Nawal Cheggaga
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Nawal Cheggaga has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Abdellah Benallal
Department of Engineering Université du Québec à Rimouski Rimouski Quebec Canada
4 shared publications - Adrian Ilinca
Department of Mechanical Engineering, École de Technologie Supérieure, Montreal, QC H3C 1K3, Canada
3 shared publications - Khadidja Dahli
University of Blida 1
2 shared publications - Amine Hebib
Department of Electronics, University of Blida 1, Blida 09000, Algeria
1 shared publication Fatiha Youcef Ettoumi
Laboratoire de Traitement d'Images et Rayonnement, Université des Sciences et de la Technologie, BP 32 El Alia, 16111 Bab Ezzouar, Alger, Algérie, Tél/Fax: +213 21 24 78 94, Mob:+213 61 68 29 18
1 shared publication- Fatima Zohra Saadaoui
Aeronautic Science Laboratory, Institute of Aeronautics and Space Studies, University Blida1, Blida, Algeria
1 shared publication
Latest Publications
- Open Access
Flocking-Inspired Solar Tracking System with Adaptive Performance in Varied Environmental Conditions
Traditional solar trackers are designed to follow the sun’s exact position, assuming that perfect sun alignment always results in optimal energy generation. However, despite perfect alignment, external factors such as shading, dust, and wind can reduce power output in real-world conditions. To address these challenges, our novel system draws inspiration from the flocking behavior of birds, where individual entities adjust their behavior based on their energy output and the energy outputs of neighboring panels. The system uses Particle Swarm Optimization (PSO) to mimic this behavior, dynamically adjusting the solar tracker’s position to respond to varying environmental conditions. One key innovation is introducing a power threshold strategy, set between 1.5 W and 2 W, to avoid continuous tracker movement and conserve energy by minimizing unnecessary adjustments when the power difference is insignificant. The proposed system demonstrated an impressive 8% increase in energy gain and a reduction of up to 11% in energy consumption compared to the traditional continuous tracker. The tracking accuracy improved by 84%, with the mean tracking error reduced in the range of 0.78° to 1.09°. The system also captured 17.4% more solar irradiance, showcasing its superior efficiency. Despite environmental challenges such as dust and shading, the proposed system consistently outperformed the traditional tracker regarding energy savings and overall performance, offering a more resilient and energy-efficient solution for solar energy generation.
Open AccessFlocking-Inspired Solar Tracking System with Adaptive Performance in Varied Environmental Conditions
Traditional solar trackers are designed to follow the sun’s exact position, assuming that perfect sun alignment always results in optimal energy generation. However, despite perfect alignment, external factors such as shading, dust, and wind can reduce power output in real-world conditions. To address these challenges, our novel system draws inspiration from the flocking behavior of birds, where individual entities adjust their behavior based on their energy output and the energy outputs of neighboring panels. The system uses Particle Swarm Optimization (PSO) to mimic this behavior, dynamically adjusting the solar tracker’s position to respond to varying environmental conditions. One key innovation is introducing a power threshold strategy, set between 1.5 W and 2 W, to avoid continuous tracker movement and conserve energy by minimizing unnecessary adjustments when the power difference is insignificant. The proposed system demonstrated an impressive 8% increase in energy gain and a reduction of up to 11% in energy consumption compared to the traditional continuous tracker. The tracking accuracy improved by 84%, with the mean tracking error reduced in the range of 0.78° to 1.09°. The system also captured 17.4% more solar irradiance, showcasing its superior efficiency. Despite environmental challenges such as dust and shading, the proposed system consistently outperformed the traditional tracker regarding energy savings and overall performance, offering a more resilient and energy-efficient solution for solar energy generation.
- Open Access
- 28 March 2025
- Published by MDPI AG in Sustainability
- Vol. 17 (7) , 3011
Tuning Parameters of Genetic Algorithms for Wind Farm Optimization Using the Design of Experiments Method
Wind energy is a vital renewable resource with substantial economic and environmental benefits, yet its spatial variability poses significant optimization challenges. This study advances wind farm layout optimization by employing a systematic genetic algorithm (GA) tuning approach using the design of experiments (DOE) method. Specifically, a full factorial 22 DOE was utilized to optimize crossover and mutation coefficients, enhancing convergence speed and overall algorithm performance. The methodology was applied to a hypothetical wind farm with unidirectional wind flow and spatial constraints, using a fitness function that incorporates wake effects and maximizes energy production. The results demonstrated a 4.50% increase in power generation and a 4.87% improvement in fitness value compared to prior studies. Additionally, the optimized GA parameters enabled the placement of additional turbines, enhancing site utilization while maintaining cost-effectiveness. ANOVA and response surface analysis confirmed the significant interaction effects between GA parameters, highlighting the importance of systematic tuning over conventional trial-and-error approaches. This study establishes a foundation for real-world applications, including smart grid integration and adaptive renewable energy systems, by providing a robust, data-driven framework for wind farm optimization. The findings reinforce the crucial role of systematic parameter tuning in improving wind farm efficiency, energy output, and economic feasibility.
- 28 March 2025
- Published by MDPI AG in Sustainability
- Vol. 17 (7) , 3011
Open AccessTuning Parameters of Genetic Algorithms for Wind Farm Optimization Using the Design of Experiments Method
Wind energy is a vital renewable resource with substantial economic and environmental benefits, yet its spatial variability poses significant optimization challenges. This study advances wind farm layout optimization by employing a systematic genetic algorithm (GA) tuning approach using the design of experiments (DOE) method. Specifically, a full factorial 22 DOE was utilized to optimize crossover and mutation coefficients, enhancing convergence speed and overall algorithm performance. The methodology was applied to a hypothetical wind farm with unidirectional wind flow and spatial constraints, using a fitness function that incorporates wake effects and maximizes energy production. The results demonstrated a 4.50% increase in power generation and a 4.87% improvement in fitness value compared to prior studies. Additionally, the optimized GA parameters enabled the placement of additional turbines, enhancing site utilization while maintaining cost-effectiveness. ANOVA and response surface analysis confirmed the significant interaction effects between GA parameters, highlighting the importance of systematic tuning over conventional trial-and-error approaches. This study establishes a foundation for real-world applications, including smart grid integration and adaptive renewable energy systems, by providing a robust, data-driven framework for wind farm optimization. The findings reinforce the crucial role of systematic parameter tuning in improving wind farm efficiency, energy output, and economic feasibility.
- Open Access
- 13 March 2025
- Published by MDPI AG in World Electric Vehicle Journal
- Vol. 16 (3) , 168
LSTM-Based State-of-Charge Estimation and User Interface Development for Lithium-Ion Battery Management
State-of-charge (SOC) estimation is pivotal in optimizing lithium-ion battery management systems (BMSs), ensuring safety, performance, and longevity across various applications. This study introduces a novel SOC estimation framework that uniquely integrates Long Short-Term Memory (LSTM) neural networks with Hyperband-driven hyperparameter optimization, a combination not extensively explored in the literature. A comprehensive experimental dataset is created using data of LG 18650HG2 lithium-ion batteries subjected to diverse operational cycles and thermal conditions. The proposed framework demonstrates superior prediction accuracy, achieving a Mean Square Error (MSE) of 0.0023 and a Mean Absolute Error (MAE) of 0.0043, outperforming traditional estimation methods. The Hyperband optimization algorithm accelerates model training and enhances adaptability to varying operating conditions, making it scalable for diverse battery applications. Developing an intuitive, real-time user interface (UI) tailored for practical deployment bridges the gap between advanced SOC estimation techniques and user accessibility. Detailed residual and regression analyses confirm the proposed solution’s robustness, generalizability, and reliability. This work offers a scalable, accurate, and user-friendly SOC estimation solution for commercial BMSs, with future research aimed at extending the framework to other battery chemistries and hybrid energy systems.
- 13 March 2025
- Published by MDPI AG in World Electric Vehicle Journal
- Vol. 16 (3) , 168
Open AccessLSTM-Based State-of-Charge Estimation and User Interface Development for Lithium-Ion Battery Management
State-of-charge (SOC) estimation is pivotal in optimizing lithium-ion battery management systems (BMSs), ensuring safety, performance, and longevity across various applications. This study introduces a novel SOC estimation framework that uniquely integrates Long Short-Term Memory (LSTM) neural networks with Hyperband-driven hyperparameter optimization, a combination not extensively explored in the literature. A comprehensive experimental dataset is created using data of LG 18650HG2 lithium-ion batteries subjected to diverse operational cycles and thermal conditions. The proposed framework demonstrates superior prediction accuracy, achieving a Mean Square Error (MSE) of 0.0023 and a Mean Absolute Error (MAE) of 0.0043, outperforming traditional estimation methods. The Hyperband optimization algorithm accelerates model training and enhances adaptability to varying operating conditions, making it scalable for diverse battery applications. Developing an intuitive, real-time user interface (UI) tailored for practical deployment bridges the gap between advanced SOC estimation techniques and user accessibility. Detailed residual and regression analyses confirm the proposed solution’s robustness, generalizability, and reliability. This work offers a scalable, accurate, and user-friendly SOC estimation solution for commercial BMSs, with future research aimed at extending the framework to other battery chemistries and hybrid energy systems.
- 4 November 2023
- Published by Springer Nature in Applied Intelligence
- Vol. 53 (24) , 29818-29844
Multi-sensory system for UAVs detection using Bayesian inference
- 4 November 2023
- Published by Springer Nature in Applied Intelligence
- Vol. 53 (24) , 29818-29844
Multi-sensory system for UAVs detection using Bayesian inference
- 28 July 2023
- Published by Wydawnictwo SIGMA-NOT, sp. z.o.o. in PRZEGLĄD ELEKTROTECHNICZNY
- Vol. 1 (7) , 113-118
A New Solar Tracking Strategy to Upgrade Solar Power Efficiency using ZIP codes as an Alternative to Sensors
Over the last few years, solar trackers has gone from being a modern power technology to a major source of electricity production. Thus far, the solar tracking technology has dominated the market of solar power and renewable energy. Usually solar trackers use sensors to locate the sun's position with a high degree of accuracy; however; the biggest disadvantages of sensor based solar trackers is that they can be complex, inaccurate with the high response time and are slightly more expensive than their stationary counterpart. In that matter, the main objective of this work is to design a new, cost effective and simple solar tracker that increases the solar power efficiency without using sensors nor feedback loops. Instead, we have found a new and more accurate strategy to properly determine the position of the sun by using a tracking code that is based on countries ZIP codes. In this paper the design, simulation and testing of a high-precision and sensorless solar tracking system is carried out using sun position algorithm and astronomical equations. Results show that our tracking system can be 99.9% as accurate as a GPS based solar tracker; moreover, it can be flexible, efficient, low-cost and fitting for both large and small solar generation.
- 28 July 2023
- Published by Wydawnictwo SIGMA-NOT, sp. z.o.o. in PRZEGLĄD ELEKTROTECHNICZNY
- Vol. 1 (7) , 113-118
A New Solar Tracking Strategy to Upgrade Solar Power Efficiency using ZIP codes as an Alternative to Sensors
Over the last few years, solar trackers has gone from being a modern power technology to a major source of electricity production. Thus far, the solar tracking technology has dominated the market of solar power and renewable energy. Usually solar trackers use sensors to locate the sun's position with a high degree of accuracy; however; the biggest disadvantages of sensor based solar trackers is that they can be complex, inaccurate with the high response time and are slightly more expensive than their stationary counterpart. In that matter, the main objective of this work is to design a new, cost effective and simple solar tracker that increases the solar power efficiency without using sensors nor feedback loops. Instead, we have found a new and more accurate strategy to properly determine the position of the sun by using a tracking code that is based on countries ZIP codes. In this paper the design, simulation and testing of a high-precision and sensorless solar tracking system is carried out using sun position algorithm and astronomical equations. Results show that our tracking system can be 99.9% as accurate as a GPS based solar tracker; moreover, it can be flexible, efficient, low-cost and fitting for both large and small solar generation.
- 19 January 2021
- Published by SAGE Publications in Wind Engineering
- Vol. 45 (6) , 1506-1516
Impact of dust events on the optimization of photovoltaic-wind hybrid system in desert
Reliable optimization of renewable energy systems has to be adapted to the installation site and its environmental factors. In dust event sources, the impact of dust on solar irradiance or on system’s production is not usually taken into consideration during optimization of photovoltaic (PV) or PV-wind hybrid systems. The first objective of this paper was to make observatory studies on wind velocity and lifting of Saharan dust that characterize Algerian desert which allowed us to extract a wind threshold for each event in our desert site. The second objective was to quantify this dust suspension and its negative impact, up to 47.46% on global solar irradiance (GSI) and 48.95% on photovoltaic yield effects were observed. The third and main objective of this paper was evaluating changes in optimized system when the dust impact was taken into account. To achieve that we adjusted GSI satellite data on HOMER software to dust presence, and then we run an optimization on HOMER with its GSI database and the new data, this data adjustment leads to a significant expansion of 13.70% on the size of PV generator, also 7.66% and 7.68% increase on the investment expenses and cost of energy respectively. Results obtained on this paper can be used to make PV-hybrid system’s technical and financial optimization in the main Algerian dust source trustworthy.
- 19 January 2021
- Published by SAGE Publications in Wind Engineering
- Vol. 45 (6) , 1506-1516
Impact of dust events on the optimization of photovoltaic-wind hybrid system in desert
Reliable optimization of renewable energy systems has to be adapted to the installation site and its environmental factors. In dust event sources, the impact of dust on solar irradiance or on system’s production is not usually taken into consideration during optimization of photovoltaic (PV) or PV-wind hybrid systems. The first objective of this paper was to make observatory studies on wind velocity and lifting of Saharan dust that characterize Algerian desert which allowed us to extract a wind threshold for each event in our desert site. The second objective was to quantify this dust suspension and its negative impact, up to 47.46% on global solar irradiance (GSI) and 48.95% on photovoltaic yield effects were observed. The third and main objective of this paper was evaluating changes in optimized system when the dust impact was taken into account. To achieve that we adjusted GSI satellite data on HOMER software to dust presence, and then we run an optimization on HOMER with its GSI database and the new data, this data adjustment leads to a significant expansion of 13.70% on the size of PV generator, also 7.66% and 7.68% increase on the investment expenses and cost of energy respectively. Results obtained on this paper can be used to make PV-hybrid system’s technical and financial optimization in the main Algerian dust source trustworthy.
- Open Access
- 20 November 2017
- Published by EDP Sciences in E3S Web of Conferences
- Vol. 23, 09003
Online Bayesian Learning with Natural Sequential Prior Distribution Used for Wind Speed Prediction
Predicting wind speed is one of the most important and critic tasks in a wind farm. All approaches, which directly describe the stochastic dynamics of the meteorological data are facing problems related to the nature of its non-Gaussian statistics and the presence of seasonal effects .In this paper, Online Bayesian learning has been successfully applied to online learning for three-layer perceptron’s used for wind speed prediction. First a conventional transition model based on the squared norm of the difference between the current parameter vector and the previous parameter vector has been used. We noticed that the transition model does not adequately consider the difference between the current and the previous wind speed measurement. To adequately consider this difference, we use a natural sequential prior. The proposed transition model uses a Fisher information matrix to consider the difference between the observation models more naturally. The obtained results showed a good agreement between both series, measured and predicted. The mean relative error over the whole data set is not exceeding 5 %.
- 20 November 2017
- Published by EDP Sciences in E3S Web of Conferences
- Vol. 23, 09003
Open AccessOnline Bayesian Learning with Natural Sequential Prior Distribution Used for Wind Speed Prediction
Predicting wind speed is one of the most important and critic tasks in a wind farm. All approaches, which directly describe the stochastic dynamics of the meteorological data are facing problems related to the nature of its non-Gaussian statistics and the presence of seasonal effects .In this paper, Online Bayesian learning has been successfully applied to online learning for three-layer perceptron’s used for wind speed prediction. First a conventional transition model based on the squared norm of the difference between the current parameter vector and the previous parameter vector has been used. We noticed that the transition model does not adequately consider the difference between the current and the previous wind speed measurement. To adequately consider this difference, we use a natural sequential prior. The proposed transition model uses a Fisher information matrix to consider the difference between the observation models more naturally. The obtained results showed a good agreement between both series, measured and predicted. The mean relative error over the whole data set is not exceeding 5 %.
- 2 November 2017
- Published by SAGE Publications in Wind Engineering
- Vol. 42 (5) , 510-522
A new artificial neural network–power law model for vertical wind speed extrapolation for improving wind resource assessment
This work is intended as a contribution toward a possible harmonization of methods and techniques, aimed at extrapolating wind speed for wind energy purposes. Through the years, different methods have been used to this end, such as power law which is used in many studies and softwares worldwide. Wind shear coefficient cannot be fixed at one value. It has been found that wind shear coefficient varies with parameters such as time of day, season, nature of the terrain, wind speed, temperature, and various thermal and mechanical mixing. This article uses an artificial neural network approach to generate the wind shear coefficient for a given site. The outputs of the models are compared with the real measured data. The results show a good accuracy.
- 2 November 2017
- Published by SAGE Publications in Wind Engineering
- Vol. 42 (5) , 510-522
A new artificial neural network–power law model for vertical wind speed extrapolation for improving wind resource assessment
This work is intended as a contribution toward a possible harmonization of methods and techniques, aimed at extrapolating wind speed for wind energy purposes. Through the years, different methods have been used to this end, such as power law which is used in many studies and softwares worldwide. Wind shear coefficient cannot be fixed at one value. It has been found that wind shear coefficient varies with parameters such as time of day, season, nature of the terrain, wind speed, temperature, and various thermal and mechanical mixing. This article uses an artificial neural network approach to generate the wind shear coefficient for a given site. The outputs of the models are compared with the real measured data. The results show a good accuracy.
- 1 March 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Improvements in wind speed forecasting using an online learning
The use of wind energy has developed significantly worldwide. Wind power is the strongest growing form of renewable energy, ideal for a future with pollution-free electric power. But the intermittent nature of wind makes it difficult to forecast. The researchers have embarked on use of the Multi-Layered Perceptrons (MLP) neural networks and other architectures of neural networks for predicting the actual wind speed from the previous values of the same variable. Several algorithms are then supplied with the data to establish the relationship between the inputs and the output. The obtained results indicate that the identified model can successfully be used, but with a poor accuracy prediction of the wind speed and the Forecasting error increases as we go far dates (hours or minutes) of learning data. In this work a new neural networks approach is developed for predicting the actual wind speed from the previous values of the same variable. Model parameters are estimated from a set of past available data, and they are regularly updated during online operation by accounting for any newly available information. The learning involves physical changes of the connections between neurons. The association between several neural structures, with a specific function, allows the emergence of a higher-order function for all. If the neural network can not monitor the physical changes over time we opt for a dynamic learning over time. Finally, we present a mathematical foundation for our approach.
- 1 March 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Improvements in wind speed forecasting using an online learning
The use of wind energy has developed significantly worldwide. Wind power is the strongest growing form of renewable energy, ideal for a future with pollution-free electric power. But the intermittent nature of wind makes it difficult to forecast. The researchers have embarked on use of the Multi-Layered Perceptrons (MLP) neural networks and other architectures of neural networks for predicting the actual wind speed from the previous values of the same variable. Several algorithms are then supplied with the data to establish the relationship between the inputs and the output. The obtained results indicate that the identified model can successfully be used, but with a poor accuracy prediction of the wind speed and the Forecasting error increases as we go far dates (hours or minutes) of learning data. In this work a new neural networks approach is developed for predicting the actual wind speed from the previous values of the same variable. Model parameters are estimated from a set of past available data, and they are regularly updated during online operation by accounting for any newly available information. The learning involves physical changes of the connections between neurons. The association between several neural structures, with a specific function, allows the emergence of a higher-order function for all. If the neural network can not monitor the physical changes over time we opt for a dynamic learning over time. Finally, we present a mathematical foundation for our approach.
- 1 August 2013
- Published by SAGE Publications in Wind Engineering
- Vol. 37 (4) , 369-379
New Neural Networks Strategy Used to Improve Wind Speed Forecasting
Wind speed forecasting is critical for wind energy conversion systems since it greatly influences the issues such as the scheduling of a power system, and the dynamic control of the wind turbine. The wind forecast problem aims to find an estimate f( t + k) of the wind vector y( t + k) based on the previous n measurements. Artificial neural networks ANN is a technique basically used to map random input vector(s) to the corresponding random output vector without pre-assuming any fixed relationship between them. Different network structures, learning rates, and inputs are believed to result in different forecast accuracies. However, in literature it was discovered that, different inputs and learning rates, as well as model structures, directly influence the forecast accuracy. In this paper, we present a robust and reliable forecast method by applying a new learning Strategy. This new method allows a renewal learning data in time. A simple multilayer perceptron (MLP) with Levenberg-Marquardt learning algorithm technique is used for predicting the wind speed. For our algorithm a neural network is developed to estimate just one value f( t + 1), then it is taken up with a new set of learning enriched by data freshly measured. The wind data used are the hourly mean wind speed collected at an observation sites in Ksar El chellala, (Algeria). Simulation results are reported, showing that the estimated wind speed values, predicted by the proposed learning algorithm technique, are in good agreement with the experimental measured values. The present paper deals with the development of an adaptive neural network model for the hourly forecasting of wind speed.
- 1 August 2013
- Published by SAGE Publications in Wind Engineering
- Vol. 37 (4) , 369-379
New Neural Networks Strategy Used to Improve Wind Speed Forecasting
Wind speed forecasting is critical for wind energy conversion systems since it greatly influences the issues such as the scheduling of a power system, and the dynamic control of the wind turbine. The wind forecast problem aims to find an estimate f( t + k) of the wind vector y( t + k) based on the previous n measurements. Artificial neural networks ANN is a technique basically used to map random input vector(s) to the corresponding random output vector without pre-assuming any fixed relationship between them. Different network structures, learning rates, and inputs are believed to result in different forecast accuracies. However, in literature it was discovered that, different inputs and learning rates, as well as model structures, directly influence the forecast accuracy. In this paper, we present a robust and reliable forecast method by applying a new learning Strategy. This new method allows a renewal learning data in time. A simple multilayer perceptron (MLP) with Levenberg-Marquardt learning algorithm technique is used for predicting the wind speed. For our algorithm a neural network is developed to estimate just one value f( t + 1), then it is taken up with a new set of learning enriched by data freshly measured. The wind data used are the hourly mean wind speed collected at an observation sites in Ksar El chellala, (Algeria). Simulation results are reported, showing that the estimated wind speed values, predicted by the proposed learning algorithm technique, are in good agreement with the experimental measured values. The present paper deals with the development of an adaptive neural network model for the hourly forecasting of wind speed.