VAE-GAN Based Price Manipulation in Coordinated Local Energy Markets

2025-07-26

AI Summary

This study identifies a critical vulnerability in local energy markets—utility providers can exploit VAE-GAN–generated adversarial price signals to conduct price manipulation, inflicting substantial financial losses on prosumers lacking generation capacity. Such attacks undermine market fairness and hinder coordinated trading among heterogeneous prosumers. Method: To address these challenges, we propose a multi-agent dynamic coordination mechanism based on MADDPG and innovatively embed VAE-GAN into the price modeling pipeline to enable controllable simulation and impact assessment of data-driven manipulation strategies. Contribution/Results: Experiments demonstrate that (1) adversarial pricing persistently erodes the economic welfare of vulnerable prosumers—a robust effect across market scales; and (2) market expansion inherently fosters agent cooperation, enhancing transactional stability and distributive fairness. Our framework provides a novel methodological foundation and empirical evidence for designing robust regulatory policies and equitable market mechanisms in decentralized energy systems.

Technology Category

• Multiagent Systems: Adversarial Agents
• Game Theory and Economic Paradigms: Adversarial Learning
• Machine Learning: Adversarial Learning & Robustness

Application Category

• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments

Abstract

This paper introduces a model for coordinating prosumers with heterogeneous distributed energy resources (DERs), participating in the local energy market (LEM) that interacts with the market-clearing entity. The proposed LEM scheme utilizes a data-driven, model-free reinforcement learning approach based on the multi-agent deep deterministic policy gradient (MADDPG) framework, enabling prosumers to make real-time decisions on whether to buy, sell, or refrain from any action while facilitating efficient coordination for optimal energy trading in a dynamic market. In addition, we investigate a price manipulation strategy using a variational auto encoder-generative adversarial network (VAE-GAN) model, which allows utilities to adjust price signals in a way that induces financial losses for the prosumers. Our results show that under adversarial pricing, heterogeneous prosumer groups, particularly those lacking generation capabilities, incur financial losses. The same outcome holds across LEMs of different sizes. As the market size increases, trading stabilizes and fairness improves through emergent cooperation among agents.

Problem

• Coordinate prosumers with diverse DERs in local energy markets
• Prevent financial losses from VAE-GAN based price manipulation
• Optimize real-time energy trading decisions using MADDPG framework

Innovation

• MADDPG framework for real-time prosumer decisions
• VAE-GAN model for adversarial price manipulation
• Data-driven reinforcement learning for energy trading