The growing interest in renewable energy and the falling prices of solar panels place solar electricity in a favourable position for adoption. However, the high-rate adoption of intermittent renewable energy introduces challenges and the potential to create power instability between the available power generation and the load demand. Hence, accurate solar Photovoltaic (PV) power forecasting is essential to maintain system reliability and maximize renewable energy integration. The current solar PV power forecasting approaches are an essential tool to maintain system reliability and maximize renewable energy integration. This paper presents a comprehensive and comparative review of existing Machine Learning (ML) based approaches used in PV power forecasting, focusing on short-term horizons. We provide an overview of factors affecting solar PV power forecasting and an overview of existing PV power forecasting methods in the literature, with a specific focus on ML-based models. To further enhance the comparison and provide more insights into the advancement in the area, we simulate the performance of different ML methods used in solar PV power forecasting and, finally, a discussion on the results of the work.

Feature extraction (FE) is an important step in image retrieval, image processing, data mining and computer vision. FE is the process of extracting relevant information from raw data. However, the problem of extracting appropriate features that can reflect the intrinsic content of a piece of data or dataset as complete as possible is still a challenge for most FE techniques. In this paper, we present a survey of the existing FE techniques used in recent times. In this study, it was observed that the most unique features that can be extracted when using GLDS features on images are contrast, homogeneity, entropy, mean and energy. In addition, it was observed that FE techniques are not mainly application specific but can be applied to several applications.

This paper presents an optimal method for optimizing network reconfiguration (NR) problems in a power distribution system (PDS) for the purpose of power loss reduction and voltage profile (VP) improvement. Furthermore, a modified algorithm was presented to address this problem in order to provide a more efficient PDS. Various works which used NR to improve VP and reduce power loss were discussed and summarized in detail. In particular, a modified Selective particle swarm optimization (SPSO) method was used for NR in existing networks considering different loading conditions. The main objective of this study is to minimize real power losses and enhance VP of a distribution system using the proposed SPSO method. The SPSO method was programmed in MATLAB R2016b software and tested using IEEE 33-bus radial distribution system (RDS). The obtained test results show that the real power was enhanced by 99.341%, 97.289%, and 95.389% for the light, normal, and heavy load conditions, respectively. Also, the minimum voltage level in the worst case was significantly enhanced from 0.8841 p.u. to 0.9510 p.u. Towards the end, a comparative analysis of the proposed SPSO with existing methods for distribution network reconfiguration (DNR) is presented. The comparative results show that the proposed SPSO was found to be more efficient in reducing voltage deviation (VD) and power losses in the system.

Internet of Things (IoT) denotes a system of interconnected devices equipped with processors, sensors, and actuators that capture and exchange meaningful data with other smart systems. IoT technology has been successfully applied across various sectors, including agriculture, supply chain management, education, healthcare, traffic control, and utility services. However, the diverse range of IoT nodes introduces significant security challenges. Common Internet of Things safety features like encryption, authentication, and access control frequently fall short of meeting their desired functions. In this paper, we present a novel perspective to IoT security by using a Graph-based (GB) algorithm to construct a graph that is evaluated with a graph-based learning Intrusion Detection System (IDS) incorporating a Graph Attention Network (GAT). In addition, we leveraged a small benchmark NSL-KDD dataset to conduct detailed performance evaluation of the GNN model by focusing on essential key metrics such as F1-score, recall, accuracy, and precision to guarantee comprehensive analysis. Our findings validate the effectiveness of the GNN-based IDS in detecting intrusions, which highlights its robustness and scalability in mitigating the evolving security challenges within IoT systems.