Publications Scientifiques

Permanent URI for this communityhttps://dspace.univ-boumerdes.dz/handle/123456789/10

Browse

Author: search.filters.author.Kheldoun, Aissa

Search Results

Now showing 1 - 10 of 47
  • Thumbnail Image
    Item
    Seasonal quantile forecasting of solar photovoltaic power using Q-CNN-GRU
    (Nature Research, 2025) Ait Mouloud, Louiza; Kheldoun, Aissa; Oussidhoum, Samira; Alharbi, Hisham; Alotaibi, Saud; Alzahrani, Thabet
    Accurately predicting solar power is essential for ensuring electric grid reliability and integrating renewable energy sources. This paper presents a novel approach to probabilistic solar power forecasting by combining Convolutional Neural Networks (CNN) with Gated Recurrent Units (GRU) into a hybrid Quantile-CNN-GRU model. The proposed model generates intra-day probabilistic quantile forecasts and is rigorously evaluated using datasets from geographically and climatically diverse regions and hemispheres: the Netherlands (temperate maritime climate), Alice Springs (arid desert climate), and Hebei (humid subtropical climate). These datasets cover varied temporal horizons (1-hour, 6-hour, 12-hour, and 24-hour predictions) and seasonal conditions (summer, fall, spring, and winter), highlighting the model’s adaptability to different scenarios. The performance of the proposed Quantile-CNN-GRU model is benchmarked against state-of-the-art deep learning models, including standalone quantile-based architectures such as Quantile-GRU and Quantile-Long Short Term Memory (LSTM). A comprehensive evaluation framework is applied, employing probabilistic tools like the Continuous Ranked Probability Score (CRPS) for assessing forecast reliability, sharpness, and reliability diagrams with consistency bars to evaluate the calibration of the predictions. Results demonstrate that the proposed Quantile-CNN-GRU model consistently outperforms its counterparts in terms of CRPS, across varying forecast horizons and seasonal conditions. To further enhance performance, a multivariate case study incorporating exogenous inputs, specifically Numerical Weather Prediction (NWP) data, is conducted. Through sensitivity analysis, the influence of these additional inputs on forecast horizons and seasonal variability is systematically explored. The study reveals that integrating NWP data significantly improves the model’s predictive skill, particularly for longer forecast horizons and during transitional seasons like spring and fall, when solar variability is higher.
  • No Thumbnail Available
    Item
    Optimized fractional order Takagi-Sugeno Fuzzy-PID power system stabilizer: An enhanced dung beetle optimization approach
    (Elsevier, 2025) Hattabi, Intissar; Kheldoun, Aissa; Bradai, Rafik; Belmadani, Hamza
    This paper introduces a novel Fractional Order Takagi-Sugeno Fuzzy-PID (FO-TSF-PID) controller, optimized using an enhanced Dung Beetle Optimization (EDBO) algorithm, to improve the damping of low-frequency oscillations in power systems. The controller's design involves simultaneous optimization of membership functions (MFs) and gains, enhancing performance, particularly under three-phase fault conditions. The optimization process, executed through the EDBO algorithm, is both flexible and straightforward to implement. The FO-TSF-PID controller was tested on a two-area power system subjected to three symmetrical faults. Performance evaluations demonstrated the controller's superiority over the standard Fractional Order PID (FOFPID) controller, achieving significant improvements in inter-area and local-area eigenvalues. Specifically, inter-area improvements were 87.08 % with PSO, 83.86 % with EO, 81.29 % with DBO, and 78.89 % with EDBO, while local-area improvements were 71.01 % with PSO, 70.52 % with EO, 65.73 % with DBO, and 64.32 % with EDBO. Comparative analysis against traditional controllers such as Lead-Lag Power System Stabilizer (PSS), Proportional-Integral-Derivative (PID), and Fractional Order PID (FOPID) consistently showed the FO-TSF-PID controller's enhanced stability and robustness. Further comparisons revealed that the EDBO-optimized FO-TSF-PID controller achieved 99.94 %, 99.93 %, and 99.95 % enhancements compared to those optimized using PSO, EO, and DBO, respectively. The results indicate that the EDBO-optimized FO-TSF-PID controller excels in reducing settling time, minimizing overshoot, and improving steady-state error, thus proving its efficacy in stabilizing power systems
  • Thumbnail Image
    Item
    Optimum sizing of hybrid sustainable and renewable energy systems using a modified harris hawks optimizer
    (Elsevier, 2025) Sifou, Djamel Eddine; Kheldoun, Aissa; Chaib, Ahmed; Belmadani, Hamza; Alharbi, Hisham; Alharbi, Saleh S.; Agajie, Takele Ferede; Ghoneim, Sherif S.M.
    To boost the use of renewable energy sources while maintaining reliability and affordability, Multi-source renewable and sustainable energy systems must be optimally sized. This research introduces a stand-alone metaheuristic algorithm for designing a hybrid sustainable and renewable energy system combining Wind turbine, PV and battery system. The main goal is to lower the overall present-day system's cost at the same time considering the indicator of reliability, which is the loss of power supply probability (LPSP), as a constraint. The developed algorithm resulted from enhancing the recent Harris Hawks Optimizer (HHO). The modified version incorporates a vector that saves the best three solutions and opposition learning to enhance the population diversity and assist the algorithm in jumping out of local optima regions. Three scenarios are presented, the first is modeled by PV/Bat the second one is modeled by WT/Bat while the third one consists of PV/WT/Bat. The studied project is located in Sidi Khattab, Relizane province, Algeria. The results demonstrate that the MHHO outperforms a range of well-known algorithms, among which one can cite the original HHO, Krill Optimization Algorithm (KOA), Red Squirrel Algorithm (RSA), Modified Coati Optimization Algorithm (MCOA), and Generalized Oppositional-based Social Spider Algorithm (GOOSE). Compared to the other algorithms, MHHO demonstrated superior performance in all proposed configuration settings
  • No Thumbnail Available
    Item
    Enhanced power system stabilizer tuning using marine predator algorithm with comparative analysis and real time validation
    (Nature Portfolio, 2024) Hattabi, Intissar; Kheldoun, Aissa; Bradai, Rafik; Khettab, Soufian; Sabo, Aliyu; Belkhier, Youcef; Khosravi, Nima; Oubelaid, Adel
    This study concentrates on the implementation of Marine Predator Algorithm (MPA) scheme for tuning of a power system stabilizer’s (PSS’s) parameters to damp the low-frequency oscillations in a power system. To this, the single machine infinite bus system (SMIB), the Western System Coordinating Council (WSCC) and the New England 10 machine 39-bus power system are utilized for testing and comparing different metaheuristic algorithms using different fitness functions. Optimal PSS parameters of SMIB test system are validated using CU-SLRT Std, a real-time digital simulator. The comparative studies demonstrate that the MPA optimized PSS yields improvements of up to 98.62% in the Particle Swarm Optimization (PSO) at 69.42%, Whale Optimization Algorithm (WOA) at 71.79%, Flower Pollination Algorithm (FPA) at 72.39%, African vulture optimization algorithm (AVOA) at 78.04%, Wild Horse Optimization (WHO) algorithm at 68.57% under various operating scenarios. The superiority of the MPA optimized PSS has been validated using Hardware-in-the-loop implementation for the SMIB test system.
  • No Thumbnail Available
    Item
    Performance evaluation of PUC7‐based multifunction single‐phase solar active filter in real outdoor environments: Experimental insights
    (John Wiley and Sons Inc, 2024) Khettab, Soufiane; Kheldoun, Aissa; Bradai, Rafik; Oubelaid, Adel; Kumar, Sandeep; Khosravi, Nima
    This paper presents a novel architecture to enhance the performance of grid-connected photovoltaic (PV) systems through the introduction of several key novelties. Firstly, a packed U-cell seven-level (PUC7)-based single-phase solar active filter is implemented, offering a comprehensive solution for harmonics mitigation, reactive power compensation, and efficient power extraction from the PV source, while facilitating the injection of real power into the grid. Secondly, the p-q power injection algorithm is modified to accommodate the extraction of solar power from the PV generator to the grid, simultaneously addressing the need for harmonic current injection to improve power quality. This modification ensures dynamic performance by extracting reference current with harmonic content and solar power information, thereby enhancing the system's overall efficiency. Lastly, the proposed architecture undergoes real outdoor testing, validating its performance in various key aspects including maximum power tracking, reduction of total harmonic distortion in comparison with previous work, operation at unity power factor, and testing the effective operation of the multifunction feature. These contributions collectively demonstrate the effectiveness of the proposed system in enhancing power injection quality and reactive power compensation under real outdoor conditions of PV systems connected to the grid.
  • No Thumbnail Available
    Item
    Seasonal Forecasting of Global Horizontal Irradiance for Grid-Connected PV Plants: A Combined CNN-BiGRU Approach
    (Institute of Electrical and Electronics Engineers, 2024) Ait Mouloud, Louiza; Kheldoun, Aissa; Merabet, Oussama; Belmadani, Hamza; Bisht, Singh Vimal; Oubelaid, Adel; Bajaj, Mohit
    The quest for environmental sustainability in power systems necessitates the incorporation of renewable energy sources into the grid infrastructure. Among these renewable sources, solar energy has risen to prominence due to its widespread availability. However, the variable nature of solar irradiance poses challenges in operational and control aspects of its integration. A potential solution lies in predictions of global horizontal irradiance (GHI). This study introduces an ensemble deep learning-based forecasting approach, leveraging a Convolutional Neural Network and Bidirectional Gated Recurrent Unit (CNN-BiGRU). The efficacy of this approach is evaluated against three ensemble models: The Convolutional Neural Network Bidirectional Long Short Term Memory (CNN-BiLSTM), Convolutional Neural Network Gated Recurrent Unit (CNN-GRU), the Convolutional Neural Network Long Short Term Memory (CNN-LSTM). The comparative analysis is centered on seasonal GHI forecasting in Alice Springs, Australia, with a 1-hour time horizon. Four metrics are employed to gauge the accuracy of the models: coefficient of determination (R2), mean absolute error (MAE), normalised root mean square error (nRMSE), and root mean square error (RMSE). The findings reveal that the proposed ensemble bidirectional model outperforms its counterparts in all seasons. Specifically, in terms of seasonal forecasting, the CNN-BiGRU model achieves a maximum nRMSE of 0.0955, indicating its superior performance.
  • No Thumbnail Available
    Item
    A Taguchi method-based optimization algorithm for the analysis of the wind driven-self-excited induction generator
    (Institute of Advanced Engineering and Science (IAES), 2024) Boukenoui, Rachid; Bradai, Rafik; Kheldoun, Aissa
    This paper investigates the use of a new global optimization algorithm that is based on Taguchi method to determine the performance parameters of self-excited induction generator being driven by variable speed wind. This analysis is based on solving equations obtained from the per-phase equivalent circuit of the induction generator. The equations have two unknowns namely the frequency and the magnetizing reactance. Both unknown are strongly dependent on the wind turbine speed, the capacity of the excitation, the load being connected at the terminals of the stator and eventually the per-phase equivalent circuit parameters. The resulting equations are nonlinear and subsequently to solve them one can employ either gradient-based algorithms or heuristic algorithms. This paper uses a new heuristic algorithm based on the Taguchi method which, in addition to its global research capability, offers superior characteristics in terms of accuracy and ease of implementation. A comparison with recently published optimization methods is carried out to show its performances in terms of accuracy and ease of implementation. The MATLAB software will be used to perform this analysis on a machine of 0.75 kW while some will be validated experimentally to confirm the aforementioned benefits.
  • No Thumbnail Available
    Item
    Guided Seagull Optimization for Improved PV MPPT in Partial Shading
    (Institute of Electrical and Electronics Engineers Inc, 2023) Belmadani, Hamza; Merabet, Oussama; Obelaid, Adel; Kheldoun, Aissa; Mohit, Bajaj; Ansari, Md Fahim; Bradai, Rafik
    Based on the Seagull Optimization approach, this paper proposes a completely new, rapid Maximum Power Point tracking method. After adding opposition learning and adjusting the convergence factor to the initial version, the intended algorithm - dubbed The Guided Seagull Optimizer (GSO) - was produced. Essentially, the goal of the new technique is to increase convergence speed while maintaining a reasonable global search capability. The GSO algorithm was tested on a stand-alone photovoltaic system subjected to complex multi-peak partial shadowing patterns. Overall, the findings reveal that the technique outperforms typical SOA and PSO algorithms when it comes to of convergence time, efficiency, and adaptability.
  • No Thumbnail Available
    Item
    Optimal coordination of directional overcurrent relays in complex networks using the Elite marine predators algorithm
    (Elsevier, 2023) Merabet, Oussama; Bouchahdane, Mohamed; Belmadani, Hamza; Kheldoun, Aissa; Eltom, Ahmed
    The integration of renewable energy sources in the distribution network (DN) has had a significant influence by reducing power loss and enhancing network dependability. Aside from that, the protection system has met coordination issues as a result of bidirectional power flow and variations in fault levels. Therefore, an optimal coordination strategy is required to deal with relays coordination problem. The coordination problem of the directional overcurrent relays (DOCRs) is a restricted optimization issue that involves determining appropriate time dial settings (TDS) and plug setting (PS) to reduce relays operating time. Currently, a various nontraditional optimization strategies have been presented to overcome this challenge. In this paper, a modified version of the marine predators algorithm (MPA) referred to as Elite marine predator (EMPA) is developed for the optimal coordination of DOCRs. Therefore, the EMPA method is used to find out the optimal settings for the DOCRs problem. The suggested algorithm's performance is evaluated using standard test systems, including 3-bus, 8-bus, 9-bus, and 15-bus. The findings are compared with the traditional MPA and with other recent optimization methods presented in the literature to prove the efficiency and superiority of the proposed EMPA in reducing relay operation time for optimal DOCRs coordination.
  • No Thumbnail Available
    Item
    A New Fast and Efficient MPPT Algorithm for Partially Shaded PV Systems Using a Hyperbolic Slime Mould Algorithm
    (Wiley-Hindawi, 2024) Belmadani, Hamza; Bradai, Rafik; Kheldoun, Aissa; Mohammed, Karam Khairullah; Mekhilef, Saad; Belkhier, Youcef; Oubelaid, Adel
    The design of new efficient maximum power point tracking (MPPT) techniques has become extremely important due to the rapid expansion of photovoltaic (PV) systems. Because under shading conditions the characteristics of PV devices become multimodal having several power peaks, traditional MPPT techniques provide crappy performance. In turn, metaheuristic algorithms have become massively employed as a typical substitute in maximum power point tracking. In this work, a new optimizer, which was named the hyperbolic slime mould algorithm (HSMA), is designed to be employed as an efficient MPPT algorithm. The hyperbolic tangent function is incorporated into the optimizer framework equations to scale down large perturbations in the tracking stage and boost its convergence trend. Moreover, to provide a strong exploration capability, a new mechanism has been developed in such a way the search process is carried out inside the best two power peak regions along the initial iterations. This region inspection mechanism is the prime hallmark of the designed optimizer in avoiding local power peaks and excessive global search operations. The developed algorithm was examined through diverse complicated partial shading conditions to challenge its global and local search abilities. A comparative analysis was carried out against the well-regarded PSO, GWO, and the standard slime mould algorithm. In overall, the designed optimizer defeated its contenders in all aspects offering higher efficiency, superior robustness, faster convergence, and fewer fluctuations to the operating point. An experimental setup that consists of the DSpace microcontroller and a PV emulator was employed to validate the algorithm overall performance. The recorded outcomes outline that the developed optimizer can achieve a tracking time of 0.6 seconds and 0.86 seconds on average, with 99.85% average efficiency under complex partial shading conditions.