Data-Based Line Trip Fault Prediction in Power Systems Using LSTM Networks and SVM

Zhang, Senlin; Wang, Yixing; Liu, Meiqin; Bao, Zhejing

doi:10.1109/access.2017.2785763

Cited by 195 publications

(85 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Grid component faults are significant problems in power distribution, for that, Senlin et al [13] proposed a method for prediction of the trip fault using long-short-term-memory and support vector machines which are a high margin classifier in neural networks. The data were captured with the LSTM network with a long time span.…”

Section: Related Work 151mentioning

confidence: 99%

A Smart Optimization of Fault Diagnosis in Electrical Grid Using Distributed Software-Defined IoT System

Mhdawi

Al-Raweshidy

2020

IEEE Systems Journal

View full text Add to dashboard Cite

Electrical power demands have increased significantly over the last years due to the rapid increase in air conditioning units and home appliances per domestic unit particularly in Iraq. Having uninterrupted power supply is essential for the continuity of power-generated home services and industrial platforms. Currently, in Iraq, electrical power interruption has become a big concern to the utility suppliers even with the successive attempts in putting end to this dilemma, but the issue still prevailed. One of the main factors in power outages in local zones is persistent faults in distribution transformers (DT). DT is considered one of the main elements in the electrical network that is essential for the reliability of the grid supply. Due to the internal lack of monitoring system and periodic maintenance, DT is relentlessly subject to faults due to high overhead utilization. Therefore, in order to enhance the grid reliability, transformer health check and maintenance practices, we propose a remote condition IoT monitoring and fault prediction system that is based on a customized Software-Defined Networking (SDN) technology. This approach is a transition to smart grid implementation by fusing the power grid with efficient and real-time wireless communication architecture. The SDN implementation is considered in two phases; one is a controller installed per local zone and the main controller that is installed between zones and connected to the core network. The core network consists of redundant links to recover from any future fails. Furthermore, we propose a prediction system that is based on Artificial Neural Network algorithm called Distribution Transformer Fault Prediction (DTFP) that is installed in the management plane for periodic prediction based on real-time sensor traffic to our proposed cloud. Moreover, we propose a communication protocol in the local zone called Local SDNsense. The SDN-sense ensures a reliable communication and local node selection to relay DT sensor data to the main controller. Our proposed architecture showcase an efficient approach to handle future interruption and faults in power grid using costeffective and reliable infrastructure that can predict and provide real-time health monitoring indices for the Iraqi grid network with minimal power interruptions. After extensive testing, the prediction accuracy was about 96.1%. The Index Terms-Software-Defined Networks (SDN), neural networks (NN), smart grid, monitoring network, fault prediction, LoRa-IoT, sensors.

show abstract

Section: Related Work 151mentioning

confidence: 99%

A Smart Optimization of Fault Diagnosis in Electrical Grid Using Distributed Software-Defined IoT System

Mhdawi

Al-Raweshidy

2020

IEEE Systems Journal

View full text Add to dashboard Cite

show abstract

“…The intelligent methods of power system forecasting have been increased significantly over the last decades to reduce the error in the expected power system changes [5][6][7][8][9]. The Autoregressive Moving Average (ARMA) with the Artificial Neural Network (ANN) is accurate in predicting small power and depends only on the data [10]. Jie Shi has applied a hybrid forecasting model based on grey relational analysis and wind speed distribution features [3].…”

Section: Introductionmentioning

confidence: 99%

Short-Term Load Forecasting for Electrical Dispatcher of Baghdad City based on SVM-FA

Jaber¹,

Satar²,

Shalash³

2018

ijacsa

View full text Add to dashboard Cite

The improvement of load forecasting accuracy is an important issue in the scientific optimization of power systems. The availability of accurate statistical data and a suitable scientific method are necessary for a perfect prediction of future occurrences. This research deals with the use of a regression forecast model (Support Vector Machine, SVM) for the prediction of the vector data for electrical power loading and temperature in Baghdad city. The Firefly algorithm was used to optimize the parameters of the SVM to improve its prediction accuracy. The quantitative statistical performance evaluation measures (absolute proportional error (MAPE)) were used to evaluate the performance of the optimization methods. The results proved that the modification method was more accurate compared to the basic method and PSO-SVM.

show abstract

“…While retaining the recursive nature of RNNs, the problem of disappearance of gradients and gradient explosions in the RNN training process is solved [24][25][26][27]. A basic RNN network is shown in Figure 1a.…”

Section: Principles Of Predictionmentioning

confidence: 99%

Prediction Method for Power Transformer Running State Based on LSTM_DBN Network

Lin

Yan

et al. 2018

Energies

View full text Add to dashboard Cite

It is of great significance to accurately get the running state of power transformers and timely detect the existence of potential transformer faults. This paper presents a prediction method of transformer running state based on LSTM_DBN network. Firstly, based on the trend of gas concentration in transformer oil, a long short-term memory (LSTM) model is established to predict the future characteristic gas concentration. Then, the accuracy and influencing factors of the LSTM model are analyzed with examples. The deep belief network (DBN) model is used to establish the transformer operation using the information in the transformer fault case library. The accuracy of state classification is higher than the support vector machine (SVM) and back-propagation neural network (BPNN). Finally, combined with the actual transformer data collected from the State Grid Corporation of China, the LSTM_DBN model is used to predict the transformer state. The results show that the method has higher prediction accuracy and can analyze potential faults.

show abstract

Data-Based Line Trip Fault Prediction in Power Systems Using LSTM Networks and SVM

Cited by 195 publications

References 32 publications

A Smart Optimization of Fault Diagnosis in Electrical Grid Using Distributed Software-Defined IoT System

A Smart Optimization of Fault Diagnosis in Electrical Grid Using Distributed Software-Defined IoT System

Short-Term Load Forecasting for Electrical Dispatcher of Baghdad City based on SVM-FA

Prediction Method for Power Transformer Running State Based on LSTM_DBN Network

Contact Info

Product

Resources

About