Researchers at the University of Science and Technology Beijing in China have proposed a novel programming solution to optimize power consumption in batteries for use in smart homes.
The researchers used adaptive dynamic programming to develop a system in which batteries can learn and optimize their power consumption.
Their programming method breaks down the dilemma of how best to use batteries in smart home systems into smaller, more manageable problems. The answer to each of these small problems contributes to the answer to the larger problem, and as circumstances change, the system can analyze all of the small answers to determine how the bigger picture evolves. The algorithm learns which inputs lead to which output, and uses this information to understand when it is best to charge and discharge in order to limit power consumed from the grid.
The researchers next plan to examine how the damage caused by frequently switching between charging and discharging modes can be avoided.
View Full Article
Abstracts Copyright © 2017 Information Inc., Bethesda, Maryland, USA