False Data Detection in Smart Grid using Artificial Intelligence

In order to increase the utilization of artificial intelligence in smart grids, it is necessary to have an accurate state estimation. This criterion is an essential aspect, along with other functionalities for successful control and monitoring. As the internet and utility network form an increasing interconnectivity, it leaves the state estimators in a state of vulnerability to various attacks like bad data detection and false data injection. Though there are many research-works done on detectors for false data detection, depending on the contingencies, the counter measure will also vary. A sudden change physically will have a high impact on the available data, resulting in incorrect classification of the future instances. As a means of addressing this issue, we have analyzed the differences between data manipulation change and physical grid change for better understanding. Focusing on distribution change, we used outage and have introduced analysis of historical data. The goal is to determine the important aspects thereby identifying the scope. We have also used statistical hypothesis and dimensionality reduction for testing purpose. We have used IEEE 14 bus system for evaluation based on the scenario of attack: under concept drift and without concept drift. The result shows a more accurate output when compared with the other previously existing methodologies using concept drift.

Download Full-text

IoT based Smart Grid Attack Resistance in AC and DC State Estimation

Journal of Electrical Engineering and Automation - September 2019 ◽

10.36548/jeea.2020.3.002 ◽

2021 ◽

Vol 2 (3) ◽

pp. 118-122

Author(s):

Vivekanadam B

Keyword(s):

Big Data ◽

Internet Of Things ◽

Smart Grid ◽

Error Detection ◽

Smart Grids ◽

Data Detection ◽

Bad Data Detection ◽

Security Issues ◽

Number Of Factors ◽

Bad Data

Use of automation and intelligence in smart grids has led to implementation in a number of applications. When internet of things is incorporated it will result in the significant improvement a number of factors such as fault recovery, energy delivery efficiency, demand response and reliability. However, the collaboration of internet of things and smart grid gives rise to a number of security issues and threats. This is especially the case when using internet based protocols and public communication infrastructure. To address these issues we should ensure that the data stored is secure and critical information from the data is extracted in a careful manner. If any threat to its security is detective an early blackout warning should be issued immediately. In this paper we have proposed a geometric view point for big data attacks which is capable of bypassing bad data detection. We have created an environment where replay scheme is used launch blind energy big data attack. The defence mechanism of our proposed work is studied and found to be efficient. Experimental evidence supports our theory and we have found our methodology to efficiently improve error detection rate.

Download Full-text

Stacked Autoencoder Framework of False Data Injection Attack Detection in Smart Grid

Mathematical Problems in Engineering ◽

10.1155/2021/2014345 ◽

2021 ◽

Vol 2021 ◽

pp. 1-8

Author(s):

Liang Chen ◽

Songlin Gu ◽

Ying Wang ◽

Yang Yang ◽

Yang Li

Keyword(s):

Smart Grid ◽

Smart Grids ◽

Control Strategies ◽

Attack Detection ◽

Cyber Attacks ◽

Data Detection ◽

Layer By Layer ◽

Monitoring And Control ◽

Bad Data Detection ◽

False Data Injection

The advanced communication technology provides new monitoring and control strategies for smart grids. However, the application of information technology also increases the risk of malicious attacks. False data injection (FDI) is one kind of cyber attacks, which cannot be detected by bad data detection in state estimation. In this paper, a data-driven FDI attack detection framework of the smart grid with phasor measurement units (PMUs) is proposed. To enhance the detecting accuracy and efficiency, the multiple layer autoencoder algorithm is applied to abstract the hidden features of PMU measurements layer by layer in an unsupervised manner. Then, the features of the measurements and corresponding labels are taken as inputs to learn a softmax layer. Last, the autoencoder and softmax layer are stacked to form a FDI detection framework. The proposed method is applied on the IEEE 39-bus system, and the simulation results show that the FDI attacks can be detected with higher accuracy and computational efficiency compared with other artificial intelligence algorithms.

Download Full-text