Real-Time Energy Disaggregation of a Distribution Feeder's Demand Using Online Learning

Though distribution system operators have been adding more sensors to their networks, they still often lack an accurate real-time picture of the behavior of distributed energy resources such as demand responsive electric loads and residential solar generation. Such information could improve system reliability, economic efficiency, and environmental impact. Rather than installing additional costly sensing and communication infrastructure to obtain additional real-time information, it may be possible to use existing sensing capabilities and leverage knowledge about the system to reduce the need for new infrastructure. In this paper, we disaggregate a distribution feeder's demand measurements into: 1) the demand of a population of air conditioners, and 2) the demand of the remaining loads connected to the feeder. We use an online learning algorithm, Dynamic Fixed Share (DFS), that uses the real-time distribution feeder measurements as well as models generated from historical building- and device-level data. We develop two implementations of the algorithm and conduct case studies using real demand data from households and commercial buildings to investigate the effectiveness of the algorithm. The case studies demonstrate that DFS can effectively perform online disaggregation and the choice and construction of models included in the algorithm affects its accuracy, which is comparable to that of a set of Kalman filters.

[1]  Johanna L. Mathieu,et al.  Characterizing the Response of Commercial and Industrial Facilities to Dynamic Pricing Signals From the Utility , 2010 .

[2]  Joshua A. Taylor,et al.  Index Policies for Demand Response , 2014, IEEE Transactions on Power Systems.

[3]  Ram Rajagopal,et al.  Online learning for demand response , 2015, 2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[4]  Mark Herbster,et al.  Tracking the Best Expert , 1995, Machine Learning.

[5]  Ward Jewell,et al.  Impact of load type on power consumption and line loss in voltage reduction program , 2013, 2013 North American Power Symposium (NAPS).

[6]  Duncan S. Callaway,et al.  Arbitraging Intraday Wholesale Energy Market Prices With Aggregations of Thermostatic Loads , 2015, IEEE Transactions on Power Systems.

[7]  Nikos D. Hatziargyriou,et al.  Machine Learning Applications to Power Systems , 2001, Machine Learning and Its Applications.

[8]  Lucio Soibelman,et al.  Enhancing Electricity Audits in Residential Buildings with Nonintrusive Load Monitoring , 2010 .

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

[10]  Shuai Lu,et al.  Development and Validation of Aggregated Models for Thermostatic Controlled Loads with Demand Response , 2012, 2012 45th Hawaii International Conference on System Sciences.

[11]  Eilyan Bitar,et al.  Risk-Sensitive Learning and Pricing for Demand Response , 2016, IEEE Transactions on Smart Grid.

[12]  Duncan S. Callaway,et al.  State Estimation and Control of Electric Loads to Manage Real-Time Energy Imbalance , 2013, IEEE Transactions on Power Systems.

[13]  Prashant J. Shenoy,et al.  Predicting solar generation from weather forecasts using machine learning , 2011, 2011 IEEE International Conference on Smart Grid Communications (SmartGridComm).

[14]  Gregory S. Ledva,et al.  Inferring the behavior of distributed energy resources with online learning , 2015, 2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton).

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

[16]  Rebecca Willett,et al.  Online Convex Optimization in Dynamic Environments , 2015, IEEE Journal of Selected Topics in Signal Processing.

[17]  Paras Mandal,et al.  Machine Learning Applications for Load, Price and Wind Power Prediction in Power Systems , 2009, 2009 15th International Conference on Intelligent System Applications to Power Systems.

[18]  Antoine Lesage-Landry,et al.  Learning to Shift Thermostatically Controlled Loads , 2017, HICSS.

[19]  Abhay Gupta,et al.  Is disaggregation the holy grail of energy efficiency? The case of electricity , 2013 .

[20]  Desheng Dash Wu,et al.  Power load forecasting using support vector machine and ant colony optimization , 2010, Expert Syst. Appl..

[21]  Ming-Guang Zhang,et al.  Short-term load forecasting based on support vector machines regression , 2005, 2005 International Conference on Machine Learning and Cybernetics.

[22]  Yan Xu,et al.  Local voltage support from distributed energy resources to prevent air conditioner motor stalling , 2010, 2010 Innovative Smart Grid Technologies (ISGT).

[23]  Kevin P. Schneider,et al.  Modern Grid Initiative Distribution Taxonomy Final Report , 2008 .

[24]  Gabriela Hug,et al.  A moving horizon state estimator in the control of thermostatically controlled loads for demand response , 2013, 2013 IEEE International Conference on Smart Grid Communications (SmartGridComm).

[25]  Alessandro Abate,et al.  Aggregation and Control of Populations of Thermostatically Controlled Loads by Formal Abstractions , 2015, IEEE Transactions on Control Systems Technology.

[26]  Tao Hong,et al.  Short Term Electric Load Forecasting , 2012 .

[27]  Bart De Schutter,et al.  Residential Demand Response of Thermostatically Controlled Loads Using Batch Reinforcement Learning , 2017, IEEE Transactions on Smart Grid.

[28]  T. Logenthiran,et al.  Forecasting of photovoltaic power using extreme learning machine , 2015, 2015 IEEE Innovative Smart Grid Technologies - Asia (ISGT ASIA).