Residential demand response targeting using machine learning with observational data

The large-scale deployment of Advanced Metering Infrastructure among residential energy customers has served as a boon for energy systems research relying on granular consumption data. Residential Demand Response aims to utilize the flexibility of consumers to reduce their energy usage during times when the grid is strained. Suitable incentive mechanisms to encourage customers to deviate from their usual behavior have to be implemented to correctly control the bids into the wholesale electricity market as a Demand Response provider. In this paper, we present a framework for shortterm load forecasting on an individual user level, and relate non-experimental estimates of Demand Response efficacy (the estimated reduction of consumption during Demand Response events) to the variability of a user's consumption. We apply our framework on a dataset from a residential Demand Response program in the Western United States. Our results suggest that users with more variable consumption patterns are more likely to reduce their consumption compared to users with a more regular consumption behavior.

[1]  Claire J. Tomlin,et al.  A Bayesian perspective on Residential Demand Response using smart meter data , 2016, 2016 54th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[2]  Johanna L. Mathieu,et al.  Examining uncertainty in demand response baseline models and variability in automated responses to dynamic pricing , 2011, IEEE Conference on Decision and Control and European Control Conference.

[3]  M. Etezadi-Amoli,et al.  Smart meter based short-term load forecasting for residential customers , 2011, 2011 North American Power Symposium.

[4]  Tin Kam Ho,et al.  Demand forecasting in smart grids , 2014, Bell Labs Technical Journal.

[5]  Eric R. Ziegel,et al.  The Elements of Statistical Learning , 2003, Technometrics.

[6]  Young-Il Kim,et al.  Methods for generating TLPs (typical load profiles) for smart grid-based energy programs , 2011, 2011 IEEE Symposium on Computational Intelligence Applications In Smart Grid (CIASG).

[7]  G. Imbens,et al.  Machine Learning Methods for Estimating Heterogeneous Causal Eects , 2015 .

[8]  Q. Henry Wu,et al.  Electric Load Forecasting Based on Locally Weighted Support Vector Regression , 2010, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

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

[10]  P. McSharry,et al.  Short-Term Load Forecasting Methods: An Evaluation Based on European Data , 2007, IEEE Transactions on Power Systems.

[11]  Lynne E. Parker,et al.  Energy and Buildings , 2012 .

[12]  Georg Reichard,et al.  Socio-Economic Factors Affecting Individual Household Energy Consumption: A Systematic Review , 2011 .

[13]  Gianfranco Chicco,et al.  Overview and performance assessment of the clustering methods for electrical load pattern grouping , 2012 .

[14]  Ying Li,et al.  Automated Residential Demand Response: Algorithmic Implications of Pricing Models , 2012, IEEE Transactions on Smart Grid.

[15]  Rob J Hyndman,et al.  Short-Term Load Forecasting Based on a Semi-Parametric Additive Model , 2012, IEEE Transactions on Power Systems.

[16]  Chris Chatfield,et al.  Introduction to Statistical Time Series. , 1976 .

[17]  Siddharth Arora,et al.  Forecasting electricity smart meter data using conditional kernel density estimation , 2014, 1409.2856.

[18]  Jie Mi,et al.  Robust Nonparametric Statistical Methods , 1999, Technometrics.

[19]  P. Holland.  Statistics and Causal Inference , 1985 .

[20]  Michael E. Webber,et al.  Clustering analysis of residential electricity demand profiles , 2014 .

[21]  Ram Rajagopal,et al.  Household Energy Consumption Segmentation Using Hourly Data , 2014, IEEE Transactions on Smart Grid.

[22]  Koen Steemers,et al.  Behavioural, physical and socio-economic factors in household cooling energy consumption , 2011 .