Anomaly detection in smart grid based on encoder-decoder framework with recurrent neural network

Fengming, Zheng; Li, Shufang; Guo, Zhimin; Wu, Bo; Tian, Shiming; Pan, Mingming

doi:10.1016/s1005-8885(17)60243-7

Cited by 36 publications

(10 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The main objective of the weighted feature selection is to maximize the variance of all the data and correlation coefficient of data of same class and it is provided in Eq. (10).…”

Section: Rnd Cf Wfmentioning

confidence: 99%

“…The power grids are generated by the fusion of different supporting devices and electrical lines to initiate a network. Moreover, they transform a certain energy unit for the network [10]. Presently, smart grids are commonly utilized in communication and information technology to improve the effectualness of operative control, performance, planning and management [11].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Optimizing Anomaly Detection in Smart Grids with Modified FDA and Dilated GRU-based Adaptive Residual RNN

Scholar,

(Senior)

2024

Preprint

View full text Add to dashboard Cite

The integration of Information and Communication Technologies (ICT) into the conventional power grid defines a smart grid, overseeing electrical power distribution, generation, and utilization. Despite its benefits, the smart grid encounters communication challenges due to various abnormalities. Detecting these anomalies is crucial for identifying power outages, energy theft, equipment failure, structural faults, power consumption irregularities, and cyber-attacks. While power systems adeptly handle natural disturbances, discerning cyber-attack-induced anomalies proves complex. This paper introduces an intelligent deep learning approach for smart grid anomaly detection. Initially, data is collected from standard smart meter, weather, and user behavior sources. Optimal weighted feature selection, utilizing the Modified Flow Direction Algorithm (MFDA), precedes inputting selected features into the "Adaptive Residual Recurrent Neural Network with Dilated Gated Recurrent Unit (ARRNN-DGRU)" for anomaly identification. Simulation results affirm the model's superior performance, with a heightened detection rate compared to existing methods, bolstering the smart grid system's robustness.

show abstract

“…The main objective of the weighted feature selection is to maximize the variance of all the data and correlation coefficient of data of same class and it is provided in Eq. (10).…”

Section: Rnd Cf Wfmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Optimizing Anomaly Detection in Smart Grids with Modified FDA and Dilated GRU-based Adaptive Residual RNN

Scholar,

(Senior)

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Phase measurement unit (PMU) measurements datasets [86], real-time simulations on IEEE Bus testing platforms [87] and power utility logs [88,89]. In addition to a wide range of machine learning approaches such as anomaly detection methods [90][91][92][93][94], time series analysis techniques [95][96][97], grid load variations [98], IoT premises [99][100][101], and anomaly detection based on smart meter data [102][103][104][105][106][107] are also used to analyze anomalies in smart grid systems. With an aim at anomaly detection for electricity usage, the authors in [108][109][110] employed cloud computing technology.…”

Section: Detection Techniquesmentioning

confidence: 99%

Survey on Simulation and Vulnerability Testing in Smart Grid

Banik,

Banik

2024

Preprint

View full text Add to dashboard Cite

The rapid integration of Information and Communication Technology (ICT) is transforming the traditional electrical grid into a {\em Smart Grid}. Smart grids enable two-way communication and improved monitoring and control between utilities and customers. However, due to its heterogeneous nature, public exposure, and weak security at low-powered devices, the Smart Grid has vulnerabilities to various malicious threats, adversaries, and cyber attacks, which may affect cost and service availability. Additionally, when the systems' confidentiality, integrity, or availability are compromised, the resulting fallout can threaten national security and have cascading effects on human lives. Given the extreme consequences of an attack, smart-grid technology must be thoroughly tested for correct operation and security {\em before} it is deployed. As a result, vulnerability testing of smart grids, not only for correctness but for security purposes, has been the subject of numerous studies by academics, government agencies, and private companies. This paper reviews the vulnerabilities associated with the smart grid and spotlights simulation as the vulnerability testing methodology conducted in recent pertinent research works. It also presents various security aspects of the smart grid, including grid applications, system and network infrastructure and components, cyber threats and attacks, simulation, and different mitigation techniques. Finally, we analyze the gaps in the current research works, focusing on simulation. We briefly present a real-time simulation testbed that mimics customer behaviour and integrates hardware in the loop to apply attack methods, analyze vulnerabilities and risk mitigation associated with the smart grid system, and propose future work to improve the current framework.

show abstract

“…Reference [18] proposed a system of statistical-based anomaly detection method based on supervised learning, and implemented a Lambda system with the in-memory distributed computing framework, Spark and its extension Spark Streaming. Reference [19] Suggested the framework of encoder-decoder in recurrent neural network (RNN) to identify an anomaly. Enhancing the reliability of power systems through anomaly detection in smart grid is critical.…”

Section: Related Workmentioning

confidence: 99%

An Intelligent Intrusion Detection System in Smart Grid Using PRNN Classifier

Ganesan¹,

Xavier²

2023

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

Typically, smart grid systems enhance the ability of conventional power system networks as it is vulnerable to several kinds of attacks. These vulnerabilities might cause the attackers or intruders to collapse the entire network system thus breaching the confidentiality and integrity of smart grid systems. Thus, for this purpose, Intrusion detection system (IDS) plays a pivotal part in offering a reliable and secured range of services in the smart grid framework. Several existing approaches are there to detect the intrusions in smart grid framework, however they are utilizing an old dataset to detect anomaly thus resulting in reduced rate of detection accuracy in real-time and huge data sources. So as to overcome these limitations, the proposed technique is presented which employs both real-time raw data from the smart grid network and KDD99 dataset thus detecting anomalies in the smart grid network. In the grid side data acquisition, the power transmitted to the grid is checked and enhanced in terms of power quality by eradicating distortion in transmission lines. In this approach, power quality in the smart grid network is enhanced by rectifying the fault using a FACT device termed UPQC (Unified Power Quality Controller) and thereby storing the data in cloud storage. The data from smart grid cloud storage and KDD99 are pre-processed and are optimized using Improved Aquila Swarm Optimization (IASO) to extract optimal features. The probabilistic Recurrent Neural Network (PRNN) classifier is then employed for the prediction and classification of intrusions. At last, the performance is estimated and the outcomes are projected in terms of grid voltage, grid current, Total Harmonic Distortion (THD), voltage sag/swell, accuracy, precision, recall, F-score, false acceptance rate (FAR), and detection rate of the classifier. The analysis is compared with existing techniques to validate the proposed model efficiency.

show abstract

Anomaly detection in smart grid based on encoder-decoder framework with recurrent neural network

Cited by 36 publications

References 3 publications

Optimizing Anomaly Detection in Smart Grids with Modified FDA and Dilated GRU-based Adaptive Residual RNN

Optimizing Anomaly Detection in Smart Grids with Modified FDA and Dilated GRU-based Adaptive Residual RNN

Survey on Simulation and Vulnerability Testing in Smart Grid

An Intelligent Intrusion Detection System in Smart Grid Using PRNN Classifier

Contact Info

Product

Resources

About