Using online learning to manage uncertainty in load-shifting with water heaters

Demand response (DR) is a large source of flexibility in power systems. DR refers to moderating the powerconsumption of electric loads like air conditioners, electric vehicles, and water heaters to provide power systemservices such as load-shifting and regulation. Loads that participate in DR programs are rewarded withdecreased electricity prices, rebates, or direct payments. Water heaters account for a substantial fraction ofwinter power consumption in Quebec. Water heaters have flexible power consumption because water may beheated hours before it is used. Therefore, water heaters are a natural candidate for DR. A key challenge in DRis load uncertainty. Conventional power system components like transmission lines, transformers, and energystorage have low uncertainty because they have precise physical models, high-bandwidth communication, andprecise actuation. None of these are true for loads. For example, a water heater depends on its human users, ishard to measure the power usage of if it is inside of a metered building, and its power consumption may be acomplicated function of temperature setpoint. Online convex optimization is a subfield of machine learningthat manages uncertainty by leveraging information as it becomes available. We will apply online convexoptimization to load-shifting with water heaters in Quebec.