Forecasting electricity smart meter data using conditional kernel density estimation

The recent advent of smart meters has led to large micro-level datasets. For the first time, the electricity consumption at individual sites is available on a near real-time basis. Efficient management of energy resources, electric utilities, and transmission grids, can be greatly facilitated by harnessing the potential of this data. The aim of this study is to generate probability density estimates for consumption recorded by individual smart meters. Such estimates can assist decision making by helping consumers identify and minimize their excess electricity usage, especially during peak times. For suppliers, these estimates can be used to devise innovative time-of-use pricing strategies aimed at their target consumers. We consider methods based on conditional kernel density (CKD) estimation with the incorporation of a decay parameter. The methods capture the seasonality in consumption, and enable a nonparametric estimation of its conditional density. Using 8 months of half-hourly data for 1000 meterswe evaluate point and density forecasts, for lead times ranging from one half-hour up to a week ahead. We find that the kernel-based methods outperform a simple benchmark method that does not account for seasonality, and compare well with an exponential smoothing method that we use as a sophisticated benchmark. To gauge the financial impact, we use density estimates of consumption to derive prediction intervals of electricity cost for different time-of-use tariffs. We show that a simple strategy of switching between different tariffs, based on a comparison of cost densities, delivers significant cost savings for the great majority of consumers.

[1]  Rob J. Hyndman,et al.  Forecasting time series with multiple seasonal patterns , 2008, Eur. J. Oper. Res..

[2]  Timo Kuosmanen,et al.  Best-practice benchmarking using clustering methods: Application to energy regulation , 2014, Omega.

[3]  James W. Taylor,et al.  Triple seasonal methods for short-term electricity demand forecasting , 2010, Eur. J. Oper. Res..

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

[5]  Jianqing Fan,et al.  A crossvalidation method for estimating conditional densities , 2004 .

[6]  Eva Regnier,et al.  Doing something about the weather , 2008 .

[7]  D. Ruppert.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction , 2004 .

[8]  Rob J. Hyndman,et al.  Bandwidth selection for kernel conditional density estimation , 2001 .

[9]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[10]  Rob J Hyndman,et al.  Forecasting Time Series With Complex Seasonal Patterns Using Exponential Smoothing , 2011 .

[11]  Ralph D. Snyder,et al.  Forecasting intraday time series with multiple seasonal cycles using parsimonious seasonal exponential smoothing , 2009 .

[12]  Chi-Keung Woo,et al.  Efficient frontiers for electricity procurement by an LDC with multiple purchase options , 2006 .

[13]  Dan Ruan,et al.  Kernel density estimation-based real-time prediction for respiratory motion , 2010, Physics in medicine and biology.

[14]  Stefan Sperlich,et al.  Simple and effective boundary correction for kernel densities and regression with an application to the world income and Engel curve estimation , 2010, Comput. Stat. Data Anal..

[15]  Sarah C. Darby,et al.  Metering: EU policy and implications for fuel poor households , 2012 .

[16]  Jooyoung Jeon,et al.  Using Conditional Kernel Density Estimation for Wind Power Density Forecasting , 2012 .

[17]  Peter Grindrod,et al.  A new error measure for forecasts of household-level, high resolution electrical energy consumption , 2014 .

[18]  Frederic Wurtz,et al.  Time series method for short-term load forecasting using smart metering in distribution systems , 2011, 2011 IEEE Trondheim PowerTech.

[19]  Ann Ewing,et al.  Doing Something about Weather , 1968 .

[20]  Rob J Hyndman,et al.  Estimating and Visualizing Conditional Densities , 1996 .

[21]  T. Gneiting.  Quantiles as optimal point forecasts , 2011 .

[22]  Siddharth Arora,et al.  Short-Term Forecasting of Anomalous Load Using Rule-Based Triple Seasonal Methods , 2013, IEEE Transactions on Power Systems.

[23]  Yee Mey Goh,et al.  Approaches to displaying information to assist decisions under uncertainty , 2012 .

[24]  Ahmad Faruqui,et al.  Unlocking the €53 Billion Savings from Smart Meters in the EU - How Increasing the Adoption of Dynamic Tariffs Could Make or Break the EU’s Smart Grid Investment , 2009 .

[25]  Jianhui Wang,et al.  Time Adaptive Conditional Kernel Density Estimation for Wind Power Forecasting , 2012, IEEE Transactions on Sustainable Energy.

[26]  Robert Fildes,et al.  Generalising about univariate forecasting methods: Further empirical evidence , 1998 .

[27]  Sean Lyons,et al.  Estimating the Impact of Time-of-Use Pricing on Irish Electricity Demand , 2014 .

[28]  Derek W. Bunn.  Short-Term Forecasting: A Review of Procedures in the Electricity Supply Industry , 1982 .

[29]  Nada R. Sanders,et al.  Quantifying costs of forecast errors: A case study of the warehouse environment☆ , 2009 .

[30]  A. Raftery,et al.  Probabilistic forecasts, calibration and sharpness , 2007 .

[31]  J. W. Taylor,et al.  Short-term electricity demand forecasting using double seasonal exponential smoothing , 2003, J. Oper. Res. Soc..