A Bayesian perspective on Residential Demand Response using smart meter data

The widespread deployment of Advanced Metering Infrastructure has made granular data of residential electricity consumption available on a large scale. One field of research that relies on such granular consumption data is Residential Demand Response, where individual users are incentivized to temporarily reduce their consumption during periods of high marginal cost of electricity. To quantify the economic potential of Residential Demand Response, it is important to estimate the reductions during Demand Response hours, taking into account the heterogeneity of electricity users. In this paper, we incorporate latent variables representing behavioral archetypes of electricity users into the process of short-term load forecasting with Machine Learning methods, thereby differentiating between varying levels of energy consumption. The latent variables are constructed by fitting Conditional Mixture Models of Linear Regressions and Hidden Markov Models on smart meter data of a Residential Demand Response program in the western United States. We observe a notable increase in the accuracy of short-term load forecasts compared to the case without latent variables. We estimate the reductions during Demand Response events conditional on the latent variables and discover a higher DR reduction among users with automated smart home devices compared to those without.

• Publication year

  2016

• Venue

  Allerton Conference on Communication, Control, and Computing

• Publication date

  2016-08-12

• Fields of study

  Computer Science, Economics, Mathematics, Engineering, Environmental Science

• Identifiers
  DOI 10.1109/ALLERTON.2016.7852373arXiv 1608.03862
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Residential demand response targeting using machine learning with observational data

  2016influential reference
• Forecasting electricity smart meter data using conditional kernel density estimation

  2014cited by this paper
• Demand forecasting in smart grids

  2014influential reference
• A model for the effect of aggregation on short term load forecasting

  2014cited by this paper
• Introduction to Probabilistic Graphical Models

  2014cited by this paper
• Occupancy estimation for smart buildings by an auto-regressive hidden Markov model

  2014cited by this paper
• Dynamic modeling of presence of occupants using inhomogeneous Markov chains

  2014cited by this paper
• Hybrid Kalman Filters for Very Short-Term Load Forecasting and Prediction Interval Estimation

  2013cited by this paper
• Occupancy Detection from Electricity Consumption Data

  2013cited by this paper
• Nonlinear Models for Short-time Load Forecasting

  2012cited by this paper
• Occupancy and indoor environment quality sensing for smart buildings

  2012cited by this paper
• An evaluation of Bayesian techniques for controlling model complexity and selecting inputs in a neural network for short-term load forecasting

  2010cited by this paper
• Electric Load Forecasting Based on Locally Weighted Support Vector Regression

  2010cited by this paper
• Do LEED-certified buildings save energy? Not really…

  2009cited by this paper
• Short-Term Load Forecasting Methods: An Evaluation Based on European Data

  2007cited by this paper
• Pattern Recognition and Machine Learning

  2006cited by this paper
• Short-term electric load forecasting based on Kalman filtering algorithm with moving window weather and load model

  2004cited by this paper
• An Introduction to Probabilistic Graphical Models

  2002cited by this paper
• Statistics and Causal Inference

  1985influential reference
• Introduction to Statistical Time Series.

  1976cited by this paper
• Estimating causal effects of treatments in randomized and nonrandomized studies.

  1974cited by this paper

• Machine Learning Applications for Smart Building Energy Utilization: A Survey

  2024cites this paper
• Artificial Intelligence Application in Demand Response: Advantages, Issues, Status, and Challenges

  2023cites this paper
• Adaptive individual residential load forecasting based on deep learning and dynamic mirror descent

  2023cites this paper
• Artificial Intelligence Enabled Demand Response: Prospects and Challenges in Smart Grid Environment

  2023cites this paper
• Data-driven modelling of energy demand response behaviour based on a large-scale residential trial

  2021cites this paper
• Reinforcement learning for whole-building HVAC control and demand response

  2020cites this paper
• Short-Term Industrial Load Forecasting Based on Ensemble Hidden Markov Model

  2020cites this paper
• Artificial intelligence and machine learning approaches to energy demand-side response: A systematic review

  2020cites this paper
• Eliciting private user information for residential demand response

  2017cites this paper
• Incentive Design in Human-in-the-Loop Cyber-Physical Systems: A Case Study on Demand Response in California

  2017cites this paper
• Estimating Heterogeneous Treatment Effects in Residential Demand Response

  2017cites this paper
• Hedging strategies for load-serving entities in wholesale electricity markets

  2017cites this paper
• Residential demand response targeting using machine learning with observational data

  2016cites this paper
• An optimal treatment assignment strategy to evaluate demand response effect

  2016cites this paper