| Title | Cyber-Physical Risk Driven Routing Planning with Deep Reinforcement-Learning in Smart Grid Communication Networks |
| Publication Type | Conference Paper |
| Year of Publication | 2020 |
| Authors | Jin, Z., Yu, P., Guo, S. Y., Feng, L., Zhou, F., Tao, M., Li, W., Qiu, X., Shi, L. |
| Conference Name | 2020 International Wireless Communications and Mobile Computing (IWCMC) |
| Keywords | communication link, Communication networks, Constraint-Dijkstra algorithm, CPS, cyber-physical system, Cyber-physical systems, Damage Assessment, deep reinforcement learning, deep reinforcement-learning, delays, DRL, information space, intelligent algorithms, learning (artificial intelligence), link load balance, Load modeling, neural nets, node load pressure, Optimization, physical space, Planning, power engineering computing, power generation planning, power grid system, pubcrawl, resilience, Resiliency, risk assessment model, Risk Balance, risk management, route planning algorithm, Routing, Routing Planning, service communication delay, smart grid communication networks, Smart grids, smart power grids |
| Abstract | In modern grid systems which is a typical cyber-physical System (CPS), information space and physical space are closely related. Once the communication link is interrupted, it will make a great damage to the power system. If the service path is too concentrated, the risk will be greatly increased. In order to solve this problem, this paper constructs a route planning algorithm that combines node load pressure, link load balance and service delay risk. At present, the existing intelligent algorithms are easy to fall into the local optimal value, so we chooses the deep reinforcement learning algorithm (DRL). Firstly, we build a risk assessment model. The node risk assessment index is established by using the node load pressure, and then the link risk assessment index is established by using the average service communication delay and link balance degree. The route planning problem is then solved by a route planning algorithm based on DRL. Finally, experiments are carried out in a simulation scenario of a power grid system. The results show that our method can find a lower risk path than the original Dijkstra algorithm and the Constraint-Dijkstra algorithm. |
| DOI | 10.1109/IWCMC48107.2020.9148342 |
| Citation Key | jin_cyber-physical_2020 |
Cyber-Physical Risk Driven Routing Planning with Deep Reinforcement-Learning in Smart Grid Communication Networks