Browsing by Author "Bilkisu Jimada Ojuolape"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    AI-driven demand forecasting for enhanced energy management in renewable microgrids: A hybrid lstm-cnn approach
    (WisdomGale., 2024-12-29) Bashiru Olalekan Ariyo; Lambe Mutalub Adesina; Olalekan Ogunbiyi; Abdulwaheed Musa; Bilkisu Jimada Ojuolape; Monsurat Omolara Balogun
    The increasing integration of renewable energy sources into microgrids (MGs) underscores the need for accurate demand forecasting to ensure stable and efficient MG operation. However, the inherent unpredictability of renewable energy sources presents significant challenges in energy management. This study aims to develop and validate an AI-driven demand forecasting model that improves prediction accuracy compared to traditional methods, thereby enhancing energy management in renewable MGs. A hybrid forecasting model that combines long short-term memory (LSTM) networks and convolutional neural networks (CNNs) was proposed. The model leverages historical energy consumption and meteorological data for training, ensuring robust and accurate predictions. Data preprocessing, training, and validation were performed meticulously to evaluate performance. The proposed model was compared with traditional forecasting techniques, including ARIMA and Exponential Smoothing, to assess its accuracy. The hybrid LSTM-CNN model demonstrated superior performance, achieving an R2 value of 0.87, a mean absolute error of 1.45 MWh, and a root mean squared error of 2.12 MWh. These results significantly outperform conventional forecasting methods, such as ARIMA and exponential smoothing, highlighting the model’s enhanced accuracy and ability to address key challenges in renewable energy forecasting. This study establishes the effectiveness of the hybrid LSTM-CNN approach in terms of improving the demand forecasting of renewable MGs. The model’s superior accuracy provides a reliable tool for real-time decision-making, energy distribution optimization, and cost reduction. Policymakers and energy stakeholders can use these insights to develop sustainable energy systems, with future research focusing on scaling up the model and exploring behavior and market pricing to improve forecasting precision.
  • Thumbnail Image
    Item
    Comparative Performance Evaluation Of Open Shortest Path First, OSPF And Routing Information Protocol, RIP In Network Link Failure and recovery cases
    (2017 IEEE 3rd International Conference on Electro-Technology for National Development (NIGERCON), 2017-05-20) Ayodeji Akeem Ajani; Bilkisu Jimada Ojuolape; Abdulkadir A. Ahmed; Tahir Aduragba; Balogun Monsurat
    The effect of Network link failure is undesirable which necessitated redundant links for reliability. This implies that operations are switched between links in case of failure. In the modern world where speed matters, it is important to investigate how quickly different routing protocols, in this case, Open Shortest Path First, OSPF and Routing Information Protocol, RIP recovers in case of link failure in a mesh topology. The research was simulated using OPNET. It was modelled after the University of Salford main campus, using three of its building, Newton, Peel and CW library. There were several links in between the buildings. There network was configured for the two routing protocols in different scenarios to test for their performance in case of single and multiple link(s) failure and recovery. It was observed that RIP converges faster (11.21s) than OSPF (53.06s) at the initial stage of the network in all cases. However, OSPF converges faster (Average of 5s – link failure, Average of 15s – Link recovery) than RIP (Average of 18.57s- link failure, Average of 18.28s – link recovery) in both single and multiple link(s) failure/recovery scenarios.Therefore, based on the performance comparison, OSPF should be used in a network prone to frequent link failure as it performs better in this situation. However, RIP would be preferred