Blockchain and AI amalgamation for energy cloud management: Challenges, solutions, and future directions

• Published in: Journal of parallel and distributed computing Vol. 143; pp. 148 - 166
• Main Authors: Kumari, Aparna, Gupta, Rajesh, Tanwar, Sudeep, Kumar, Neeraj
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 01.09.2020
• Subjects: Blockchain; Energy cloud management; Smart grid; AI; Energy cloud management; Smart grid; Blockchain
• ISSN: 0743-7315; 1096-0848
• DOI: 10.1016/j.jpdc.2020.05.004

In the recent years, the Smart Grid (SG) system faces various challenges like the ever-increasing energy demand, the enormous growth of renewable energy sources (RES) with distributed energy generation (EG), the extensive Internet of Things (IoT) devices adaptation, the emerging security threats, and the foremost goal of sustaining the SG stability, efficiency and reliability. To cope up these issues there exists, the energy cloud management (ECM) system, which combines the infrastructure for energy, with intelligent energy usage and value-added services as per consumers demand. To achieve these, efficient demand-side forecasting and secure data transmission are the key factors. The energy management issues pose extreme gravity in finding sustainable solutions by using the blockchain (BC) and Artificial Intelligence (AI). AI-based techniques support various services such as energy load prediction, classification of the consumer, load management, and analysis where the BC provides data immutability and trust mechanism for secure energy management. Therefore, this paper reviews several existing AI-based approaches along with the advantages and challenges of integrating the BC technology and AI in the ECM system. We presented a decentralized AI-based ECM framework for energy management using BC and validate it using a case study. It is shown that how BC and AI can be used to mitigate ECM with security and privacy issues. Finally, we highlighted the open research issues and challenges of the BC-AI-based ECM system. •We presented a survey on security issues in existing BC and AI-based energy management for SG systems.•We highlighted the benefits by integration of BC and AI techniques and presented a solution taxonomy.•We proposed a decentralized and secure integrated architecture of ECM.•We highlighted various open issues and future recommendations to ensure secure and reliable ECM.