Machine-Learning for Demand-Response
At a glance
In many countries, renewable energy investment is starting to become economically viable without support. This disrupts the business of electric utilities and may result in significant grid expansion needs in order to accommodate the increasing amount of renewable electricity. A promising solution to this problem is the usage of load management (load shifting and load restrictions). To leverage demand response, it is important to understand customer preferences for adjusting electricity demand to match with power supply. A conventional method is to assess consumers’ willingness to allow load control using a survey approach and dispatch their flexibility assuming constant preferences. However, static estimates based on surveys are likely to be imprecise, because consumers have limited experience with demand restrictions and because consumer preferences will vary across time. Automatic updates of consumer preferences based on their override actions and other data sources could thus reduce the need for static assessments of customer willingness to allow load control and revolutionize the way that the power system is operated.