Deep Learning through LSTM Classification and Regression for Transmission Line Fault Detection, Diagnosis and Location in Large-Scale Multi-Machine Power Systems

Measurement ◽  
2021 ◽  
pp. 109330
Author(s):  
Soufiane Belagoune ◽  
Noureddine Bali ◽  
Azzeddine Bakdi ◽  
Boussaadia Baadji ◽  
Karim Atif
Keyword(s):  
Deep Learning ◽  
Fault Detection ◽  
Power Systems ◽  
Transmission Line ◽  
Large Scale ◽  
Classification And Regression

scholarly journals Predicting AC Optimal Power Flows: Combining Deep Learning and Lagrangian Dual Methods

2020 ◽  
Vol 34 (01) ◽  
pp. 630-637 ◽  
Author(s):  
Ferdinando Fioretto ◽  
Terrence W.K. Mak ◽  
Pascal Van Hentenryck
Keyword(s):  
Deep Learning ◽  
Power Systems ◽  
Power Flow ◽  
Optimal Power Flow ◽  
Large Scale ◽  
Renewable Energy Sources ◽  
Electrical Power ◽  
Practical Applications ◽  
Fundamental Building Block ◽  
Optimal Power

The Optimal Power Flow (OPF) problem is a fundamental building block for the optimization of electrical power systems. It is nonlinear and nonconvex and computes the generator setpoints for power and voltage, given a set of load demands. It is often solved repeatedly under various conditions, either in real-time or in large-scale studies. This need is further exacerbated by the increasing stochasticity of power systems due to renewable energy sources in front and behind the meter. To address these challenges, this paper presents a deep learning approach to the OPF. The learning model exploits the information available in the similar states of the system (which is commonly available in practical applications), as well as a dual Lagrangian method to satisfy the physical and engineering constraints present in the OPF. The proposed model is evaluated on a large collection of realistic medium-sized power systems. The experimental results show that its predictions are highly accurate with average errors as low as 0.2%. Additionally, the proposed approach is shown to improve the accuracy of the widely adopted linear DC approximation by at least two orders of magnitude.

Intrinsic time decomposition based differential protection with adaptive threshold for UPFC compensated transmission line

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Ajay Panday ◽  
Ram Dayal Patidar ◽  
Sandeep Biswal
Keyword(s):  
Fault Detection ◽  
Power Systems ◽  
Transmission Line ◽  
Power Flow ◽  
Unified Power Flow Controller ◽  
Distance Protection ◽  
Intrinsic Time ◽  
Time Decomposition ◽  
Power Flow Controller ◽  
Current Detection

Abstract In the presence of nonlinear response created by power electronics-based compensators, reliable fault detection and classification by distance protection relays is a major concern. The unified power flow controller (UPFC) has a dynamic characteristics that causes stability and protection issues. A intrinsic time decomposition (ITD) based strategy is proposed for addressing this issue. A differential energy based detection index computed using ITD and adaptive thresholding technique is employed such that unerring fault detection is achieved wherein faulty phases of a UPFC compensated transmission line are well pointed out. Various fault and non-fault cases considering critical power system conditions are analysed for power systems with varying configurations modelled using EMTDC/PSCAD. A comparison of the current detection method to recently proposed techniques reveals the benefits and feasibility of the presented detection strategy, which has been proved to be accurate and efficient.

scholarly journals Lightweight Neural Network for Component Recognition and Fault Detection of Large-Scale Transmission Line

2020 ◽  
Vol 768 ◽  
pp. 072070
Author(s):  
Guowei Zhao ◽  
Qiang Wang ◽  
Juan Zhang ◽  
Rui Zhao ◽  
Jielun Zhao ◽  
...  
Keyword(s):  
Neural Network ◽  
Fault Detection ◽  
Transmission Line ◽  
Large Scale ◽  
Component Recognition

scholarly journals Self-Regulating Line Fault Detection and Location in Transmission Lines

2020 ◽  
Vol 9 (1) ◽  
pp. 2540-2544
Keyword(s):  
Fault Detection ◽  
Power Systems ◽  
Transmission Line ◽  
Optical Fibers ◽  
Transmission Lines ◽  
Data Transmission ◽  
Power Transmission ◽  
Power Delivery ◽  
Climatic Fluctuations ◽  
Human Labor

In the present time scenario, where we use cables and optical fibers for data transmission along with power transmission, locating the flaws and faults in the transmission lines has become a necessity. Transmission lines are among the essential fragments of power systems. Being exposed to climatic fluctuations makes them the most vulnerable fragment. There may be numerous reasons that originate faults in the lines, such as temperature escalation, lightning strokes, even drizzles and fog because insulated carriers to wear out mechanically. It is indispensable to locate the fault point to restore the power at the earliest. Excellence in power delivery is achieved only if the time enforced in determining the flaw point in the line is limited. Accordingly, an authentic access is essential to figure out the literal location of the fault in the transmission line. This project introduces an accurate and adequate approach for determining the location of the line fault. It illustrates how the use of GSM and GPS along with ARDUINO UNO can relatively reduce the human labor and increase the accuracy whilst downsizing the obligatory time.

Sign in / Sign up

Export Citation Format

Share Document