Customer Baseline Load Estimation for Incentive-Based Demand Response Using Long Short-Term Memory Recurrent Neural Network
Authors:
- 1 September 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Abstract
The transition to an intelligent, reliable and efficient smart grid with a high penetration of renewable energy drives the need to maximise the utilization of customers demand response potential. The availability of smart meter data means this potential can be more accurately estimated and suitable demand response (DR) programs can be targeted to customers for load shifting, clipping and reduction. In this paper, we focus on estimating customer demand baseline for incentive-based DR. We propose a long short-term memory recurrent neural network framework for customer baseline estimation using previous like days data during DR events period. We test the proposed methodology on the publicly available Irish smart meter data and results shows a significant increase in baseline estimation accuracy when compared to traditional baseline estimation methods.Keywords
This publication has 15 references indexed in Scilit:
- Short-Term Residential Load Forecasting Based on LSTM Recurrent Neural NetworkIEEE Transactions on Smart Grid, 2017
- Short-term electrical load forecasting using the Support Vector Regression (SVR) model to calculate the demand response baseline for office buildingsApplied Energy, 2017
- Data-Driven Baseline Estimation of Residential Buildings for Demand ResponseEnergies, 2015
- Statistical Estimation of the Residential BaselineIEEE Transactions on Power Systems, 2015
- Probabilistic baseline estimation via Gaussian process2015
- A Survey on Demand Response in Smart Grids: Mathematical Models and ApproachesIEEE Transactions on Industrial Informatics, 2015
- A Survey on Demand Response Programs in Smart Grids: Pricing Methods and Optimization AlgorithmsIEEE Communications Surveys & Tutorials, 2014
- When Bias Matters: An Economic Assessment of Demand Response Baselines for Residential CustomersIEEE Transactions on Smart Grid, 2014
- Efficient BackProp2012
- Long Short-Term MemoryNeural Computation, 1997