arXiv subjects

Salim Oyinlola

Publications and source records attributed to Salim Oyinlola.

3 recordsLinked to original sources

arXiv2026

Time Series Based CO2 Emission Forecasting and Energy Mix Analysis for Net Zero Transitions: A Multi Country Study

This study examines long-term CO$_2$ emission trajectories across five major economies: Nigeria, the United States, China, Brazil, and Russia, by integrating national energy-mix characteristics with time-series forecasting models. Annual emissions from 2000-2023 were analyzed alongside energy production data to classify countries into fossil-dependent, transition-phase, or renewable-accelerated profiles. Three forecasting models (ARIMA, SARIMA, and Holt-Winters exponential smoothing) were evaluated using MAE, RMSE, MAPE, and R$^2$ metrics. Results show that Holt-Winters provided the most accurate forecasts for Nigeria, the United States, China, and Brazil, while SARIMA performed best for Russia due to its relatively stable emissions. Long-term projections from 2024 to 2060 indicate divergent decarbonization pathways. Brazil aligns most closely with a low-emission future owing to its renewable-dominant energy system, whereas Nigeria continues on an upward emissions trajectory driven by fossil dependence. The United States and China maintain moderate declines but require accelerated mitigation to reach their respective net-zero commitments. Russia's emissions remain largely flat under current conditions. These findings highlight the strong influence of energy structures on national decarbonization prospects and underscore the need for targeted energy policy reforms to align with global climate objectives.

eess.SY↗

arXiv2025

Machine Learning for Campus Energy Resilience: Clustering and Time-Series Forecasting in Intelligent Load Shedding

The growing demand for reliable electricity in universities necessitates intelligent energy management. This study proposes a machine learning-based load shedding framework for the University of Lagos, designed to optimize distribution and reduce waste. The methodology followed three main stages. First, a dataset of 3,648 hourly records from 55 buildings was compiled to develop building-level consumption models. Second, Principal Component Analysis was applied for dimensionality reduction, and clustering validation techniques were used to determine the optimal number of demand groups. Mini-Batch K-Means was then employed to classify buildings into high-, medium-, and low-demand clusters. Finally, short-term load forecasting was performed at the cluster level using multiple statistical and deep learning models, including ARIMA, SARIMA, Prophet, LSTM, and GRU. Results showed Prophet offered the most reliable forecasts, while Mini-Batch K-Means achieved stable clustering performance. By integrating clustering with forecasting, the framework enabled a fairer, data-driven load shedding strategy that reduces inefficiencies and supports climate change mitigation through sustainable energy management.

eess.SY↗

arXiv2025

Reinforcement Learning for Autonomous Point-to-Point UAV Navigation

Unmanned Aerial Vehicles (UAVs) are increasingly used in automated inspection, delivery, and navigation tasks that require reliable autonomy. This project develops a reinforcement learning (RL) approach to enable a single UAV to autonomously navigate between predefined points without manual intervention. The drone learns navigation policies through trial-and-error interaction, using a custom reward function that encourages goal-reaching efficiency while penalizing collisions and unsafe behavior. The control system integrates ROS with a Gym-compatible training environment, enabling flexible deployment and testing. After training, the learned policy is deployed on a real UAV platform and evaluated under practical conditions. Results show that the UAV can successfully perform autonomous navigation with minimal human oversight, demonstrating the viability of RL-based control for point-to-point drone operations in real-world scenarios.

cs.RO↗