Optimization

This project presents the optimization of solar inverter efficiency using machine learning algorithms to improve power generation accuracy and system reliability under varying environmental conditions. Traditional solar inverter systems and Maximum Power Point Tracking (MPPT) methods often experience limitations in adapting to fluctuations in solar irradiance, temperature, and shading conditions, leading to reduced efficiency and energy loss. To address these challenges, this study developed and evaluated machine learning models capable of predicting and optimizing inverter performance in real time. Environmental and operational data including irradiance, temperature, day, hour, and inverter performance metrics were collected from the NASA and NSRDB datasets for the University of Benin region. Data preprocessing techniques such as normalization, interpolation, and feature engineering were applied before model training. Three machine learning models — Random Forest (RF), Gradient Boosting Machine (GBM), and Artificial Neural Network (ANN) — were implemented and evaluated using Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Coefficient of Determination (R²). Results showed that the ANN model outperformed the other models with an MAE of 0.019, RMSE of 0.029, and R² value of 0.962. The optimized system achieved an efficiency improvement of 8.3% compared to conventional MPPT methods. The study further demonstrated the capability of machine learning algorithms to adapt to changing environmental conditions and improve solar inverter performance. The developed model was deployed using Django REST Framework for real-time prediction and monitoring. This research confirms that machine learning-based optimization can significantly enhance solar inverter efficiency, reduce energy losses, and contribute to sustainable and intelligent renewable energy systems.

This project investigates the effect of key drilling parameters on Rate of Penetration (ROP) using real-world field data from a selected well. The parameters analyzed include Weight on Bit (WOB), Rotational Speed (RPM), and mud properties such as Plastic Viscosity, Yield Point, and Gel Strength. The study aims to understand how variations in these parameters influence ROP and to identify combinations that could
enhance drilling efficiency. Microsoft Excel was used for organizing, calculating, and analyzing the data, with additional tools such as Solver applied for basic optimization. By focusing on a practical, data-driven approach, this work contributes to ongoing efforts in optimizing drilling operations, especially in regions where advanced software and models may be inaccessible. The findings provide insight into the practical relationships between operational parameters and ROP, and highlight opportunities for performance improvement in similar field environments

Given Nigeria's abundant agro-industrial wastes, the study focused on optimizing a ternary blend of cassava peels (CP), coconut husk (CH), and sawdust (SD) to maximize bioethanol yields. Unlike previous studies that examined these feedstocks individually, this work investigated their co-processing potential to overcome disposal challenges and enhance their utilization. The characterization of the feedstocks revealed diverse compositions: CP was rich in hemicellulose, CH presented a balanced composition, and SD was cellulose-rich but highly recalcitrant due to its high lignin content. Utilizing a {3,2} Simplex Lattice Design (SLD) across 15 experimental runs, a Special Quartic model was developed to elucidate the relationship between blend ratios and sugar yield. This model demonstrated high significance (F-value = 88.93, p < 0.0001) and an excellent fit (R² = 0.9916), highlighting substantial synergistic interactions, especially between CP and CH. The optimized blend, consisting of 66.7% CP, 16.7% CH, and 16.7% SD, yielded an impressive experimental sugar yield of 370.31 mg/g, which significantly surpassed the yields from individual feedstocks. Subsequent validation of this optimized blend involved acid pretreatment, enzymatic hydrolysis, and fermentation using Saccharomyces cerevisiae, resulting in an experimental ethanol yield of 0.0644 g ethanol/g biomass. This achievement represents 85.4% of the theoretical yield, confirming a high fermentation efficiency and validating the strategic blending as an effective waste-to-wealth strategy for sustainable bioenergy production

Optimization of process parameter to improve on weld joint quality has been at the centre of global research. Some optimization methods have produced welds of low strength and quality whereas , some have made remarkable improvements on the quality of welded joints. In this study, the SWARA-ARAS method was adopted to access its effect on the quality of the obtained welded joints. Stepwise Weight Assessment Ratio Analysis (SWARA) method was used to determine the geometric mean of weights for each of the output parameters that is the mechanical test and measurement results. Additive Ratio Assessment (ARAS) was applied to optimize these parameters by utilizing the weights generated by using SWARA. From applying the SWARA-ARAS method, weldment was found to possess the best input and output parameters

In this era, the best problem solving method is needed in all field irrespective of the complexity or simplicity of the problem. Researchers and developers are doing their best to make software’s and machines more potent and intelligent. This is the advantage of artificial intelligent in developing solutions to searching algorithms that are potent and optimal. The most potent highly developed investigate method in Artificial Intelligence is the genetic algorithm. Genetic algorithm was developed to get best result to a known difficulty premised on inheritance, collection, crossover, mutation and further method. It has been proven that genetic algorithm is the most potent, impartial optimization method for analyzing a solution with large space. this research have been able to define what is genetic algorithm, how it differs from other existing traditional search optimization method, review of ten (10) traditional techniques of finding the best route in a given network. Also the design of genetic algorithm, it’s implementation on finding the best route within 20 cities (point) which is invariably the travelling salesman problem (TSP), and areas of application of application of genetic algorithms. The best route is invariably the shortest path.