Title :
SmartCharge: Cutting the electricity bill in smart homes with energy storage
Author :
Mishra, Anadi ; Irwin, David ; Shenoy, Prashant ; Kurose, Jim ; Ting Zhu
Author_Institution :
Univ. of Massachusetts, Amherst, MA, USA
Abstract :
Market-based electricity pricing provides consumers an opportunity to lower their electric bill by shifting consumption to low price periods. In this paper, we explore how to lower electric bills without requiring consumer involvement using an intelligent charging system, called SmartCharge, and an on-site battery array to store low-cost energy for use during high-cost periods. SmartCharge´s algorithm reduces electricity costs by determining when to switch the home´s power supply between the grid and the battery array. The algorithm leverages a prediction model we develop, which forecasts future demand using statistical machine learning techniques. We evaluate SmartCharge in simulation using data from real homes to quantify its potential to lower bills in a range of scenarios. We show that typical savings today are 10-15%, but increase linearly with rising electricity prices. We also find that SmartCharge deployed at only 22% of 435 homes reduces the aggregate demand peak by 20%. Finally, we analyze SmartCharge´s installation and maintenance costs. Our analysis shows that battery advancements, combined with an expected rise in electricity prices, have the potential to make the return on investment positive for the average home within the next few years.
Keywords :
battery chargers; demand forecasting; electrical installation; energy conservation; energy storage; learning (artificial intelligence); load forecasting; maintenance engineering; power consumption; power engineering computing; power grids; power markets; power supplies to apparatus; pricing; secondary cells; statistical analysis; SmartCharge installation; SmartCharge simulation algorithm; demand forecasting; demand peak aggregation; electricity bill; electricity cost; energy storage; intelligent charging system; maintenance cost; market-based electricity pricing; on-site battery array; power supply grid; prediction model; smart home; statistical machine learning technique; Arrays; Batteries; Electricity; Monitoring; Pricing; Real time systems; Switches; Battery; Electricity; Energy; Grid;
Conference_Titel :
Future Energy Systems: Where Energy, Computing and Communication Meet (e-Energy), 2012 Third International Conference on
Conference_Location :
Madrid