Australia , 2018, Adv. Eng. Informatics.

[13]  K. Aberer,et al.  Individual, Aggregate, and Cluster-based Aggregate Forecasting of Residential Demand , 2014 .

[14]  Stamatis Karnouskos,et al.  Impact assessment of smart meter grouping on the accuracy of forecasting algorithms , 2013, SAC '13.

[15]  Hamidou Tembine,et al.  A Bayesian mean field game approach to supply demand analysis of the smart grid , 2013, 2013 First International Black Sea Conference on Communications and Networking (BlackSeaCom).

[16]  C. Clastres.  Smart grids: Another step towards competition, energy security and climate change objectives , 2011 .

[17]  Tharam S. Dillon,et al.  Short term load forecasting using an adaptive neural network , 1991 .

[18]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

[19]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[20]  N. L. Johnson,et al.  Multivariate Analysis , 1958, Nature.

[21]  Hsiao-Tien Pao,et al.  Forecasting electricity market pricing using artificial neural networks , 2007 .

[22]  Víctor Manuel Fernandes Mendes,et al.  Classification of new electricity customers based on surveys and smart metering data , 2016 .

[23]  Anil K. Jain.  Data clustering: 50 years beyond K-means , 2008, Pattern Recognit. Lett..

[24]  Abdollah Kavousi-Fard,et al.  A hybrid method based on wavelet, ANN and ARIMA model for short-term load forecasting , 2014, J. Exp. Theor. Artif. Intell..

[25]  Arunesh Kumar Singh,et al.  Load forecasting techniques and methodologies: A review , 2012, 2012 2nd International Conference on Power, Control and Embedded Systems.

[26]  Alexander J. Smola,et al.  Support Vector Regression Machines , 1996, NIPS.

[27]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[28]  F. Sioshansi.  Competitive electricity markets : design, implementation, performance , 2008 .

[29]  Matthew Rowe,et al.  Mathematical solutions for electricity networks in a low carbon future , 2013 .

[30]  J. C. Hwang,et al.  The application of artificial neural networks to substation load forecasting , 1996 .

[31]  Mohamed Chaouch,et al.  Clustering-Based Improvement of Nonparametric Functional Time Series Forecasting: Application to Intra-Day Household-Level Load Curves , 2014, IEEE Transactions on Smart Grid.

[32]  J. Nazarko,et al.  ARIMA models in load modelling with clustering approach , 2005, 2005 IEEE Russia Power Tech.

[33]  W. Jewell,et al.  Analysis of the cost per kWh to store electricity , 2008, 2008 IEEE Power and Energy Society General Meeting - Conversion and Delivery of Electrical Energy in the 21st Century.

[34]  Yacine Rezgui,et al.  Trees vs Neurons: Comparison between random forest and ANN for high-resolution prediction of building energy consumption , 2017 .

[35]  Yuancheng Li,et al.  Short-Term Load Forecasting Based on the Analysis of User Electricity Behavior , 2016, Algorithms.

[36]  Yong Cheol Kang,et al.  Short-term load forecasting for special days in anomalous load conditions using neural networks and fuzzy inference method , 2000 .

[37]  C. Holt.  Author's retrospective on ‘Forecasting seasonals and trends by exponentially weighted moving averages’ , 2004 .

[38]  C. K. Hansen,et al.  Short-term electricity load forecasting with Time Series Analysis , 2017, 2017 IEEE International Conference on Prognostics and Health Management (ICPHM).

[39]  S. Fan,et al.  Short-term load forecasting based on an adaptive hybrid method , 2006, IEEE Transactions on Power Systems.

[40]  Takanori Ida,et al.  Using Dynamic Electricity Pricing to Address Energy Crises Evidence from Randomized Field Experiments , 2013 .

[41]  Shyh-Jier Huang,et al.  Short-term load forecasting via ARMA model identification including non-Gaussian process considerations , 2003 .

[42]  Sieh Kiong Tiong,et al.  Electrical Power Load Forecasting using Hybrid Self-Organizing Maps and Support Vector Machines , 2008 .

[43]  Heng Huang,et al.  Using Smart Meter Data to Improve the Accuracy of Intraday Load Forecasting Considering Customer Behavior Similarities , 2015, IEEE Transactions on Smart Grid.

[44]  Ming-Wei Chang,et al.  Load forecasting using support vector Machines: a study on EUNITE competition 2001 , 2004, IEEE Transactions on Power Systems.

[45]  Karl Aberer,et al.  Electricity load forecasting for residential customers: Exploiting aggregation and correlation between households , 2013, 2013 Sustainable Internet and ICT for Sustainability (SustainIT).

[46]  Fereidoon P. Sioshansi.  Competitive electricity markets: questions remain about design, implementation, performance , 2008 .

[47]  B. Ripley,et al.  Pattern Recognition , 1968, Nature.

[48]  Lingfeng Wang,et al.  Smart meters for power grid — Challenges, issues, advantages and status , 2011, 2011 IEEE/PES Power Systems Conference and Exposition.

[49]  Wei-Jen Lee,et al.  Short-Term Load Forecasting Using Comprehensive Combination Based on Multimeteorological Information , 2009, IEEE Transactions on Industry Applications.