Zhaojun Hao, Politecnico di Milano, Energy Department, Italy
Operation and Maintenance of Cyber-Physical Energy Systems Accounting for Reliable and Safe Power Production and Supply (2023)
Supervisors: Prof. Enrico Zio, Prof. Francesco Di Maio
Keywords: Cyber-Physical Systems; Renewable Energy; Nuclear Power Plant; Flexible Operation; Dynamic Reliability Assessment; Operation & Maintenance; Deep Reinforcement Learning; Proximal Policy Optimization; Monte Carlo Tree Search; Multi-Objective Optimization; Advanced Lead-cooled Fast Reactor European Demonstrator (ALFRED
Cyber-Physical Energy Systems (CPESs) are energy systems that integrate cyber components within hardware systems for energy production, transmission, and distribution. With the penetration of Renewable Energy Sources (RESs), CPESs are required to provide flexible operation (e.g., load-following, frequency regulation) to respond to any sudden imbalance of the power grid, due to the variability in power generation by RESs.
A proper Operation & Maintenance (O&M) strategy is required to account for flexibility to respond to the energy demand and supply to the stochasticity of RESs, and also to avoid accidents of severe consequences caused by system physical or cyber system failures for safety reasons.
The objective of the Ph.D. work is to develop a framework for optimizing the O&M strategy of CPESs, which includes: I. modeling to identify and simulate the cyber aging mechanisms and its effects on CPES flexible operation control; II. developing a dynamic reliability framework with cyber aging model embedded to analyze CPES flexible operation dynamic reliability considering cyber aging factor; III. developing a Deep Reinforcement Learning (DRL) framework for CPES O&M strategy optimization and addressing the profit and safety tradeoff by using Multi-Objective Deep Reinforcement Learning (MODRL).
More information on Zhaojuns work
References and links:
- [J] Hao, F. Di Maio, E. Zio, "Multi-state Reliability Assessment Model of Base-load Cyber-Physical Energy Systems (CPES) during Flexible Operation considering Cyber Components aging", Energies 2021, 14(11), 3241; https://doi.org/10.3390/en14113241, https://www.mdpi.com/1996-1073/14/11/3241/htm
- [J] Hao, F. Di Maio, E. Zio, "A Sequential Decision Problem Formulation and Deep Reinforcement Learning Solution of the Optimization of O&M of Cyber-Physical Energy Systems (CPESs) for Reliable and Safe Power Production and Supply", Reliability Engineering & System Safety, 2023, https://www.sciencedirect.com/science/article/abs/pii/S0951832023001461