Optimizing Prosumer Policies in Periodic Double Auctions Inspired by Equilibrium Analysis (Extended Version)
Bharat Manvi, Sanjay Chandlekar, Easwar Subramanian
TL;DR
This work addresses cost-optimal bidding in periodic double auctions with prosumer participation by formulating the problem as a finite-horizon Markov game and deriving Markov perfect Nash equilibrium (MPNE) policies under complete information. It then introduces MPNE-BBS, a practical algorithm that reconstructs an approximate supply curve from past auctions to operate under incomplete information, and validates the approach in the PowerTAC wholesale market simulator against strong baselines. The key contributions include MPNE solutions for adequate and inadequate supply conditions, robustness to multiple bids, and a complete design pipeline from analytical equilibria to a deployable bidding strategy. The results demonstrate that MPNE-BBS achieves near-best wholesale costs across various market and demand scenarios, highlighting the practical viability of equilibrium-based bidding in realistic energy markets.
Abstract
We consider a periodic double auction (PDA) wherein the main participants are wholesale suppliers and brokers representing retailers. The suppliers are represented by a composite supply curve and the brokers are represented by individual bids. Additionally, the brokers can participate in small-scale selling by placing individual asks; hence, they act as prosumers. Specifically, in a PDA, the prosumers who are net buyers have multiple opportunities to buy or sell multiple units of a commodity with the aim of minimizing the cost of buying across multiple rounds of the PDA. Formulating optimal bidding strategies for such a PDA setting involves planning across current and future rounds while considering the bidding strategies of other agents. In this work, we propose Markov perfect Nash equilibrium (MPNE) policies for a setup where multiple prosumers with knowledge of the composite supply curve compete to procure commodities. Thereafter, the MPNE policies are used to develop an algorithm called MPNE-BBS for the case wherein the prosumers need to re-construct an approximate composite supply curve using past auction information. The efficacy of the proposed algorithm is demonstrated on the PowerTAC wholesale market simulator against several baselines and state-of-the-art bidding policies.