Optimization algorithms are search methods where the goal is to find an optimal solution to a problem, in order to satisfy one or more objective functions, possibly subject to a set of constraints. Studies of social animals and social insects have resulted in a number of computational models of swarm intelligence. Within these swarms their collective behavior is usually very complex. The collective behavior of a swarm of social organisms emerges from the behaviors of the individuals of that swarm. Researchers have developed computational optimization methods based on biology such as Genetic Algorithms, Particle Swarm Optimization, and Ant Colony. The aim of this paper is to describe an optimization algorithm called the Bees Algorithm, inspired from the natural foraging behavior of honey bees, to find the optimal solution. The algorithm performs both an exploitative neighborhood search combined with random explorative search. In this paper, after an explanation of the natural foraging behavior of honey bees, the basic Bees Algorithm and its improved versions are described and are implemented in order to optimize several benchmark functions, and the results are compared with those obtained with different optimization algorithms. The results show that the Bees Algorithm offering some advantage over other optimization methods according to the nature of the problem.

Solar photovoltaic energy generation has garnered substantial interest owing to its inherent advantages, such as zero pollution, flexibility, sustainability, and high reliability. Ensuring the efficient functioning of PV power facilities hinges on precise fault detection. This not only bolsters their reliability and safety but also optimizes profits and avoids costly maintenance. However, the detection and classification of faults on the Direct Current (DC) side of the PV system using common protection devices present significant challenges. This research delves into the exploration and analysis of complex faults within photovoltaic (PV) arrays, particularly those exhibiting similar I-V curves, a significant challenge in PV fault diagnosis not adequately addressed in previous research. This paper explores the design and implementation of Support Vector Machines (SVMs) and Extreme Gradient Boosting (XGBoost), focusing on their capacity to effectively discern various fault states in small PV arrays. The research broadens its focus to incorporate the use of optimization algorithms, specifically the Bees Algorithm (BA) and Particle Swarm Optimization (PSO), with the goal of improving the performance of basic SVM and XGBoost classifiers. The optimization process involves refining the hyperparameters of the Machine Learning models to achieve superior accuracy in fault classification. The findings put forth a persuasive case for the Bees Algorithm’s resilience and efficiency. When employed to optimize SVM and XGBoost classifiers for the detection of complex faults in PV arrays, the Bees Algorithm showcased remarkable accuracy. In contrast, classifiers fine-tuned with the PSO algorithm exhibited comparatively lower performances. The findings underscore the Bees Algorithm’s potential to enhance the accuracy of classifiers in the context of fault detection in photovoltaic systems.

This paper focuses on using the Bees Algorithm (BA) to tune the parameters of the proposed Fuzzy Proportional–Integral–Derivative with Filtered derivative (Fuzzy PIDF), Fractional Order PID (FOPID) controller and classical PID controller developed to stabilize and balance the frequency in the Great Britain (GB) power system at rated value. These controllers are proposed to meet the requirements of the GB Security and Quality of Supply Standard (GB-SQSS), which requires frequency to be brought back to its nominal value after a disturbance within a specified time. This work is extended to employ the proposed fuzzy structure controller in a dual-area interconnected power system. In comparison with controllers tuned by Particle Swarm Optimization (PSO) and Teaching Learning-Based Optimization (TLBO) used for the same systems, simulation results show that the Fuzzy PIDF tuned by BA is able to significantly reduce the deviation in the frequency and tie-line power when a sudden disturbance is applied. Furthermore, the applied controllers tuned by BA including the Fuzzy PIDF prove their high robustness against a wide range of system parametric uncertainties and different load disturbances.

This paper proposes a design of Sliding Mode Control (SMC) for Load Frequency Control (LFC) in a two-area electrical power system. The mathematical model design of the SMC is derived based on the parameters of the investigated system. In order to achieve the optimal use of the proposed controller, an optimisation tool called the Bees Algorithm (BA) is suggested in this work to tune the parameters of the SMC. The dynamic performance of the power system with SMC employed for LFC is studied by applying a load disturbance of 0.2 pu in area one. To validate the supremacy of the proposed controller, the results are compared with those of recently published works based on Fuzzy Logic Control (FLC) tuned by Teaching–Learning-Based Optimisation (TLBO) algorithm and the traditional PID optimised by Lozi map-based Chaotic Optimisation Algorithm (LCOA). Furthermore, the robustness of SMC-based BA is examined against parametric uncertainties of the electrical power system by simultaneous changes in certain parameters of the testbed system with 40% of their nominal values. Simulation results prove the superiority and the robustness of the proposed SMC as an LFC system for the investigated power system.

Fault diagnosis of induction motor anomalies is vital for achieving industry safety. This paper proposes a new hybrid Machine Learning methodology for induction-motor fault detection. Some of the motor parameters such as the stator currents and vibration signals provide a great deal of information about the motor’s conditions. Therefore, these signals of the motor were selected to test the proposed model. The induction motor was assessed in a laboratory under healthy, mechanical, and electrical faults with different loadings. In this study a new hybrid model was developed using the collected signals, an optimal features selection mechanism is proposed, and machine learning classifiers were trained for fault classification. The procedure is to extract some statistical features from the raw signal using Matching Pursuit (MP) and Discrete Wavelet Transform (DWT). Then, the Invasive Weed Optimization algorithm (IWO)-based optimal subset was selected to reduce the data dimension and increase the average accuracy of the model. The optimal subset of features was fed into three classification algorithms: k-Nearest Neighbor (KNN), Support Vector Machine (SVM), and Random Forest (RF), which were trained using k-fold cross-validation to distinguish between the induction motor faults. A similar strategy was performed by applying the Genetic Algorithm (GA) to compare with the performance of the proposed method. The suggested fault detection model’s performance was evaluated by calculating the Receiver Operation Characteristic (ROC) curve, Specificity, Accuracy, Precision, Recall, and F1 score. The experimental results have proved the superiority of IWO for selecting the discriminant features, which has achieved more than 99.7% accuracy. The proposed hybrid model has successfully proved its robustness for diagnosing the faults under different load conditions.

The reliable operation of power transformers is essential for grid stability, yet existing fault detection methods often suffer from inaccuracies and high false alarm rates. This study introduces a machine learning framework leveraging voltage signals for early fault detection. Simulating diverse fault conditions—including single line-to-ground, line-to-line, turn-to-ground, and turn-to-turn faults—on a laboratory-scale three-phase transformer, we evaluated decision trees, support vector machines, and logistic regression models on a dataset of 6000 samples. Decision trees emerged as the most effective, achieving 99.90% accuracy during 5-fold cross-validation and 95% accuracy on a separate test set of 400 unseen samples. Notably, the framework achieved a low false alarm rate of 0.47% on a separate 6000-sample healthy condition dataset. These results highlight the proposed method’s potential to provide a cost-effective, robust, and scalable solution for enhancing transformer fault detection and advancing grid reliability. This demonstrates the efficacy of voltage-based machine learning for transformer diagnostics, offering a practical and resource-efficient alternative to traditional methods.