A Learning-Based Solution for an Adversarial Repeated Game in Cyber–Physical Power Systems

Paul, Shuva; Ni, Zhen; Mu, Chaoxu

doi:10.1109/tnnls.2019.2955857

Cited by 33 publications

(19 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When applying adversarial RL to the power system cyber security problem [179]- [181], one can model the cyber attacker as the adversarial agent, whose attack actions, attack schemes, and payoffs depend on the practical settings. Reference [180] formulates a repeated game to mimic the interactions between the attackers and defenders in power systems. Reference [181] proposes an agent-specific adversary MDP to learn an adversarial policy and uses it to improve the robustness of RL methods via adversarial training.…”

Section: A Safety and Robustnessmentioning

confidence: 99%

Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challenges

Chen

Tang

et al. 2022

IEEE Trans. Smart Grid

153

View full text Add to dashboard Cite

With large-scale integration of renewable generation and distributed energy resources, modern power systems are confronted with new operational challenges, such as growing complexity, increasing uncertainty, and aggravating volatility. Meanwhile, more and more data are becoming available owing to the widespread deployment of smart meters, smart sensors, and upgraded communication networks. As a result, data-driven control techniques, especially reinforcement learning (RL), have attracted surging attention in recent years. This paper provides a comprehensive review of various RL techniques and how they can be applied to decision-making and control in power systems. In particular, we select three key applications, i.e., frequency regulation, voltage control, and energy management, as examples to illustrate RL-based models and solutions. We then present the critical issues in the application of RL, i.e., safety, robustness, scalability, and data. Several potential future directions are discussed as well.

show abstract

Section: A Safety and Robustnessmentioning

confidence: 99%

Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challenges

Chen

Tang

et al. 2022

IEEE Trans. Smart Grid

153

View full text Add to dashboard Cite

show abstract

“…These algorithms provide defence strategies and resistance against security threats to prevent and minimize the impacts or casualties adaptively. Many machine learning and deep learning models have applied intrusion detection [5][6][7], malware detection [8][9][10][11], cyber-physical attacks [12][13][14] and data privacy protection [14].…”

Section: Introductionmentioning

confidence: 99%

A Novel Hybrid Deep Learning Framework for Intrusion Detection Systems in WSN-IoT Networks

Maheswari¹,

Karthika²

2022

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

With the advent of wireless communication and digital technology, low power, Internet-enabled, and reconfigurable wireless devices have been developed, which revolutionized day-to-day human life and the economy across the globe. These devices are realized by leveraging the features of sensing, processing the data and nodes communications. The scale of Internet-enabled wireless devices has increased daily, and these devices are exposed to various cyberattacks. Since the complexity and dynamics of the attacks on the devices are computationally high, intelligent, scalable and high-speed intrusion detection systems (IDS) are required. Moreover, the wireless devices are battery-driven; implementing them would consume more energy, weakening the accuracy of detecting the attacks. Hence the design of the IDS is required, which has to establish the good trade-offs between Energy and accuracy. This research includes the Multi-tiered Intrusion Detection (MDIT) with hybrid deep learning models for improved detection accuracy in wireless networks; spotted hyena optimization (SHO) and Long short-term memory (LSTM) have been studied to design IDS effectively. Extensive experimentation has been carried out in real-time scenarios using the Node MCU Embedded boards and standard benchmarks such as CIDDS-001, UNSWNB15 and KDD++ datasets compared with the other traditional and existing learning models. The average prediction accuracy of 99.89% for all datasets has been achieved. The results show that the proposed system guarantees a high detection accuracy and reduces the prediction time, making this system suitable for resource-constrained IP-enabled wireless devices.

show abstract

“…The idea of ADP was first introduced by Werbos in [9] to solve the optimal control problem of discrete-time systems, and has evolved from model-based to model-free. Since it was introduced, ADP has received more and more attention and has been applied in many fields, such as robots [10], energy [11], helicopter [12], power systems [13], wastewater treatment [14], air-breathing hypersonic vehicle [15], multiagent systems [16] [17], ice-storage air conditioning systems [18], networked control systems [19], smart home energy management [20]. At the theoretical level, ADP has been extensively studied and become a powerful tool for solving optimal control problems of complex systems, such as optimal control of linear system and nonlinear system [21] [22] [23] [24], optimal tracking control of linear system and nonlinear system [25] [26] [27] [28].…”

Section: Introductionmentioning

confidence: 99%

Adaptive Dynamic Programming and Optimal Control of Unknown Multiplayer Systems Based on Game Theory

Zhao

2022

IEEE Access

View full text Add to dashboard Cite

In this paper, we present a new adaptive dynamic programming (ADP) scheme to solve the optimal control problem of multi-player systems with unknown dynamics from the perspective of nonzero-sum (NZS) games. In the presented scheme, a new iterative equation is given. On the basis of the given iterative equation, the control policy and corresponding value function for each player can be learned by using the state and input data, which does not need to identify the system dynamics. To overcome the difficulty of unknown system dynamics, neural network (NN)-based function approximation techniques are employed in the implementation. Based on the given iterative equation and NN-based function approximation techniques, a new non-model-based ADP algorithm is developed. The convergence of the developed non-model-based ADP algorithm is rigorously analyzed and proved. Finally, two numerical simulation examples are provided to demonstrate the performance of the developed non-model-based ADP algorithm. INDEX TERMS Adaptive dynamic programming, Nonzero-sum (NZS) games, Multi-player systems, Coupled Hamilton-Jacobi (HJ) equations, Neural network (NN).

show abstract

A Learning-Based Solution for an Adversarial Repeated Game in Cyber–Physical Power Systems

Cited by 33 publications

References 56 publications

Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challenges

Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challenges

A Novel Hybrid Deep Learning Framework for Intrusion Detection Systems in WSN-IoT Networks

Adaptive Dynamic Programming and Optimal Control of Unknown Multiplayer Systems Based on Game Theory

Contact Info

Product

Resources

About