Journal
IEEE TRANSACTIONS ON SMART GRID
Volume 9, Issue 6, Pages 6118-6127Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TSG.2017.2703643
Keywords
Agile methodology; complex bidding; demand response; multi-agent system; reinforcement learning
Categories
Ask authors/readers for more resources
This paper formulates an applied methodology for an agile demand response using mathematical micromodels. The optimal strategy chosen by an aggregator is the maximization of social welfare derived from demand flexibility. The notion of complex demand bidding is already given in the literature, however heretofore it is formulated as the relationship of price with both demand elasticity and marginal cost along with temporal and profit constraints. Although the planning of flexible demand is already handled by using advance learning techniques in literature, herein simple Q-learning technique in a decentralized fashion is proposed. Moreover, trade-offs between the proposed complex bidding rules are explored in a day-ahead market context. Due to the given complex bidding rules and principle of learning, the methodology can be easily applied in active distribution network. Several number of houses, equipped with the proposed complex bidding mechanism and decentralized learning capability, has been simulated, thus illustrating the application of methodology formulated herein.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available