The study of power load forecasting is gaining greater significance nowadays, particularly with the use and integration of renewable power sources and external power stations. Power forecasting is an important task in the planning, control, and operation of utility power systems. In addition, load forecasting (LF) aims to estimate the power or energy needed to meet the required power or energy to supply the specific load. In this article, we introduce, review and compare different power load forecasting techniques. Our goal is to help in the process of explaining the problem of power load forecasting via brief descriptions of the proposed methods applied in the last decade. The study reviews previous research that deals with the design of intelligent systems for power forecasting using various methods. The methods are organized into five groups—Artificial Neural Network (ANN), Support Vector Regression, Decision Tree (DT), Linear Regression (LR), and Fuzzy Sets (FS). This way, the review provides a clear concept of power load forecasting for the purposes of future research and study.

Off-grid power systems are often used to supply electricity to remote households, cottages, or small industries, comprising small renewable energy systems, typically a photovoltaic plant whose energy supply is stochastic in nature, without electricity distributions. This approach is economically viable and conforms to the requirements of the European Green Deal and the Fit for 55 package. Furthermore, these systems are associated with a lower short circuit power as compared with distribution grid traditional power plants. The power quality parameters (PQPs) of such small-scale off-grid systems are largely determined by the inverter’s ability to handle the impact of a device; however, this makes it difficult to accurately forecast the PQPs. To address this issue, this work compared prediction models for the PQPs as a function of the meteorological conditions regarding the off-grid systems for small-scale households in Central Europe. To this end, seven models—the artificial neural network (ANN), linear regression (LR), interaction linear regression (ILR), quadratic linear regression (QLR), pure quadratic linear regression (PQLR), the bagging decision tree (DT), and the boosting DT—were considered for forecasting four PQPs: frequency, the amplitude of the voltage, total harmonic distortion of the voltage ($TH{D}_u$), and current ($TH{D}_i$). The computation times of these forecasting models and their accuracies were also compared. Each forecasting model was used to forecast the PQPs for three sunny days in August. As a result of the study, the most accurate methods for forecasting are DTs. The ANN requires the longest computational time, and conversely, the LR takes the shortest computational time. Notably, this work aimed to predict poor PQPs that could cause all the equipment in off-grid systems to respond in advance to disturbances. This study is expected to be beneficial for the off-grid systems of small households and the substations included in existing smart grids.

Accurate and reliable load forecasting is a very important and required task conditioning the operation and management of electrical power generation systems. It is a key issue especially in planning and controlling the power grid system. The load forecasting process makes part of a smart control system. In off-grid platforms, smart control systems are needed to keep the consumed power equal to generated power as well as to maintain the power quality at standard levels of power quality parameters. Many mathematical models have been designed for load forecasting, including artificial neural network (ANN), decision tree (DT), support vector machine (SVM), fuzzy sets, etc. Still, the power load forecasting remains an open issue. In this article, we introduce an intelligent approach that predicts electrical load using data taken from an off-grid platform. The proposed approach builds on four models, namely K-means with ANN, K-means with DT, K-medoids with ANN, and K- medoids with DT. The article describes the design of these four forecasting models and compares them. The simulation results of the four models were evaluated and compared using mean absolute percentage error (MAPE) criteria. The best forecasting results were obtained using K-medoids clustering combined with ANN, where the MAPE was about 8%.

This study delves into selective laser melting (SLM). By using M300 steel in virgin and recycled powder form (after 20 cycles), with the aim of reducing the cost of printing for the practical application of M300 maraging steel, a comprehensive comparison between the two types of powder was evaluated. The powder’s morphology was analyzed using scanning electron microscopy (SEM) and backscattered electrons (BSE). The particles were seen to have a spherical shape, with a notable number of satellites attached to their surfaces. The particle size distribution (PSD) was examined and ranged from 10 to 90 µm for both powders. In addition, the porosity exhibited an average value of 0.07% for the virgin powder and 0.10% for the recycled powder. The microstructure was examined. Additionally, the surface wettability was tested, and it was seen to display wetting behavior for both types of powder, while blackened surfaces showed a higher wetting angle than untreated surfaces (hydrophobic). The 2D roughness measurements showed that the recycled powder had no significant difference from the virgin powder (Ra = 5.33 µm, Rz = 24.17 µm) before blackening and (Ra = 5.48 µm, Rz = 24.07 µm) after blackening. Corrosion tests proved that the recycled powder did not affect the corrosion properties of the material, while blackening caused partial surface corrosion in both types of samples, regardless of the used powder.

Similarity Analysis of EEG Data Based on Self Organizing Map Neural Network