Correlation-based Feature Selection for Discrete and Numeric Class Machine Learning
ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
When to reap and when to sow - lowering peak usage with realistic batteries
WEA'08 Proceedings of the 7th international conference on Experimental algorithms
Agent-based micro-storage management for the Smart Grid
Proceedings of the 9th International Conference on Autonomous Agents and Multiagent Systems: volume 1 - Volume 1
LIBSVM: A library for support vector machines
ACM Transactions on Intelligent Systems and Technology (TIST)
The impact of electricity pricing schemes on storage adoption in Ontario
Proceedings of the 3rd International Conference on Future Energy Systems: Where Energy, Computing and Communication Meet
Aggressive Datacenter Power Provisioning with Batteries
ACM Transactions on Computer Systems (TOCS)
Scaling distributed energy storage for grid peak reduction
Proceedings of the fourth international conference on Future energy systems
DC picogrids: a case for local energy storage for uninterrupted power to DC appliances
Proceedings of the fourth international conference on Future energy systems
Proceedings of the fourth international conference on Future energy systems
Sharing renewable energy in smart microgrids
Proceedings of the ACM/IEEE 4th International Conference on Cyber-Physical Systems
Incentivizing Advanced Load Scheduling in Smart Homes
Proceedings of the 5th ACM Workshop on Embedded Systems For Energy-Efficient Buildings
It's Different: Insights into home energy consumption in India
Proceedings of the 5th ACM Workshop on Embedded Systems For Energy-Efficient Buildings
Hi-index | 0.00 |
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.