On Deep Machine Learning Based Techniques for Electric Power Systems
Doktorsavhandling, 2022

This thesis provides deep machine learning-based solutions to real-time mitigation of power quality disturbances such as flicker, voltage dips, frequency deviations, harmonics, and interharmonics using active power filters (APF). In an APF the processing delays reduce the performance when the disturbance to be mitigated is tima varying. The the delays originate from software (response time delay) and hardware (reaction time delay). To reduce the response time delays of APFs, this thesis propose and investigate several different techniques. First a technique based on multiple synchronous reference frame (MSRF) and order-optimized exponential smoothing (ES) to decrease the settling time delay of lowpass filtering steps. To reduce the computational time, this method is implemented in a parallel processing using a graphics processing unit (GPU) to estimate the time-varying harmonics and interharmonics of currents. Furthermore, the MSRF and three machine learning-based solutions are developed to predict future values of voltage and current in electric power systems which can mitigate the effects of the response and reaction time delays of the APFs. In the first and second solutions, a Butterworth filter is used to lowpass filter the  dq  components, and linear prediction and long short-term memory (LSTM) are used to predict the filtered  dq  components. The third solution is an end-to-end ML-based method developed based on a combination of convolutional neural networks (CNN) and LSTM. The Simulink implementation of the proposed ML-based APF is carried out to compensate for the current waveform harmonics, voltage dips, and flicker in Simulink environment embedded AI computing system Jetson TX2.


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.

Voltage fluctuation


phase locked loop

Partial Discharges

Voltage Dip

Deep Learning

Reinforcement learning

Harmonics and Interharmonics

Cable faults

Active Power filter

Machine Learning

Chalmers University of Technology EC room
Opponent: Prof. Ali Abur


Ebrahim Balouji

Chalmers, Elektroteknik, Signalbehandling och medicinsk teknik

Locating high-impedance faults in DC microgrid clusters using support vector machines

Applied Energy,; Vol. 308(2022)

Artikel i vetenskaplig tidskrift

A LSTM-based Deep Learning Method with Application to Voltage Dip Classification


Paper i proceeding

Deep reinforcement learning based grid-forming inverter

Deep Learning Based Predictive Compensation of Flicker, Voltage Dips, Harmonics and Interharmonics in Electric Arc Furnaces

Classification of Partial Discharges Originating from Multi-level PWM Using Machine Learning

Exponential Smoothing of Multiple Reference Frame Components With GPUs for Real-Time Detection of Time-Varying Harmonics and Interharmonics of EAF Currents

Smart Grids will replace the traditional concept of electrical power systems to meet the growing needs of flexibility, availability, reliability, and quality of power supply. Economy and energy efficiency are the paradigms that are followed to utilize the available distributed energy resources (DER), which guarantees technical and environmentally friendly standards. The path to Smart Grids is complicated due to the heterogeneity increasing of electric devices, customers e.g., electric vehicle charging stations, and large industrial loads, leading to non-stationary disturbances that cause the significant malfunction of the electrical equipment. The term power quality (PQ) is used to describe these issues.

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.


Hållbar utveckling




Elektroteknik och elektronik



Doktorsavhandlingar vid Chalmers tekniska högskola. Ny serie: 5085



Chalmers University of Technology EC room


Opponent: Prof. Ali Abur

Mer information

Senast uppdaterat