Abstract:
Demand response is a crucial tool to maintain the stability of
the smart grids. With the upcoming research trends in the area
of electricity markets, it has become a possibility to design a
dynamic pricing system, and consumers are made aware of
what they are going to pay. Though the dynamic pricing system (pricing based on the total demand a distributor company
is facing) seems to be one possible solution, the current dynamic pricing approaches are either too complex for a consumer to understand or are too naive leading to inefficiencies
in the system (either consumer side or distributor side). Due
to these limitations, the recent literature is focusing on the
approach to provide incentives to the consumers to reduce
the electricity, especially in peak hours. For each round, the
goal is to select a subset of consumers to whom the distributor should offer incentives so as to minimize the loss which
comprises of cost of buying the electricity from the market,
uncertainties at consumer end, and cost incurred to the consumers to reduce the electricity which is a private information to the consumers. Due to the uncertainties in the loss
function (arising from renewable energy resources as well as
consumption needs), traditional auction theory-based incentives face manipulation challenges. Towards this, we propose
a novel combinatorial multi-armed bandit (MAB) algorithm,
which we refer to as GLS-MAB to learn the uncertainties
along with an auction to elicit true costs incurred by the consumers. We prove that our mechanism is regret optimal and is
incentive compatible. We further demonstrate efficacy of our
algorithms via simulations.
