Energy data security and pricing model in local energy markets using artificial intelligence

The increasing adoption of local energy markets has introduced new opportunities for decentralized energy trading but has rendered these systems vulnerable to significant cyberthreats. For local energy markets to remain trustworthy and reliable for efficient energy trading, data availability and integrity must be guaranteed. However, due to the use of contemporary information and communication technologies, these systems are becoming more susceptible to cyberthreats, such as distributed denial of service and false data injection attacks, which can interfere with regular business operations and jeopardize the fairness of trading. This article presents a comprehensive framework utilizing artificial intelligence to ensure a secure bilateral trading environment by identifying corrupted trading data, preventing customers from reacting to it, and mitigating threats’ impact on it. In addition, the proposed framework suggests a new real-time optimal trading price-giving model based on artificial intelligence to improve the financial benefits for both sellers and buyers. The framework's effectiveness in maintaining trading data security and operational resilience is demonstrated through a thorough analysis. The simulation results testify that the designed trading price-giving approach benefits both sellers and buyers more than business-as-usual. Moreover, how the secured trading data sharing environment helps in maintaining financial benefits among customers during attack scenarios is also investigated. This work not only enhances the security and dependability of local energy markets but also emphasizes the financial benefits of implementing artificial intelligence-based schemes in energy trading systems.