A PREDICTIVE MODEL FOR ELECTRICITY CONSUMPTION IN UNIVERSITY CAMPUSES USING ARTIFICIAL NEURAL NETWORKS (A CASE STUDY)

A PREDICTIVE MODEL FOR ELECTRICITY CONSUMPTION IN UNIVERSITY CAMPUSES USING ARTIFICIAL NEURAL NETWORKS (A CASE STUDY)

Abstract:
The efficient management of electricity consumption in university campuses is crucial for sustainability, cost reduction, and environmental impact mitigation. This study presents a predictive model for electricity consumption in university campuses using artificial neural networks (ANNs), with a specific focus on a case study involving a particular university campus.

The proposed model utilizes historical electricity consumption data, along with relevant weather and temporal variables, to forecast future electricity consumption patterns. The ANN architecture employed in this study consists of multiple layers of interconnected nodes, enabling the model to learn complex relationships between input variables and electricity consumption.

To develop the model, a comprehensive dataset comprising historical electricity consumption records, weather data, and temporal information from the university campus was collected and preprocessed. Feature engineering techniques were applied to extract meaningful features, and the data was divided into training, validation, and testing sets.

The developed ANN model was trained using the training dataset and optimized using appropriate algorithms to minimize prediction errors. The validation dataset was used to fine-tune the model's hyperparameters and ensure its generalization capability. Finally, the testing dataset was employed to evaluate the model's performance and assess its accuracy in predicting electricity consumption.

The results of the study demonstrate the effectiveness of the ANN-based predictive model in accurately forecasting electricity consumption on the university campus. The model exhibits a high degree of accuracy and reliability, enabling campus administrators to anticipate electricity demand, optimize energy management strategies, and make informed decisions regarding infrastructure planning and resource allocation.

Furthermore, the study highlights the impact of weather and temporal factors on electricity consumption patterns and reveals the significance of incorporating these variables into the predictive model. By considering weather conditions and temporal characteristics, the model provides more precise and robust predictions, enhancing the overall effectiveness of energy management in university campuses.

In conclusion, this research contributes to the field of energy management in university campuses by presenting a predictive model based on artificial neural networks. The model offers an accurate and reliable tool for forecasting electricity consumption, facilitating sustainable decision-making and efficient resource allocation. Future research may focus on expanding the model's scope to incorporate additional variables and investigating other machine learning techniques to further enhance its predictive capabilities.

A PREDICTIVE MODEL FOR ELECTRICITY CONSUMPTION IN UNIVERSITY CAMPUSES USING ARTIFICIAL NEURAL NETWORKS (A CASE STUDY), GET MORE  COMPUTER SCIENCE PROJECT TOPICS AND MATERIALS

Sharing is caring!