The development and deployment of an effective wind speed forecasting technology can improve the safety and stability of power systems with significant wind penetration. Due to the wind’s unpredictable and unstable qualities, accurate forecasting of wind speed and power is extremely challenging. Several algorithms were proposed for this purpose to improve the level of forecasting reliability. The Long Short-Term Memory (LSTM) network is a common method for making predictions based on time series data. This paper proposed a machine learning algorithm, called Adaptive Dynamic Particle Swarm Algorithm (AD-PSO) combined with Guided Whale Optimization Algorithm (Guided WOA), for wind speed ensemble forecasting. The AD-PSO-Guided WOA algorithm selects the optimal hyperparameters value of the LSTM deep learning model for forecasting of wind speed. In experiments, a wind power forecasting dataset is employed to predict hourly power generation up to forty-eight hours ahead at seven wind farms. This case study is taken from the Kaggle Global Energy Forecasting Competition 2012 in wind forecasting. The results demonstrated that the AD-PSO-Guided WOA algorithm provides high accuracy and outperforms several comparative optimization and deep learning algorithms. Different tests’ statistical analysis, including Wilcoxon’s rank-sum and one-way analysis of variance (ANOVA), confirms the accuracy of the presented algorithm.

Dissolved gas analysis (DGA) is the standard technique to diagnose the fault types of oil-immersed power transformers. Various traditional DGA methods have been employed to detect the transformer faults, but their accuracies were mostly poor. In this light, the current work aims to improve the diagnostic accuracy of power transformer faults using artificial intelligence. A KNN algorithm is combined with the decision tree principle as an improved DGA diagnostic tool. A total of 501 dataset samples are used to train and test the proposed model. Based on the number of correct detections, the neighbor's number and distance type of the KNN algorithm are optimized in order to improve the classifier's accuracy rate. For each fault, indeed, several input vectors are assessed to select the most appropriate one for the classifier's corresponding layer, increasing the overall diagnostic accuracy. On the basis of the accuracy rate obtained by knots and type of defect, two models are proposed where their results are compared and discussed. It is found that the global accuracy rate exceeds 93% for the power transformer diagnosis, demonstrating the effectiveness of the proposed technique. An independent database is employed as a complimentary validation phase of the proposed research.

This paper presents the design and characterization of a compact broadband antenna and its MIMO configuration for 28 GHz 5G applications. The antenna was designed using Rogers RT/5880 with a thickness of 1.575 mm and has an overall compact size of 30 mm × 30 mm. The design methodology was initiated by designing a compact conventional microstrip antenna for 28 GHz. Afterward, the rectangular slots were utilized to improve the impedance bandwidth so that antenna covers the globally allocated 28 GHz band spectrum for 5G applications. Furthermore, a compact 2 × 2 MIMO antenna with polarization diversity is designed for high channel capacity systems. The mutual coupling between the closely spaced antenna elements is reduced by using two consecutive iterations of defected ground structure (DGS). The proposed MIMO antenna system offers broad bandwidth, high gain, low mutual coupling, and low envelope correlation coefficient along with high diversity gain, low mean effective gain, and low channel capacity loss. Moreover, the proposed been compared with the state-of-the-art MIMO antenna proposed for 28 GHz application to demonstrate worth of the presented design.

The accurate parameter extraction of photovoltaic (PV) module is pivotal for determining and optimizing the energy output of PV systems into electric power networks. Consequently, a Photovoltaic Single-Diode Model (PVSDM), Double Diode Model (PVDDM), and Triple- Diode Model (PVTDM) is demonstrated to consider the PV losses. This article introduces a new application of the Forensic-Based Investigation Algorithm (FBIA), which is a new meta-heuristic optimization technique, to accurately extract the electrical parameters of different PV models. The FBIA is inspired by the suspect investigation, location, and pursuit processes that are used by police officers. The FBIA has two phases, which are the investigation phase applying by the investigators team, and the pursuit phase employing by the police agents team. The validity of the FBIA for PVSDM, PVDDM, and PVTDM is commonly considered by the numerical analysis executing under diverse values of solar irradiations and temperatures. The optimal five, seven, and nine parameters of PVSDM, PVDDM, and PVTDM, respectively, are accomplished using the FBIA and compared with those manifested by various optimization techniques. The numerical results are compared for the marketable Photowatt-PWP 201 polycrystalline and Kyocera KC200GT modules. The efficacy of the FBIA for the three models is properly carried out checking its standard deviation error with that obtained from various recently proposed optimization techniques in 2020 which are Jellyfish search (JFS) optimizer, Manta Ray Foraging optimizer (MRFO), Marine Predators Algorithm(MPA), Equilibrium Optimizer (EO), Heap Based Optimizer (HBO). The standard deviations of the fitness values over 30 runs are developed to be less than $1 \times 10^{-6}$ for the three models, which make the FBIA results are extremely consistent. Therefore, FBIA is foreseen to be a competitive technique for PV module parameter extraction.

Connecting different renewable energy sources (RESs) to the electrical grids is presently being urged to fulfill the enormous need for electric power and to decrease traditional sources' ecological related issues, the so-called hybrid systems. Unfortunately, these hybrid systems suffer from the possible negative environmental impacts of the wind gusts in wind energy conversion systems (WECSs) that may degrade the overall system performance. Additionally, various severe faults may disconnect some RESs from the hybrid system, like three-phase faults. In this paper, the static synchronous compensator (STATCOM) is considered for both improving the performance of a hybrid system, contains WECS and photovoltaics (PVs) against wind gusts and maintaining the continuous operations of RESs during three-phase fault occur at the point of common coupling (PCC) between the RESs and the grid. The STATCOM is stimulated by two PI controllers regulating the reactive power flow between the STATCOM and the hybrid system at PCC and, consequently, regulating the voltage at PCC. A metaheuristic optimizer optimally schedules these two PI controllers based on whale optimization algorithm (WOA). The impartial comparison between the WOA dynamic performance and the particle swarm optimization as another optimization algorithm verifies the efficiency of the WOA for the near-optimal gain scheduling of the PI controller gains.

The extraction of parameters of solar photovoltaic generating systems is a difficult problem because of the complex nonlinear variables of current-voltage and power-voltage. In this article, a new implementation of the Gorilla Troops Optimization (GTO) technique for parameter extraction of several PV models is created. GTO is inspired by gorilla group activities in which numerous strategies are imitated, including migration to an unknown area, moving to other gorillas, migration in the direction of a defined site, following the silverback, and competition for adult females. With numerical analyses of the Kyocera KC200GT PV and STM6-40/36 PV modules for the Single Diode (SD) and Double-Diode (DD), the validity of GTO is illustrated. Furthermore, the developed GTO is compared with the outcomes of recent algorithms in 2020, which are Forensic-Based Investigation Optimizer, Equilibrium Optimizer, Jellyfish Search Optimizer, HEAP Optimizer, Marine Predator Algorithm, and an upgraded MPA. GTO’s efficacy and superiority are expressed by calculating the standard deviations of the fitness values, which indicates that the SD and DD models are smaller than 1E−16, and 1E−6, respectively. In addition, validation of GTO for the KC200GT module is demonstrated with diverse irradiations and temperatures where great closeness between the emulated and experimental P-V and I-V curves is achieved under various operating conditions (temperatures and irradiations).