On Deep Machine Learning Based Techniques for Electric Power Systems
Doctoral thesis, 2022
In another study, we propose Deep Deterministic Policy Gradient (DDPG), a reinforcement learning (RL) method to replace the controller loops and estimation blocks such as PID, MSRF, and lowpass filters in grid-forming inverters. In a conventional approach it is well recognized that the controller tuning in the differen loops are difficult as the tuning of one loop influence the performance in other parts due to interdependencies.
In DDPG the control policy is derived by optimizing a reward function which measure the performance in a data-driven fashion based on extensive experiments of the inverter in a simulation environment. Compared to a PID-based control architecture, the DDPG derived control policy leads to a solution where the response and reaction time delays are decreased by a factor of five in the investigated example.
Classification of voltage dips originating from cable faults is another topic addressed in this thesis work. The Root Mean Square (RMS) of the voltage dips is proposed as preprocessing step to ease the feature learning for the developed LSTM based classifier. Once a cable faults occur, it need to be located and repaired/replaced in order to restore the grid operation. Due to the high importance of stability in the power generation of renewable energy sources, we aim to locate high impedance cable faults in DC microgrid clusters which is a challenging case among different types of faults. The developed Support Vector Machine (SVM) algorithm process the maximum amplitude and di/dt of the current waveform of the fault as features, and the localization task is carried out with 95 % accuracy.
Two ML-based solutions together with a two-step feature engineering method are proposed to classify Partial Discharges (PD) originating from pulse width modulation (PWM) excitation in high voltage power electronic devices. As a first step, maximum amplitude, time of occurrence, area under PD curve, and time distance of each PD are extracted as features of interest. The extracted features are concatenated to form patterns for the ML algorithms as a second step. The suggested feature classification using the proposed ML algorithms resulted in 95.5 % and 98.3 % accuracy on a test data set using ensemble bagged decision trees and LSTM networks.
Deep Learning
Cable faults
phase locked loop
Flicker
Harmonics and Interharmonics
Reinforcement learning
Voltage Dip
Active Power filter
Machine Learning
Voltage fluctuation
Partial Discharges
Author
Ebrahim Balouji
Chalmers, Electrical Engineering, Signal Processing and Biomedical Engineering
Locating high-impedance faults in DC microgrid clusters using support vector machines
Applied Energy,;Vol. 308(2022)
Journal article
A LSTM-based Deep Learning Method with Application to Voltage Dip Classification
2018 18TH INTERNATIONAL CONFERENCE ON HARMONICS AND QUALITY OF POWER (ICHQP),;(2018)
Paper in proceeding
Deep reinforcement learning based grid-forming inverter
Deep Learning Based Predictive Compensation of Flicker, Voltage Dips, Harmonics and Interharmonics in Electric Arc Furnaces
IEEE Transactions on Industry Applications,;Vol. In Press(2022)
Journal article
Classification of Partial Discharges Originating from Multi-level PWM Using Machine Learning
IEEE Transactions on Dielectrics and Electrical Insulation,;Vol. In Press(2022)
Journal article
Deep Learning Based Harmonics and Interharmonics Pre-Detection Designed for Compensating Significantly Time-varying EAF Currents
2019 IEEE Industry Applications Society Annual Meeting, IAS 2019,;(2019)
Paper in proceeding
PQ is an essential topic in the utility world as it impacts both the producer and consumer of electricity and the grid operator. All these new entities create many voltages and PQ issues that throw traditional grid management out of gear and call for large-scale automatization in surveillance and mitigation.
This thesis provides artificial intelligence (AI) and machine learning-based solutions to analyze the PQ disturbances in electric power systems. Furthermore, it gives an AI-based control algorithm that automatically recognizes, estimates, and mitigates the PQ disturbances. Also, once these disturbances occur, they need to be located, which is time-consuming and requires manual effort and human resources. Thus this thesis aimed to develop ML-based solutions to accurately find the location of the disturbances by analyzing the recorded data from the electric power system. Finally, this thesis aimed to develop AI-based solutions towards root cause identification and predictive maintenance of electric devices connected to electric power systems.
Driving Forces
Sustainable development
Areas of Advance
Energy
Subject Categories
Electrical Engineering, Electronic Engineering, Information Engineering
Other Electrical Engineering, Electronic Engineering, Information Engineering
ISBN
978-91-7905-619-3
Doktorsavhandlingar vid Chalmers tekniska högskola. Ny serie: 5085
Publisher
Chalmers