ABSTRACT This paper proposes a dual‐layer control architecture for a dual‐motor rear‐wheel‐drive electric vehicle (EV) equipped with two permanent magnet synchronous motors (PMSMs) and direct torque control (DTC). In the motor control layer, a GA‐optimized artificial neural network (GA‐ANN) replaces the conventional PI speed regulator to generate an adaptive torque‐related control signal, improving transient performance under nonlinear operating conditions. In the vehicle layer, an ant colony optimization (ACO) module computes real‐time left/right torque distributions to implement electronic differential action and enhance cornering behavior. The proposed scheme is evaluated in simulation under straight‐line driving (including road‐grade disturbance) and cornering maneuvers. Compared with conventional control strategies, the proposed approach achieves faster settling, reduced steady‐state tracking error, and improved wheel‐speed coordination during turning, resulting in improved vehicle stability and traction behavior. The results indicate that combining adaptive motor regulation with optimization‐based torque allocation provides an effective solution for EV drivetrains under variable driving conditions.

This paper presents a case study detailing the design, implementation, and analysis of a secure and comprehensive platform for monitoring smart grid meter data. The system integrates simulated IoT device data generation, secure MQTT communications using AES encryption, back-end processing with robust credential management via Fernet encryption, persistent MySQL storage, and distinct web interfaces for end users and administrators, built using Flask and Dash/Plotly. The architecture focuses on security, scalability, and ease of use, providing a practical model for managing bidirectional energy flow data in modern smart grids. The analysis covers the system’s functionality, key features, security measures, potential scalability, ease of use, and comparisons with related work. It concludes with limitations and future development directions.

Online monitoring and fault detection play important roles in ensuring the healthy performance of grid-connected PV power stations. In this work, both linear and nonlinear multivariate statistical analyses based on PCA and Kernel PCA were utilized to achieve this. Additionally, Hotelling’s T2, Q-static, and KDE techniques have been incorporated into the algorithm. The proposed real-time fault detection system was tested on a 7 kWp grid-connected PV station in Adrar, Algeria’s Saharan region. Various fault experiments, including open circuit, short circuit, and partial shading at different degrees, were conducted to validate the algorithm thoroughly. The experimental results show that the detection performance varies from 34

This paper presents an advanced bio-inspired strategy for Global Maximum Power Point Tracking (GMPPT) in standalone Photovoltaic (PV) systems operating under partial shading conditions (PSC). The proposed approach integrates a novel Circulatory System-Based Optimization (CSBO) algorithm with a Model Predictive Current Control (MPCC) scheme to enhance tracking speed, accuracy and robustness. The CSBO algorithm emulates the dual-path dynamics of the human circulatory-system by segmenting the population into systemic and pulmonary branches, mirroring oxygen-rich and oxygen-poor flows. This bio-inspired architecture enables a dynamic equilibrium between global exploration and local exploitation, significantly enhancing convergence reliability and robustness. Such a strategy ensures consistent tracking of the GMPP under multi-modal Power-Voltage (P-V) characteristics. Meanwhile, the MPCC leverages real-time inductor current estimation to sharpen transient performance and suppress steady-state oscillations, thereby improving overall tracking efficiency and system stability. The combined CSBO-MPCC approach is implemented on a standalone PV system, and its performance is validated through detailed simulations and experimental results under various irradiance profiles. Comparative analysis with other GMPPT techniques demonstrates significant improvements in convergence speed, tracking efficiency, and stability, particularly under PSC. This work confirms the potential of hybrid bio-inspired MPCC methods in advancing intelligent energy harvesting strategies for standalone renewable energy systems.

In this study, we present a predictive modeling framework for anticipating power outages using temporal, meteorological, and historical outage data. The proposed methodology gathers aggregate temporal and contextual data from multiple sources, and then engineers features based on time, binary indicators, and derived features. A Random Forest classifier is developed using a train-test partition and the model robustness is established through cross-validation. The model is designed to predict outages based on patterns in the energy consumption and environmental conditions. The performance of the model is evaluated using several metrics, it reached an accuracy of approximately 99 %, with precision, recall, and F1-scores all exceeding 98 %. The findings of this study provide evidence that supports the proposed approach for anticipating power outages to create smarter grid management and better reliability in power systems.

In this paper, we successfully created a low-cost, facile and reliable solution for real-time monitoring of grid-connected photovoltaic (PV) system. Our solution simplifies the connection and access to database of system performances, dependent on various parameters and environmental conditions. The real-time monitoring enables swift fault rectification, enhancing system efficiency, and providing insights into energy consumption of the PV system. We implemented our solution using low-cost electronic devices and sensors connected to 1.75 kW PV system installed in Adrar city situated in the Saharan region of southern Algeria. The electrical characteristics were measured using multiple sensors and stored in SD memory card and in server. Following the design and implementation of our data acquisition system for monitoring parameters from grid-connected photovoltaic system, we conducted a comparative study with the Fluke 2635A HYDRA Series II data acquisition system. The proposed system can be easily scaled to monitor higher power and larger PV stations with minimal adjustments by changing the high-range sensors and their parameters in the software.

This paper introduces a temperature supervision and monitoring system implemented through an embedded controller (EC) utilizing the supervisory control and data acquisition (SCADA) platform. The Arduino Mega involved an Ethernet shield, serving as the EC master, which was employed to initially collect measurements from the LM35 temperature sensor. Subsequently, the acquired data was transmitted to the slave SCADA for display in various formats, including digital and gauge representations and real-time tracing. The data communication link between the Master and slave was established via an Ethernet cable, following the industrial Modbus TCP/IP protocol.

In this study, a Schottky diode consisting of Au/GaN/GaAs was fabricated using a radiofrequency nitrogen plasma source. The voltageconductance characteristics (G/omega-V) of this diode structure were investigated at room temperature. To interpret the changes in the electrical properties of the nitrided GaAs-based Schottky structure, we developed a simulation program. This program employs a numerical model to calculate the G-V characteristics, allowing us to validate the experimental measurements conducted on the Schottky diodes. The geometric model used in our simulation considers not only the GaN layer formed between the metal and GaAs substrate but also the density and distribution of trapped states within the band gap. The program utilizes the numerical resolution of the Poisson and continuity equations to calculate the electrostatic potential and the concentrations of both n and p mobile carriers. These parameters are then used to determine the electric charge, current, capacitance, and conductance. The simulation results were subsequently compared to the experimental measurements to ensure their accuracy.

Algeria, strategically located at the northern gateway of Africa, boasts a significant renewable energy potential, with solar Energy in the Saharan region being a central component. With an average sunshine duration of 3,000 hours per year, extending up to 3,500 hours in the Saharan region, the country is positioned as one of the world's prime locations for solar energy harnessing. The Global Horizontal Irradiance in Algeria averages between 5.1 KWh in the North and 6.6 KWh in the Great South per square meter daily, making it an attractive destination for solar energy projects. Despite the nation's heavy reliance on fossil fuel revenues, recent efforts by the Algerian government have been directed toward promoting the transition to clean and renewable energies. In 2018, solar power contributed to 84% of the country's electricity from renewable sources. Nevertheless, the vast potential of solar energy resources still needs to be utilized. This paper aims to provide an in-depth overview of the solar energy landscape in Algeria, emphasizing its untapped potential, current initiatives, and prospects.

In this work, experimental studies were carried out to study in detail the impact of sand and dust on the electrical performance of photovoltaic modules in the Adrar region. For this, a comparison between two identical photovoltaic systems of 7 kWp each (PV17 and PV67) was carried out, the PV17 is cleaned regularly and the PV67 is cleaned infrequently. The experiment results reveal a significant impact of sand and dust accumulation on the electrical performance of the systems. The energy losses just after exposure to sandstorms are 7.37 kWh (1.45% of total production in 07 days of operation and two days of sandstorms), for dust accumulation they are 2.2 kWh, 3.2 kWh, 5.13 kWh, and 4 kWh after 6, 11, 18 and 23 days of operation respectively. The results show that cleaning PV systems immediately after sandstorm days can significantly reduce energy losses. For dust accumulation works, cleaning once every 20 days allows the PV systems to have energy reduction by 1.60%. The economic study carried out in this work shows that PV systems cleaning in the Adrar region is financially profitable with capacities greater than 20 kWp and energy gain greater than 2.74 kWh.

In this paper a detailed evaluation analysis of a photovoltaic plant with 2.5 Kwp capacity was performed, this grid tied photovoltaic plant is located and installed on the roof top of the Research Unit on Renewable Energy (URER-MS) in Adrar region in southern Algeria (Latitude 27.88°N, Longitude -0.27 °E, Altitude 262 m) in year 2018/2019. The Adrar region is characterized by a very high average temperature, low humidity rate and high potential for solar radiation. This analysis was carried out by carrying out a precise evaluation of the various impacts of the environmental parameters on the operating performance of the grid-connected photovoltaic installation. During 12 months of the year 2019 with the annual average temperature was 32°C, the grid connected photovoltaic plant was supplied a total power of 4456 kWh. The experimental results indicated that for different months an important variation have been observed in performance parameters. The maximum/minimum of monthly average daily values of final, reference, and array yields are; 5.55-4.08 kW h/kWp/day, 5.68-5.2 kW h/kWp/day, and 5.07/3.75 kW h/kWp/day, respectively. The overall system, PV module and inverter efficiency reached; 12.80-11.87%, 15.08-11.78%, and 97.5-/98.01%, respectively. The annual performance ratio (PR) is from 65.4% to 82.74%.

Online monitoring and prediction play a crucial role in ensuring the optimal performance of grid-connected photovoltaic (PV) stations. On the other hand, using machine learning techniques, specifically tree-based methods, has demonstrated its effectiveness in predicting and detecting faults in nonlinear processes. In this study, we employed a tree regression method for the online monitoring and prediction of a 7 kWp PV station located in the desert region of Adrar. Our approach exhibited clear superiority when compared to classical regression methods such as the Linear Least Squares Method (LLS). We achieved a determination coefficient $(\mathbf{R}^{\mathbf{2}})$ of 0.9671 and a Mean Absolute Error (MAE) of 187.2, surpassing the results obtained with LLS, which yielded an $\mathbf{R}^{\mathbf{2}}$ of 0.9646 and an MAE of 252.06, highlighting the efficacy of our proposed methodology.

Over the past decade, significant advancements in electronics, computer science, and communications have propelled the evolution of embedded systems within the Internet of Things (IoT) domain. This paper focuses on the implementation of a remote temperature monitoring system, leveraging a Wi-Fi card integrated into a smartphone Android application. The development process involves utilizing the MIT App Inventor IDE, a user-friendly visual programming interface, along with the ESP8266 microcontroller for platform development. The temperature sensing capability is achieved through the integration of the LM35 sensor. The system enables real-time temperature monitoring and data acquisition, facilitating informed decision-making and timely responses to temperature variations. Through rigorous testing and evaluation, the effectiveness, accuracy, and reliability of the system are demonstrated. The combination of cost-effectiveness, ease of use, and widespread availability makes this solution suitable for a range of applications in various environments.

With its diverse topographical and climatic conditions, Algeria presents a promising avenue for exploiting wind energy. Situated in North Africa, the country's vast territories, especially regions like Adrar, exhibit significant wind potential, with wind speeds ranging between 3 to 8.5 m/s at an altitude of 80 m. Despite the nation's historical reliance on fossil fuels, there has been a growing recognition of the untapped potential of wind energy. In 2018, wind turbines contributed 1% of the total renewable electricity production, indicating both the progress and vast opportunities ahead. This paper aims to provide a comprehensive overview of the wind energy landscape in Algeria. We will explore the geographical regions with high wind potential, delve into the current state of wind energy utilization, and highlight research and initiatives that underscore Algeria's commitment to harnessing this renewable source. Through a detailed analysis, this study seeks to emphasize the strategic importance of wind energy in Algeria's sustainable energy future.

The accurate forecasting of photovoltaic (PV) power refers to the ability to predict the amount of electrical energy that will be generated by a photovoltaic system in response to given irradiation and temperature. This forecast is important for several reasons, including optimizing the system's performance, facilitating energy trade and managing network integration. In this article, Long Short Term Memory (LSTM) neural network are used for forecasting the output power of a photovoltaic power generation station using a set of historical time series data composed of photovoltaic power, irradiation and temperature. The data has been collected by the measuring environmental variables and generated power every 15 minutes from a station located in the city of Adrar in the Southern West of Algeria. The accuracy of the LSTM based model is compared to other classic models such as ANFIS and ANN for the same conditions. The results of the trained LSTM model show a slight difference between the forecasted and measured power with a Mean Absolute Error (MAE) value equal to MAE= 127.10. The training and evaluation of the PV power forecasts by other techniques give an average accuracy MAE= 1.3857 for the ANN model, and MAE=3.0052*10 -4 for the ANFIS model.

This work investigates the issues found in the dynamic performance of the PV system associated with a cascade-controlled DC-DC converter in the current source region (CSR). The overall system time response in the CSR exhibits oscillatory behavior which has been found to be caused by the outer voltage control loop. Instead of a commonly used tracking controller, a novel disturbance rejection-based cascade controller is proposed in order to improve dynamic system performance and robustness. The proposed controller is composed of a sliding mode controller for the inner current control loop and a feedback linearization combined with the fractional order PID controller for the outer voltage control loop. The voltage controller is tuned using the Equilibrium Optimizer (EO) algorithm where a new performance index has been considered. Simulation results are given to demonstrate the higher performance of the proposed control strategy in different operating regions including the CSR region.

Compared to moderate climate conditions, hot and dry environment, as known desert, present the most difficult environment that affects negatively PV panels performance. In the present paper, the root causes that have the major contribution in PV panel performance degradation in desert climates and the direct relationship between desert climate factors and accelerate degradation mechanism are analyzed. Algeria's desert is chosen as a case to study, an overview of Algeria's desert climate has been presented. High solar irradiation accompanied by high ambient temperature has been considered as the most responsible for accelerated discoloration and initiating damage of EVA encapsulant material which can create a challenge for long-term reliability of c-Si PV panels. The declared 20–25 year PV panel lifetime is very optimistic in Algeria's desert climates. This research work can be beneficial in future studies on challenges related to the optimal performance and the expected operating lifetime of photovoltaic applications in desert climates.

Batteries are widely used for energy storage in stand-alone PV systems. However, both PV modules and batteries exhibit nonlinear behavior. Therefore, battery modeling is an essential step toward appropriate battery control and overall PV system management. Empirical models remain reliable for lead-acid batteries, especially the Copetti model, which describes many inner and outer battery phenomena, including temperature dependency. However, the parameters of the Copetti model require further adjustment to increase its ability to accurately represent battery behavior. Recently, metaheuristic algorithms have been employed for parameter identification, especially hybrid algorithms that combine the advantages of two or more algorithms. This paper proposes an enhanced battery model based on the Copetti model. The parameter identification of the enhanced model has been carried out using a novel hybrid PSO-GA algorithm (HPGA). The hybrid algorithm combines GA and PSO in a cascade configuration, with GA as the master algorithm. The HPGA algorithm has been compared with other algorithms, namely GA, PSO, ABC, COA, and a hybrid GWO-COA, to reveal its advantages and disadvantages. The NRMSE is used to evaluate algorithms in terms of tracking speed and efficiency. HPGA shows an improvement in tracking efficiency compared to GA and PSO. The proposed model is validated on several charging-discharging data and exhibits a 15% lower mean error compared to the Copetti model with original parameters. Additionally, the proposed model demonstrates a lower mean error of 0.16% compared to other models in the literature with a 0.36% mean error at least.

Solar energy is rapidly gaining ground because of its sustainability, pollution-free nature, and cost-effectiveness. However, the efficiency of photovoltaic modules is affected by factors such as instant irradiation, temperature, and site-specific load properties. As a solution, MPPT strategies are employed to optimize module power extraction and reduce power losses. This study introduces an MPPT controller utilizing a hybrid GWO and PSO, specifically designed for PV systems operating under partial shading conditions PSCs.To assess the proposed algorithm, comparisons are made with both PSO and GWO algorithms to evaluate the performance of the hybrid method and perceive how the combination enhances tracking speed and efficiency compared to individual algorithms. Results indicate that the hybrid algorithm exhibits a minimum of 20% faster response time and superior tracking efficiency compared to PSO and GWO algorithms.

Traditional Maximum Power Point Tracking (MPPT) techniques are unable to reach high performance in photovoltaic (PV) system under partial shading conditions because of the multi-peaks present in the Power-Voltage curve. For that, particle Swarm Optimization (PSO) and genetic algorithms (GA) have been combined in recent years. However, these algorithms demonstrate some drawbacks in tracking accuracy and convergence rates, which impair control performance. In this paper, a new controller based on hybridization of PSO and GA is introduced to track the global maximum power point (GMPP). The proposed algorithm (HPGA) increases the balance rate between exploration and exploitation due to the cascade design of GA and PSO. Thus, the GMPP tracking of both algorithms will be improved. Simulations are carried out based on ISOFOTON-75W PV modules to prove the high performance of the proposed algorithm. From the obtained results, we conclude that HPGA shows fast convergence and very good tracking accuracy of GMPP in PV system even under different shading patterns.