Multi-unit Double Auctions: Equilibrium Analysis and Bidding Strategy using DDPG in Smart-grids

@inproceedings{Chandlekar2022MultiunitDA,
  title={Multi-unit Double Auctions: Equilibrium Analysis and Bidding Strategy using DDPG in Smart-grids},
  author={Sanjay Chandlekar and Easwar Subramanian and Sanjay Bhat and Praveen Paruchuri and Sujit Gujar},
  booktitle={Adaptive Agents and Multi-Agent Systems},
  year={2022}
}
We present a Nash equilibrium analysis for single-buyer singleseller multi-unit k-double auctions for scaling-based bidding strategies. We then design a Deep Deterministic Policy Gradient (DDPG) based learning strategy, DDPGBBS, for a participating agent to suggest bids that approximately achieve the above Nash equilibrium. We expand DDPGBBS to be helpful in more complex settings with multiple buyers/sellers trading multiple units in a Periodic Double Auction (PDA), such as the wholesale market… 

Figures and Tables from this paper

VidyutVanika21: An Autonomous Intelligent Broker for Smart-grids

An autonomous broker that liaises between retail customers and power-generating companies (GenCos) is essential for the smart grid ecosystem. The efficiency brought in by such brokers to the smart

References

SHOWING 1-10 OF 41 REFERENCES

Minimal-Intelligence Agents for Bargaining Behaviors in Market-Based Environments

This report describes simple mechanisms that allow autonomous software agents to en gage in bargaining behaviors in market based environments Groups of agents with such mechanisms could be used in

Learning Equilibrium Contributions in Multi-project Civic Crowdfunding

Crowdfunding is an efficient method for raising funds for projects. When used for non-excludable public projects, the process is termed Civic Crowdfunding (CC) and is an active research area.

Deep Deterministic Policy Gradient Based on Double Network Prioritized Experience Replay

The results show that the proposed DDPG algorithm based on the double network prioritized experience replay mechanism (DNPER-DDPG) has increased convergence speed and cumulative reward compared with the comparison algorithm.

Aiming for Half Gets You to the Top: Winning PowerTAC 2020

This paper presents a novel trading strategy that aims to balance gains against costs, and was utilized by the champion of the PowerTAC-2020 tournament, TUC-TAC, and incorporates a wholesale market strategy that employs Monte Carlo Tree Search to determine TUAC’s best course of action when participating in the market's double auctions.

The 2020 Power Trading Agent Competition

This is the specification for the Power Trading Agent Competition for 2020 (Power TAC 2020). Power TAC is a competitive simulation that models a “liberalized” retail electrical energy market, where

Bidding in Smart Grid PDAs: Theory, Analysis and Strategy (Extended Version)

This paper performs an equilibrium analysis of single unit single-shot double auctions with a certain clearing price and payment rule, which is referred to as ACPR, and empirically shows that MDPLCPBS follows the equilibrium strategy for double auctions that was previously analyzed.

Penalty Bidding Mechanisms for Allocating Resources and Overcoming Present Bias

This paper unite resource allocation and commitment devices through the design of contingent payment mechanisms, and proposes the two-bid penalty-bidding mechanism, which substantially improves utilization and achieves higher welfare and better equity in comparison with mechanisms used in practice and mechanisms that optimize welfare in the absence of present bias.

Thompson Sampling Based Multi-Armed-Bandit Mechanism Using Neural Networks

The results, in the setting of crowd-sourcing for recruiting quality workers, indicate that the learned payment rule guarantees better cost while maximizing the social welfare and also ensuring reduced variance in the utilities to the agents.

VidyutVanika: A Reinforcement Learning Based Broker Agent for a Power Trading Competition

This paper designs an autonomous broker VidyutVanika, the runner-up in the 2018 Power TAC competition, which relies on reinforcement learning in the tariff market and dynamic programming in the wholesale market to solve modified versions of known Markov Decision Process (MDP) formulations in the respective markets.

AgentUDE17: A Genetic Algorithm to Optimize the Parameters of an Electricity Tariff in a Smart Grid Environment

An online genetic algorithm that optimizes the parameters of an electricity consumption tariff, such as unit retail price, periodic, sign-up, and early withdrawal penalty payments on the fly, and uses time-of-use (TOU) price scheme to reduce peak-demand charges.