Improved GSA-GA Algorithm Based Bad Data Detection, Identification and Correction for Power Grid

2013 ◽  
Vol 860-863 ◽  
pp. 2470-2473
Author(s):  
Hai Feng Liang ◽  
Ding Hui Shen ◽  
Xiao Lei Yu ◽  
Jing Zhang ◽  
Cheng Shan Wang
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Clustering Algorithm ◽  
Power Grid ◽  
Bp Algorithm ◽  
Data Detection ◽  
Grid Data ◽  
Bad Data Detection ◽  
Ga Algorithm ◽  
Bad Data

This paper presents an improved GSA-GA algorithm to achieve bad-data detection, identification and correction in power grid. The algorithm combines BP neural network, K-means clustering algorithm, gap statistical algorithm (GSA) and genetic algorithm together. BP neural network preprocesses the data, K-means algorithm clusters the preprocessed data and GSA algorithm determines the optimal clustering number and identifies the presence of bad data. After identifying the bad data, GA-BP algorithm is used to correct the identified data. This paper takes simulation tests to verify the proposed algorithms correctness and effectiveness based on actual grid data considering multiple types of existed bad data.

scholarly journals A Novel Detection Algorithm to Identify False Data Injection Attacks on Power System State Estimation

Energies ◽  
2019 ◽  
Vol 12 (11) ◽  
pp. 2209 ◽  
Author(s):  
Mehdi Ganjkhani ◽  
Seyedeh Narjes Fallah ◽  
Sobhan Badakhshan ◽  
Shahaboddin Shamshirband ◽  
Kwok-wing Chau
Keyword(s):  
Neural Network ◽  
Power System ◽  
State Estimation ◽  
Data Detection ◽  
System State ◽  
Power System State Estimation ◽  
Bad Data Detection ◽  
False Data Injection ◽  
Injection Attacks ◽  
Bad Data

This paper provides a novel bad data detection processor to identify false data injection attacks (FDIAs) on the power system state estimation. The attackers are able to alter the result of the state estimation virtually intending to change the result of the state estimation without being detected by the bad data processors. However, using a specific configuration of an artificial neural network (ANN), named nonlinear autoregressive exogenous (NARX), can help to identify the injected bad data in state estimation. Considering the high correlation between power system measurements as well as state variables, the proposed neural network-based approach is feasible to detect any potential FDIAs. Two different strategies of FDIAs have been simulated in power system state estimation using IEEE standard 14-bus test system for evaluating the performance of the proposed method. The results indicate that the proposed bad data detection processor is able to detect the false injected data launched into the system accurately.

Rapid Double-Layer Identification Method of Multi-Relevant Bad Data in Large-Scale Power Grids

2014 ◽  
Vol 672-674 ◽  
pp. 1294-1300
Author(s):  
Zhao Kun ◽  
Xing Ying ◽  
Jie Xu ◽  
Yin Zhang ◽  
Yan Lei ◽  
...  
Keyword(s):  
Double Layer ◽  
Large Scale ◽  
Detection Method ◽  
Power Grid ◽  
Power Grids ◽  
Data Detection ◽  
Bad Data Detection ◽  
Identification Method ◽  
Detection And Identification ◽  
Bad Data

Bad data detection and identification is an important part of state estimation. When the relevant bad data appears, however, there is residual pollution and residual submerged condition in currently available methods of bad data detection and identification. In view of the above problem, this article presents a double-layer bad data detection and identification technique. At first, it is based on regularization residual detection method (Rn detection method) to identify the suspect measurement sets. And then, it presents a fast search technique of interrelated suspect measurements to search interrelated measurements in all the suspect measurements of the entire power grid and produce interrelated suspect measurement sets. Furthermore, use double-layer identification method to fast identify the bad data in interrelated suspect measurement sets, in other words, identify all the bad data in entire power grid. At last, taking IEEE39 node power grid for example, this detection method of bad data is analyzed, the accuracy and effectiveness of this method is to be verified.

Sign in / Sign up

Export Citation Format

Share Document