Journal ArticleDOI
Reinforcement-learning-based dynamic defense strategy of multistage game against dynamic load altering attack
TLDR
A new dynamic defense strategy against D-LAAs is proposed through a multistage game between the attacker and the defender which is solved by minimax-q learning and can be deployed in advance when such cyber-physical attacks are anticipated.About:
This article is published in International Journal of Electrical Power & Energy Systems.The article was published on 2021-10-01. It has received 10 citations till now. The article focuses on the topics: Reinforcement learning & Cascading failure.read more
Citations
More filters
Journal ArticleDOI
Mitigating Load-Altering Attacks Against Power Grids Using Cyber-Resilient Economic Dispatch
TL;DR: In this article , a Cyber-Resilient Economic Dispatch (CRED) concept is proposed and seamlessly integrated with attack detection and identification to form a cyber resiliency enhancement framework.
Journal ArticleDOI
Defense Strategy Selection Model Based on Multistage Evolutionary Game Theory
TL;DR: In this article, a reward value learning mechanism (RLM) is proposed to penalize the attack and defense reward values for the next stage, which reduces the probability of defense strategy failure.
Proceedings ArticleDOI
Cyberattacks against Direct Load Control of Residential Electric Water Heaters in Smart Grids
TL;DR: This paper considers a cyberattack scenario in which an adversary gains access to the advanced metering infrastructure and sends malicious activation commands to a large number of water heaters forcing them to simultaneously switch on in the midst of a peak shaving period, thus causing a sudden, large power demand that could lead to a system-wide blackout.
Journal ArticleDOI
Dynamic load altering attack detection for cyber physical power systems via sliding mode observer
TL;DR: In this article , an attack detection scheme based on deviation signal is proposed for smart grid under dynamic load altering attack (DLAA), and the proposed attack detection logic is designed to detect attacks by comparing the deviation signal and threshold.
Journal ArticleDOI
A Learning Assisted Method for Uncovering Power Grid Generation and Distribution System Vulnerabilities
TL;DR: In this paper , a combination of formal methods and machine learning tools are used to learn power system dynamics with the objective of generating unsafe yet stealthy false data based attack sequences, which enables the grid with anomaly detectors in a generalized manner.
References
More filters
Book ChapterDOI
Markov games as a framework for multi-agent reinforcement learning
TL;DR: A Q-learning-like algorithm for finding optimal policies and its application to a simple two-player game in which the optimal policy is probabilistic is demonstrated.
Journal ArticleDOI
Stochastic Games
TL;DR: In a stochastic game the play proceeds by steps from position to position, according to transition probabilities controlled jointly by the two players, and the expected total gain or loss is bounded by M, which depends on N 2 + N matrices.
Book ChapterDOI
Introduction to Machine Learning
F. Richard Yu,Ying He +1 more
TL;DR: Machine learning is evolved from a collection of powerful techniques in AI areas and has been extensively used in data mining, which allows the system to learn the useful structural patterns and models from training data as discussed by the authors.
Book
An Introduction to Game Theory
TL;DR: An Introduction to Game Theory International Edition, by Martin J. Osborne, presents the main principles of game theory and shows how they can be used to understand economics, social, political, and biological phenomena as discussed by the authors.
Book
Energy function analysis for power system stability
TL;DR: In this article, the authors present an energy function for a single-machine 39 bus system, which is based on the Tsolas-Araposthasis-Varaiya model.