Pascal Dieu Seul Assala
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Pascal Dieu Seul Assala has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
Haoyong Chen
School of Electric Power, South China University of Technology, Guangzhou, China
5 shared publicationsYongzhi Cai
School of Electric Power, South China University of Technology, Guangzhou, China
3 shared publicationsTianyao Ji
School of Electric Power, South China University of Technology, Guangzhou, 510641 China
2 shared publications- Haoyong Chen
School of Electric Power Engineering, South China University of Technology, Guangzhou, China
1 shared publication Lihao Wu
1 shared publication- Luc Vivien Assiene Mouodo
Department of Electrical Engineering, Higher Normal School of Technical Education (ENSET), University of Douala, Douala P.O. Box 1872, Cameroon
1 shared publication
Latest Publications
- Open Access
- 6 July 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (13) , 6756
Experimental Approach to Intelligent Estimation of the State-of-Charge (SoC) of Batteries: Case of Electric Vehicles
The development of the electric vehicle sector increasingly requires optimal intelligent and embedded energy management. Electric vehicles are now positioning themselves as a strategic alternative to traditional fuel vehicles. This article therefore highlights the design of an embedded system capable of evaluating and transmitting in real time the state-of-charge (SoC) of an electric vehicle battery to a cloud platform, while optimizing energy consumption and data reliability. The methodological approach proposes an experimental study involving the development of two deep learning models, LSTM (Long Short-Term Memory) and GRU (Gated Recurrent Unit), in the MATLAB 2024.b environment, associated with the design of an embedded prototype for data collection and transmission via Arduino IoT Cloud. Then, a comparative analysis of the models’ performances is also carried out. The results obtained show that the GRU model offers the best performance, with an accuracy of 83.6%, an MSE of 0.0715, and an RMSE of 0.2589, thus validating the relevance of the proposed approach for the intelligent estimation of the state-of-charge in a real application context.
- 6 July 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (13) , 6756
Open AccessExperimental Approach to Intelligent Estimation of the State-of-Charge (SoC) of Batteries: Case of Electric Vehicles
The development of the electric vehicle sector increasingly requires optimal intelligent and embedded energy management. Electric vehicles are now positioning themselves as a strategic alternative to traditional fuel vehicles. This article therefore highlights the design of an embedded system capable of evaluating and transmitting in real time the state-of-charge (SoC) of an electric vehicle battery to a cloud platform, while optimizing energy consumption and data reliability. The methodological approach proposes an experimental study involving the development of two deep learning models, LSTM (Long Short-Term Memory) and GRU (Gated Recurrent Unit), in the MATLAB 2024.b environment, associated with the design of an embedded prototype for data collection and transmission via Arduino IoT Cloud. Then, a comparative analysis of the models’ performances is also carried out. The results obtained show that the GRU model offers the best performance, with an accuracy of 83.6%, an MSE of 0.0715, and an RMSE of 0.2589, thus validating the relevance of the proposed approach for the intelligent estimation of the state-of-charge in a real application context.
- 1 October 2018
- Published by Elsevier in Electric Power Systems Research
- Vol. 163, 572-580
Residual life assessment of 110 kV XLPE cable
- 1 October 2018
- Published by Elsevier in Electric Power Systems Research
- Vol. 163, 572-580
Residual life assessment of 110 kV XLPE cable
- 22 January 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 12 (5) , 1726-1735
Intelligent Transient Overvoltages Location in Distribution Systems Using Wavelet Packet Decomposition and General Regression Neural Networks
Overvoltages are the main causes of damages and accidents in electric power grids. The traditional approach is to install some static protection devices that are passive and cannot identify the overvoltage types or locate where the overvoltage event occurs. In recent years, with the development of smart grids, some online overvoltage monitoring systems have been developed. However, the approaches to data processing still need further development. A novel technique for identification and location of overvoltages in power distribution systems is proposed, which uses capacitor bank energization overvoltages (CBOVs) and ground fault temporary overvoltages (TOVs) as the study cases. The wavelet packet decomposition (WPD) theory is used for frequency band decomposition, and a general regression neural network (GRNN) is used in identification and location. Simulation results based on real-world power distribution systems show that the method is accurate and fast.
- 22 January 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 12 (5) , 1726-1735
Intelligent Transient Overvoltages Location in Distribution Systems Using Wavelet Packet Decomposition and General Regression Neural Networks
Overvoltages are the main causes of damages and accidents in electric power grids. The traditional approach is to install some static protection devices that are passive and cannot identify the overvoltage types or locate where the overvoltage event occurs. In recent years, with the development of smart grids, some online overvoltage monitoring systems have been developed. However, the approaches to data processing still need further development. A novel technique for identification and location of overvoltages in power distribution systems is proposed, which uses capacitor bank energization overvoltages (CBOVs) and ground fault temporary overvoltages (TOVs) as the study cases. The wavelet packet decomposition (WPD) theory is used for frequency band decomposition, and a general regression neural network (GRNN) is used in identification and location. Simulation results based on real-world power distribution systems show that the method is accurate and fast.
- 1 December 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21574839,p. 1-6
Synchronization effects on power transients in distribution networks with grid connected photovoltaic generation
The high level penetration of distributed generation in power distribution systems has not only improved the power quality but also generated other challenges. The challenges are related to the interconnection of different power generation units and the need to keep the power delivered to the end user at the standards levels. Different controllers are implemented to simplify interconnection of a distributed generation with conventional power grids. The control process is mainly about keeping the voltage amplitudes and angles of the distributed generation unit and the power distribution network in a loop to detect the right instant to operate. In the present paper, a deep analysis of the effect of voltage synchronization in the transients behavior of a distribution network with a connected photovoltaic power generation system is conducted. The currents delivered by the two power sources are evaluated at different voltage angles between the two sources during the interconnection. The influence of voltage synchronization is also examined for transients overvoltages from capacitor bank operation. The workflow in this paper provides an insight to the phenomena and useful details to consider when designing a controller for interconnection of a photovoltaic power generation to a conventional power distribution network.
- 1 December 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21574839,p. 1-6
Synchronization effects on power transients in distribution networks with grid connected photovoltaic generation
The high level penetration of distributed generation in power distribution systems has not only improved the power quality but also generated other challenges. The challenges are related to the interconnection of different power generation units and the need to keep the power delivered to the end user at the standards levels. Different controllers are implemented to simplify interconnection of a distributed generation with conventional power grids. The control process is mainly about keeping the voltage amplitudes and angles of the distributed generation unit and the power distribution network in a loop to detect the right instant to operate. In the present paper, a deep analysis of the effect of voltage synchronization in the transients behavior of a distribution network with a connected photovoltaic power generation system is conducted. The currents delivered by the two power sources are evaluated at different voltage angles between the two sources during the interconnection. The influence of voltage synchronization is also examined for transients overvoltages from capacitor bank operation. The workflow in this paper provides an insight to the phenomena and useful details to consider when designing a controller for interconnection of a photovoltaic power generation to a conventional power distribution network.
- 1 December 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
State estimation of synchronous generators under model parameter uncertainty based on set membership filter
Recently, the phasor measurement units (PMUs) are being rapidly adopted worldwide. Because the dynamics of synchronous generator are closely related to the stability of power system, there is growing concern about estimating the states of synchronous generators when disturbances occur in power system. In this paper, we study the state estimation of synchronous generators in the presence of model parameter uncertainty. Assuming that the process model parameters are uncertainty but bounded, the set membership filter (SMF) based on ellipsoid algorithm is employed to estimate the states of synchronous generators. Comparing with EKF and CKF, the simulations prove that the SMF are more robust and provide better results in the presence of model parameter uncertainty.
- 1 December 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
State estimation of synchronous generators under model parameter uncertainty based on set membership filter
Recently, the phasor measurement units (PMUs) are being rapidly adopted worldwide. Because the dynamics of synchronous generator are closely related to the stability of power system, there is growing concern about estimating the states of synchronous generators when disturbances occur in power system. In this paper, we study the state estimation of synchronous generators in the presence of model parameter uncertainty. Assuming that the process model parameters are uncertainty but bounded, the set membership filter (SMF) based on ellipsoid algorithm is employed to estimate the states of synchronous generators. Comparing with EKF and CKF, the simulations prove that the SMF are more robust and provide better results in the presence of model parameter uncertainty.
- 1 December 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21574839,p. 1-5
Guaranteed state estimation of synchronous generators based on DC programming
Because the dynamics of synchronous generator relates to the stability of power system closely, there is growing concern about estimating the status of synchronous generator when disturbances occur in power system. This paper employs Set Membership Filter based on DC Programming (SMFDC) for estimating the states of synchronous generator, by using local measurements of each generation unit. The estimator only assumes the process and measurement noises are bounded without any other statistics assumptions. By transforming the estimation model to Deference of Convex (DC) function form, the problem of bounding the linearization errors can be convert to solve DC programming, which is different from the interval analysis method in ESMF. To compare with ESMF [20], the estimation results of SMFDC are better and the estimator makes a great improvement in real-time property.
- 1 December 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21574839,p. 1-5
Guaranteed state estimation of synchronous generators based on DC programming
Because the dynamics of synchronous generator relates to the stability of power system closely, there is growing concern about estimating the status of synchronous generator when disturbances occur in power system. This paper employs Set Membership Filter based on DC Programming (SMFDC) for estimating the states of synchronous generator, by using local measurements of each generation unit. The estimator only assumes the process and measurement noises are bounded without any other statistics assumptions. By transforming the estimation model to Deference of Convex (DC) function form, the problem of bounding the linearization errors can be convert to solve DC programming, which is different from the interval analysis method in ESMF. To compare with ESMF [20], the estimation results of SMFDC are better and the estimator makes a great improvement in real-time property.
- 1 January 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Power system overvoltage detection based on a morphological filtering algorithm
The fast development of electronics and the use of diverse electronic based materials have brought with themselves many new aspects of challenges to be faced by electric power providers. Overvoltages as the main cause of damages and accidents in power distribution networks represent the important aspect that is being studied in order to provide better energy to consumers giving the double advantage of preserving and reducing accidents in both the energy user and the provider sides. The work presented in this paper is one step of the overvoltage detection system to be designed by the authors. Several cases of overvoltages have been studied and simulated on ATP-EMTP software to help adjusting choices of the most suitable morphological filtering algorithm to perform the detection part of the future online overvoltages monitoring system. The authors have focussed on the overvoltage time and frequency research results to make the assertions on overvoltages waveforms processing based on mathematical morphology theory. Experiments related to different overvoltages types and amplitudes have helped to parameterize the most suitable detection algorithm. Simulation results done with MATLAB show the efficiency of the morphological gradient detection algorithm specialized for power system overvoltage detection.
- 1 January 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Power system overvoltage detection based on a morphological filtering algorithm
The fast development of electronics and the use of diverse electronic based materials have brought with themselves many new aspects of challenges to be faced by electric power providers. Overvoltages as the main cause of damages and accidents in power distribution networks represent the important aspect that is being studied in order to provide better energy to consumers giving the double advantage of preserving and reducing accidents in both the energy user and the provider sides. The work presented in this paper is one step of the overvoltage detection system to be designed by the authors. Several cases of overvoltages have been studied and simulated on ATP-EMTP software to help adjusting choices of the most suitable morphological filtering algorithm to perform the detection part of the future online overvoltages monitoring system. The authors have focussed on the overvoltage time and frequency research results to make the assertions on overvoltages waveforms processing based on mathematical morphology theory. Experiments related to different overvoltages types and amplitudes have helped to parameterize the most suitable detection algorithm. Simulation results done with MATLAB show the efficiency of the morphological gradient detection algorithm specialized for power system overvoltage detection.
- 1 January 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 19325517,p. 1-5
Power system overvoltage identification using feedforward neural network
The main causes of electrical accidents in power distribution networks are internal and external overvoltages. In this paper, the authors introduce an intelligent way of identifying internal and external overvoltages based on time domain studies of their waveforms. Seven parameters are extracted from the signal to build a sample vector as entry data for every sampled overvoltage to be identified. A neural network based on feedforward multilayer perceptron topology is used for the identification and classification. The overvoltage samples used in this work are obtained from ATP-EMTP software and the data extraction is performed with a script written in Matlab. A variety of power system overvoltages have been used to test the validity of the proposed method and we obtained an result of 98.82% of positive identification and classification. Results prove that, the feedforward multilayer perceptron is a suitable candidate in power system overvoltage identification and classification.
- 1 January 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 19325517,p. 1-5
Power system overvoltage identification using feedforward neural network
The main causes of electrical accidents in power distribution networks are internal and external overvoltages. In this paper, the authors introduce an intelligent way of identifying internal and external overvoltages based on time domain studies of their waveforms. Seven parameters are extracted from the signal to build a sample vector as entry data for every sampled overvoltage to be identified. A neural network based on feedforward multilayer perceptron topology is used for the identification and classification. The overvoltage samples used in this work are obtained from ATP-EMTP software and the data extraction is performed with a script written in Matlab. A variety of power system overvoltages have been used to test the validity of the proposed method and we obtained an result of 98.82% of positive identification and classification. Results prove that, the feedforward multilayer perceptron is a suitable candidate in power system overvoltage identification and classification.