FSFelix Ghislain Yem Souhe

Felix Ghislain Yem Souhe

*This is an algorithmically generated author record based on publicly available information.

Felix Ghislain Yem Souhe has a total of 12 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A novel combined deep learning-based technique for electricity theft detection in a smart grid

    by Etienne Mouckomey, Jacques Bikai, Camille Franklin Mbey, Felix Gislain Yem Souhe, Alexandre Teplaira Boum, Vinny Junior Foba Kakeu

    Energy theft represents a major challenge for electricity distribution companies worldwide and constitutes a key component of non-technical losses (NTLs), alongside faulty meters and billing inaccuracies. Despite the rise of artificial intelligence techniques for electricity theft detection, existing approaches exhibit limitations in classification and data analysis when applied to large-scale datasets. These shortcomings can reduce the effectiveness and precision of the theft detection systems. Therefore, this article proposes a bidirectional long short-term memory (Bi-LSTM) with the lookahead adaptive moment estimation (LADAM) optimizer and a support vector machine (SVM) with a bidirectional gated recurrent unit (Bi-GRU) for the detection of energy theft in a smart electricity grid to assess energy supplier companies. In this work, the proposed model is implemented on the State Grid Corporation of China (SGCC) dataset. In the proposed framework, the Bi-LSTM is used for feature extraction, while the LADAM optimizer is employed for feature selection and normalization. The refined feature set is subsequently fed into the SVM classifier to distinguish between theft and non-theft instances. The obtained findings highlight the superior efficiency of the proposed strategy compared with those in the literature, highlighting its potential for practical deployment in real-world smart grid systems.

  • Open Access

    Intelligent Energy Management of Hybrid Microgrid Using Deep Learning–Based Optimal Predictive Controller

    by Vinny Junior Foba Kakeu, Samuel Eke, Felix Ghislain Yem Souhe, Camille Franklin Mbey, Alexandre Teplaira Boum

    The increasing integration of renewable energy sources into hybrid microgrids has significantly improved the sustainability of power systems. However, the intermittent nature of solar and wind generation makes real‐time energy management a major challenge. Conventional energy management strategies often exhibit limited adaptability to rapidly changing operating conditions, resulting in inefficient power dispatch, increased fuel consumption, and accelerated battery degradation. To address these limitations, this study proposes an intelligent energy management framework based on the integration of a gated recurrent unit (GRU) deep learning model with model predictive control (MPC) for a grid‐connected hybrid microgrid supplying residential buildings in Maroua, Cameroon. The GRU model predicts load demand and renewable energy generation using historical and real‐time data, while the MPC optimally schedules power flows by considering system constraints, battery state of charge, renewable energy availability, and load requirements. The proposed GRU–MPC strategy was implemented and validated in MATLAB/Simulink using real operational data from the study area. Simulation results demonstrate that the proposed approach achieves a 30% reduction in fuel consumption, a 15% improvement in overall system efficiency, a 20% reduction in battery stress, and a forecasting accuracy of 99.8% compared with conventional energy management approaches. In addition, the proposed framework improves renewable energy utilization, maintains the battery state of charge around 65%, ensures continuous power supply, and reduces the operating energy cost to approximately 25 USD under the investigated scenarios. These results confirm that the GRU–MPC strategy provides an effective, robust, and scalable solution for intelligent energy management in modern hybrid renewable energy microgrids.


  • Open Access

    Anomaly Detection in a Smart Grid Using a Novel Hybrid Deep Learning Approach

    by Camille Franklin Mbey, Gabriel Ekemb, Felix Ghislain Yem Souhe, Vinny Junior Foba Kakeu, Alexandre Teplaira Boum

    The evolution of smart grids has enabled more efficient fulfilment of energy demands and addressed the limitations of conventional power systems through rapid detection of electrical and cyber anomalies. This study presents deep learning models based on LSTM, CNN and GRU architectures designed to ensure fast and reliable anomaly detection while maintaining a minimal false positive rate, thereby preventing unnecessary service interruptions. An LSTM‐CNN model is initially applied to anomaly datasets to address challenges associated with imbalanced classification. A hybrid LSTM‐GRU model is subsequently employed for feature extraction and identification of false data. Finally, these models are integrated into a combined LSTM‐GRU‐CNN framework, demonstrating superior anomaly detection performance across large‐scale datasets, with enhanced accuracy and execution speed. Experimental evaluation on a real‐world consumer database confirms the effectiveness of the proposed hybrid models. The LSTM‐GRU‐CNN hybrid architecture emerged as the best performer, achieving an excellent precision of 99.9%, an F1‐score of 94.83%, and an excellent MCC of 91.25%, and resulting in a total absence of false positives. This performance underscores the ability of optimised deep learning models to identify anomalies with high acuity while avoiding false triggers.

  • Open Access

    A Novel Predictive Control Approach Based on Hybrid Deep Learning Algorithm for Photovoltaic Power Forecasting in Microgrid

    by Vinny Junior Foba Kakeu, Felix Ghislain Yem Souhe, Samuel Eke, Camille Franklin Mbey, Alexandre Teplaira Boum

    With the increasing penetration of photovoltaic (PV) installations and their inherent intermittency due to weather variability, advanced energy control strategies have become essential for modern microgrid operation. In this context, reliable short‐term forecasting and optimal decision‐making are critical to ensure stable and efficient energy management. This work proposes a predictive energy management framework based on a parallel deep learning architecture combining long short‐term memory (LSTM) and gated recurrent unit (GRU) networks, whose hyperparameters are optimized using a multiobjective particle swarm optimization (MOPSO) algorithm for accurate PV power forecasting. The developed forecasting model is explicitly integrated into a model predictive control (MPC) scheme for real‐time microgrid energy management. In this MPC framework, the LSTM–GRU–MOPSO model provides multi‐step‐ahead PV power predictions that serve as key inputs to the optimization problem solved at each control interval (5 min). The MPC then determines optimal power dispatch decisions, including energy storage charging/discharging and grid interaction, while respecting system constraints and minimizing operational cost and power imbalance. The proposed approach is validated using a real PV dataset collected in Maroua, Far North Cameroon, under daily, weekly, and monthly prediction horizons. Results demonstrate that the hybrid forecasting model achieves high accuracy across daily, weekly, and monthly horizons, with R 2 values of 0.9984, 0.9988, and 0.9934, and RMSE values of 0.2096, 0.2034, and 0.3501, respectively. Comparative analysis shows that the proposed LSTM–GRU–MOPSO model outperforms conventional methods such as LSTM, GRU, support vector machine (SVM), and feedforward neural networks (FFNN), as well as hybrid architectures including LSTM–CNN and LSTM–RNN. The integration with MPC further enhances system reliability by enabling predictive, constraint‐aware, and adaptive microgrid energy management.

  • Open Access

    A Novel Hybrid Platform Based on Deep Learning for Fault Detection and Localization in a Smart Distribution Grid

    by Felix Ghislain Yem Souhe, Gabriel Ekemb, Camille Franklin Mbey, Vinny Junior Foba Kakeu, Alexandre Teplaira Boum

    The reliability of smart transmission systems critically depends on the rapid and accurate detection and localization of faults. However, existing approaches face inherent limitations; thus, traveling‐wave (TW) methods offer high localization accuracy but require stringent measurement conditions, while data‐driven models provide robustness but may suffer from reduced precision under certain scenarios. To address these challenges, this paper proposes a hybrid fault detection and localization methodology that combines physics‐based and deep learning approaches within a unified and modular framework. The proposed method integrates a TW analytical module and a one‐dimensional convolutional neural network (1D‐CNN) model, designed to exploit their complementary strengths. A key contribution of this work lies in the development of an adaptive decision fusion strategy, which combines the outputs of both modules based on confidence levels to produce a more accurate and reliable fault location estimate. The entire approach is implemented within a modular platform architecture, enabling clear separation between data acquisition, preprocessing, individual localization modules, and decision‐making. To ensure a rigorous evaluation, a large dataset of fault scenarios is generated using high‐fidelity electromagnetic transient simulations (PSCAD/EMTDC) of the Song Loulou–Logbaba 225‐kV transmission line in Cameroon, covering a wide range of fault types, locations, resistances, and operating conditions. The performance of each module and the hybrid approach is systematically assessed using standard detection and localization metrics. The results demonstrate that the TW module achieves high localization precision, while the 1D‐CNN model ensures robust detection and fault classification under varying conditions. The proposed hybrid approach significantly improves overall performance, achieving a 100% detection rate and reducing the average localization error to 0.017 km, outperforming individual methods. These findings confirm that the proposed hybrid methodology enhances both accuracy and robustness, making it a promising solution for advanced fault monitoring and protection in modern power grids.

  • Open Access

    A smart grid fault detection using neuro-fuzzy deep learning algorithm

    by Etienne Francois Mouckomey, Jacques Bikai, Camille Franklin Mbey, Alexandre Teplaira Boum, Felix Ghislain Yem Souhe, Vinny Junior Foba Kakeu

    This paper proposes a novel data analysis framework that integrates deep learning with a binary neuro-fuzzy algorithm to address the problem of fault localization in smart power grids. In the first stage, a long short-term memory (LSTM) network is employed to train data samples collected from smart meters. The resulting learned features are subsequently utilized by an adaptive neuro-fuzzy inference system (ANFIS) for accurate fault detection and classification. Through this intelligent hybrid approach, multi-phase faults can be efficiently identified using a limited amount of data. The proposed method distinguishes itself by its capacity to rapidly train and test large datasets while maintaining high computational efficiency. To evaluate the performance of the model, an advanced simulation of the IEEE 123-node test feeder is conducted. The robustness and effectiveness of the proposed framework are validated using multiple performance metrics, including precision, recall, accuracy, F1-score, computational complexity, and the ROC curve. The results demonstrate that the proposed deep learning–based model significantly outperforms existing approaches in the literature, achieving a fault detection and classification precision of 99.99%.


  • Open Access

    Electricity Theft Detection in a Smart Grid Using Hybrid Deep Learning‐Based Data Analysis Technique

    by Camille Franklin Mbey, Jacques Bikai, Felix Ghislain Yem Souhe, Vinny Junior Foba Kakeu, Alexandre Teplaira Boum

    With the popularization of smart meters around the world and the appearance of a large amount of electricity consumption data, the analysis of smart meter data is of major interest to electricity distributors around the world. Therefore, we proposed a hybrid artificial intelligence (AI) technique considering sudden changes of consumption in order to accurately predict fraudulent consumers in the smart network. Thus, the proposed hybrid model is based on the support vector machine (SVM) and a particle swarm optimization (PSO) algorithm to detect energy fraudsters in the network. In addition, a real smart grid dataset is used to verify the effectiveness of the proposed algorithm. Moreover, a smart calendar context is modeled showing the scheduling of energy consumption. The effectiveness of the proposed technique is evaluated using performance coefficients such as precision, recall, F1‐score, and area under ROC curve (AUC). We also perform sensitivity analysis through regression, variance, and variogram analysis. The results obtained give a performance of 98.9% in the detection of irregular consumers in the smart power grid. These results demonstrate the effectiveness of the proposed method compared to that in the literature.


  • Open Access

    A Novel Deep Learning‐Based Data Analysis Model for Solar Photovoltaic Power Generation and Electrical Consumption Forecasting in the Smart Power Grid

    by Camille Franklin Mbey, Felix Ghislain Yem Souhe, Vinny Junior Foba Kakeu, Alexandre Teplaira Boum

    With the installation of solar panels around the world and the permanent fluctuation of climatic factors, it is, therefore, important to provide the necessary energy in the electrical network in order to satisfy the electrical demand at all times for smart grid applications. This study first presents a comprehensive and comparative review of existing deep learning methods used for smart grid applications such as solar photovoltaic (PV) generation forecasting and power consumption forecasting. In this work, electrical consumption forecasting is long term and will consider smart meter data and socioeconomic and demographic data. Photovoltaic power generation forecasting is short term by considering climatic data such as solar irradiance, temperature, and humidity. Moreover, we have proposed a novel hybrid deep learning method based on multilayer perceptron (MLP), long short‐term memory (LSTM), and genetic algorithm (GA). We then simulated all the deep learning methods on a climate and electricity consumption dataset for the city of Douala. Electrical consumption data are collected from smart meters installed at consumers in Douala. Climate data are collected at the climate management center in the city of Douala. The results obtained show the outperformance of the proposed optimized method based on deep learning in the both electrical consumption and PV power generation forecasting and its superiority compared to basic methods of deep learning such as support vector machine (SVM), MLP, recurrent neural network (RNN), and random forest algorithm (RFA).


  • Open Access

    Fault detection and classification using deep learning method and neuro‐fuzzy algorithm in a smart distribution grid

    by Camille Franklin Mbey, Vinny Junior Foba Kakeu, Alexandre Teplaira Boum, Felix Ghislain Yem Souhe

    This article proposes a deep learning (DL) model made of Long Short Term Memory (LSTM) and Adaptive Neuro Fuzzy Inference System (ANFIS) to detect fault in smart distribution grid assisted by communication systems using smart meter data. In smart grid, data analysis for fault identification and detection is crucial for grid monitoring. Nowadays, there are several DL techniques developed for smart grid data analysis applications. To solve this problem, a novel data analysis model based on deep learning and Neuro‐fuzzy algorithm is developed for fault location in a smart power grid. First, the LSTM is applied for training the data samples extracted from the smart meters. Then, an ANFIS algorithm is implemented for fault detection and identification from the trained data. Finally, faults are located with the higher accuracy. With this intelligent method proposed, single‐phase, two‐phase and three‐phase faults can be identified using a restricted amount of data. The novelty of the proposed method compared with other methods is the capability of fast training and testing even with large amount of data. To verify the effectiveness of our methodology, an intelligent model of the IEEE 13‐node network is used. The effectiveness and robustness of the proposed model are evaluated using several parameters such as accuracy, precision‐recall, F1‐score, Receiver Operating Characteristic (ROC) curve and complexity time. The obtained results indicate that the proposed deep learning model outperforms existing deep learning methods in the literature for fault detection and classification with 99.99% accuracy.


  • Open Access

    Photovoltaic Power Generation Forecasting Using a Novel Hybrid Intelligent Model in Smart Grid

    by Alexandre Teplaira Boum, Vinny Junior Foba Kakeu, Camille Franklin Mbey, Felix Ghislain Yem Souhe

    The exponential growth of electrical demand and the integration of renewable energy sources (RES) brought new challenges in the traditional grid about energy quality. The transition from traditional grid to smart grid is the best solution which provides necessary tools and information and communication technologies (ICT) for service enhancement. In this study, variation of energy demand and some factors of atmospheric change are considered to forecast production of photovoltaic energy that can be adapted for evolution of consumption in smart grid. The contribution of this study concerns a novel optimized hybrid intelligent model made of the artificial neural network (ANN), support vector machine (SVM), and particle swarm optimization (PSO) implemented for long term photovoltaic (PV) power generation forecasting based on real data of consumption and climate factors of the city of Douala in Cameroon. The accuracy of this model is evaluated using the coefficients such as the mean square error (MSE), root mean square error (RMSE), mean absolute percentage error (MAPE), mean absolute error (MAE), and regression coefficient (R). Using this novel hybrid technique, the MSE, RMSE, MAPE, MAE, and R are 14.9721, 3.8693, 3.32, 0.867, and 0.9984, respectively. These obtained results show that the novel hybrid model outperforms other models in the literature and can be helpful for future renewable energy requirements. However, the convergence speed of the proposed approach can be affected due to the random variability of available data.