Abstract:
With the increasing demand for sustainable energy practices and the rising cost of electricity, accurate prediction of electricity consumption in university campuses has become crucial for efficient resource management and cost optimization. This abstract presents a predictive model that utilizes artificial neural networks (ANNs) to forecast electricity consumption in university campuses.
The proposed model leverages historical electricity consumption data, weather conditions, academic calendars, and other relevant factors as input features for training the neural network. The data is preprocessed to handle missing values, outliers, and normalization. The ANN architecture is designed to capture complex nonlinear relationships between the input features and electricity consumption patterns.
The training process involves an iterative optimization algorithm to adjust the network’s weights and biases, minimizing the prediction error. The model is validated using a holdout dataset, and performance metrics such as mean absolute error (MAE) and root mean square error (RMSE) are calculated to evaluate its accuracy.
The results demonstrate that the developed predictive model using ANNs can effectively forecast electricity consumption in university campuses. The model exhibits high accuracy, capturing both short-term and long-term consumption patterns. By accurately predicting electricity demand, universities can proactively manage energy resources, optimize energy usage, and reduce costs. This enables the implementation of energy-saving strategies, load balancing, and peak-demand management.
The proposed model contributes to sustainable energy management in university campuses by providing decision-makers with timely and accurate information for energy planning, infrastructure upgrades, and resource allocation. Furthermore, it serves as a foundation for developing intelligent energy management systems that can optimize electricity consumption based on real-time data, weather forecasts, and other dynamic factors.
The research highlights the potential of artificial neural networks as a powerful tool for predicting electricity consumption in university campuses and lays the groundwork for future research in energy forecasting and optimization. By leveraging advanced data analytics techniques, universities can make informed decisions to reduce their environmental footprint and promote sustainable practices in campus operations.
AN IMPLEMENTATION OF A PREDICTIVE MODEL FOR ELECTRICITY CONSUMPTION IN UNIVERSITY CAMPUSES USING ARTIFICIAL NEURAL NETWORKS, GET MORE COMPUTER SCIENCE PROJECT TOPICS AND MATERIALS
