Distributed generation (DG) units are used to improve grid reliability and stability. Electric vehicle charging stations (EVCS) consume more power from the grid at peak periods. These two systems cannot be practically located on every part of the grid due to technical effects. In this study, two metaheuristic techniques are adopted to improve the voltage profile and minimise power losses by simultaneously allocating DG units and EVCS. The study employed the IEEE 33 bus test system in finding the solution. The study used standard Particle Swarm Optimization(PSO) and Artificial Bee Colony(ABC) algorithms for DG and EVCS allocation. The results show that PSO outperformed ABC and other algorithms in terms of the simultaneous allocation of DG units and EVCS. The power losses were 40.78% less when PSO is used for allocation. Buses 2 and 19 are the favorite buses for EVCS on an IEEE 33 bus system. The paper concludes that the addition of high-capacity EVCS should lead to the simultaneous introduction of DG units on the network.

Network attacks detection is still a difficult task because of the large data volumes needed for training a cutting-edge machine learning algorithms to unearth network invasions. Recently, a number of data mining methods have been put out for network intrusion detection. Meanwhile, each of them encounters certain difficulties resulting from the sophisticated nature of threats the existing models cannot detect. The NSL-KDD dataset containing four different form of attacks was employed in this paper. In this paper, we demonstrate the efficiency of LoGD-ai, a soft voting-based ensemble learner as network intrusion detection system to classify network data to normal and malicious. This soft-voting based ensemble classifier employs logistic regression, gradient boosting and decision tree algorithms for intrusion detection. Finally, the performance of the LoGD-ai classifier is compared to the popular gradient boosting machine (GBM), random forests (RF), and AdaBoost. Scoring 98.05% on accuracy, the LoGD-ai classifier performs better than GBM, RF and AdaBoost classifiers, efficiently detecting and classifying network traffic as normal or malicious. Compared to gradient boosting, our proposed methodology increases accuracy by 0.52%, which is critical for network intrusion detection.

The incorporation of renewable distributed generation (DG) stands as a pivotal component in implementing strategies directed toward mitigating power losses within electrical networks. With the continual rise in electricity demand and the accompanying maintenance expenditures, the importance of DG has become increasingly apparent. The effectiveness of reducing power losses, improving voltage profiles, and lowering system expenses was evaluated in this study by comparing the techniques of Artificial Bee Colony (ABC), differential evolution (DE), and particle swarm optimization (PSO). Among these methods, ABC emerged as the most effective, showing substantial potential in enhancing DG performance within a 33 kV distribution system, resulting in a 98.97% reduction in system costs. The findings of this analysis provide appreciated insights for guiding future research efforts in optimizing electrical systems.

Utilization of Distribution Static Compensator (DSTATCOM) has proven to be instrumental in essential strategies aimed at mitigating power losses within electrical network systems. The growing demand for electricity and high maintenance costs have propelled DSTATCOM into a prominent position for discussion and consideration. This paper conducted a comprehensive comparative study employing optimization methods such as Differential Evolution (DE), Particle Swarm Optimization (PSO), and Artificial Bee Colony (ABC). The objectives of this study are to compare the performance in terms of Voltage Profile Improvement (VPI), Power Loss Reduction (PLR), and System Cost (SC) while selecting the best method as a suggestion for future research. The techniques were simulated in a MATLAB environment and a 50-bus system was used for real testing. The DE method emerged as the most effective technique in the analysis of the three objective functions. This outcome suggests that DE holds significant promise as a viable and efficient method for enhancing the performance of DSTATCOM in terms of VPI, PLR, and SC. These findings offer valuable guidance for future research endeavors in the realm of electrical network system optimization.

The rise of electric vehicles (EVs) in sustainable cities has fuelled interest in DG unit allocation. A well-planned and efficient charging infrastructure is required for effective e-mobility. The paper examined the single-objective frameworks of optimal simultaneous allocation of DG units and fast EV charging stations (EVCS). The applications are employed on the IEEE 69 bus network and a real part of the Ghana network in the Ashanti region. The optimization tasks are carried out by using Particle swarm optimization (PSO) and artificial bee colony (ABC) algorithms. The impact of optimal placement on the networks was analyzed. The results show that with high penetration levels of DG units (up to 40%) and fast EVCS, PSO, and ABC can achieve a significant power loss reduction that reaches 68%. Furthermore, PSO outperforms ABC in relation to the voltage deviation index on both the test network and the Ashanti region network, while still satisfying the IEC standards’ 5% margins. The results indicate that PSO and ABC are viable swarm algorithms for mitigating active power loss and enhancing the voltage profile of a system through concurrent allocation