Search

Forecasting of load is essential for operating power systems. India recently witnessed one of the worst power crisis with the highest ever power demand of 207 GW on April 29, 2022. The demand in the month of May and June 2022 was estimated to reach 215 GW. The peak demand this year 2023, according to the electricity ministry, is predicted to be around 230 GW from April to June. The inability to meet certain fundamental issues as power can take a toll on any country's economy. Proper prediction helps in proper decision making and planning. The main objective of this paper is to predict day ahead electrical load demand for Assam. Statistical and Machine Learning Algorithms has been studied. The study has been carried out using real-time data for the years 2016, 2017 and 2018. The paper presents a detailed analysis of the different hyper parameters of the deep learning models and their effect is seen on the learning efficiency. A novel stacked forecasting model is proposed using neural networks as base learners and CatBoost as the meta-learner. The performance of the proposed model has been evaluated and compared with individual models in terms of training time and accuracy using different error metrics namely MAE, MSE, RMSE, MAPE and R2 score. A comparison of the proposed prediction model with the prediction models available in literature has been presented. The conclusion states that both the statistical and machine learning algorithms used in this study act as useful tools for daily load forecasting with considerable accuracy; yet machine learning algorithm outperforms the statistical methods. The entire work has been done in Google Colaboratory using Python as the programming language. [ABSTRACT FROM AUTHOR]

Human-animal conflict in Assam, India's north-eastern state, is rising continuously. Because it occurs year-round, it damages agricultural productivity and kills people and animals, including elephants. When a herd of wild elephants emerges from a deep forest and enters human-inhabited territory around the Kaziranga National Park (KNP) in Assam, an alert must be sounded for the neighbourhood residents and forest workers to prevent conflicts. Another concern is that many wild animals die near the KNP while crossing the national highway NH-37 which traverses the area. During floods, animals flee to the highlands for food and shelter. An automated animal identification and warning system near the KNP may reduce human-animal confrontations. This paper reports the design of a system that attempts to address the above concerns. Artificial Intelligence (AI)-based strategies are utilized to recognize wild animals from live video sequences, provide warnings to avoid encounters, and protect humans and animals. Deep learning models and YoloV5 with the SENet attention layer are used to recognize wild animals in real-time. This model is trained using a public and customized dataset of animal species. Cameras attached to the cloud-based AI system take photographs from several KNP locations to confirm the model. The model's 96% accuracy in animal photographs and videos taken day and night and in feed from contemporaneous location has shown its utility. The model also improves reliability by 1–13% over previous methods. • Efficient real-time wild animal detection system designed using YOLOv5 and SENet attention layer. • The model enhances detection accuracy using fine-grain features of the object, enabling the detection of a diverse class of animals captured with varied illumination, distance, and background variations with the provision of auto-alarm generation. • Better detection rate is obtained by weighing noisy channels and focusing on specific feature sets using the SENet attention layer. [ABSTRACT FROM AUTHOR]