COMPUTER ENGINEERING

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 presents the design and development of a web-based portfolio site offering software solutions. The system was conceived to provide a professional online platform for individuals or organizations to showcase their technical expertise, previous projects, and range of offered services. The growing dependence on digital platforms for business visibility has made online portfolios a vital tool for branding and client engagement. The project was implemented using a combination of front-end technologies — HTML for content structure, CSS for styling, and JavaScript for interactivity — while Django, a
Python-based web framework, was employed for back-end development and server-side processing. PostgreSQL was used as the database management system to ensure reliable data storage and retrieval.
The website features multiple modules, including a landing page, services page, about page, contact form, and an administrative dashboard for managing content. Additional functionalities such as user authentication, task management for the development team, and an integrated payment system were incorporated to extend the platform’s usability for both clients and administrators. The system was tested manually to ensure that all modules functioned according to specification, and results confirmed efficient performance, responsiveness, and ease of navigation. Overall, the project successfully demonstrates the application of modern web technologies in developing an interactive and dynamic portfolio website capable of promoting professional services online. It provides a scalable foundation that can be
extended in the future to include advanced content management, analytics integration, and broader service offerings.
Keywords: Portfolio Website, Django, Web Development, Software Solutions, Database
Management, HTML, CSS, JavaScript, PostgreSQL.

The aim of this paper is to design and develop an IoT based Smart Monitoring System. The purpose of the current method is to create a safe and secure fish farming that helps the fish pond owners in producing high quality fish by maintaining normal water levels in the fish tank. (Sajal Saha, 2007). In order to implement this design, the Atmega 328p microcontroller is used as well assensors and actuators such as the DSB18b20 temperature sensor, HC-sr04 ultrasonic sensor, HC- sr501 motion sensor and a solenoid valve to automate the process of controlling the water quality parameters, such as the water level, temperature which is best at 24-27 oc (Johnson et al.,2007) and PH range which is acceptable at 6.5 to 9.0 (Will Mosley, 2009). These sensor values are stored in cloud so that farmers can see on their mobiles through mobile app or web application anywhere remotely. Android phone is used as the terminal device. A user can monitor the water condition using an android app through Wi-Fi within Wi-Fi range of 2400-2484 MHz and through Internet from anywhere in the world, A significant cost reduction is achieved as a result of farm equipment and water pumps being operated only when required using optimization schemes to maintain desired waterlevel in fish tank with efficient energy consumption through appropriate selection of pumps and tank filling level (Nirosha et al, 2017). The system consists of various sensors that measure important factors of the water like temperature, pH and water level and the data from these sensors can be accessed by an application through firebase (Weber et al, 2010). The farmer can then act as per the information relayed or the model can automatically act on behalf of the farmer as per the predefined actions. The real time information enables timely intervention by the farmers which eventually helps minimizing or eliminate wastages.

This work presents the development of an intelligent software solution for the design and optimization of solar energy systems. The system integrates key variables such as solar panel efficiency, geographic location, battery storage requirements, and peak load consumption to generate optimized configurations tailored to user needs. The tool supports both mobile and desktop platforms, providing an intuitive graphical user interface (GUI) for real-time analysis and seamless data input. The software features a comprehensive cost-benefit analysis module that compares the initial investment with projected long-term savings in energy costs. The software architecture is layered and modular. The GUI Layer enables users to simulate various solar system configurations, input energy requirements, geographic location, budget, and preferences for renewable energy components (e.g., solar panels, batteries, inverters). It provides actionable recommendations, displays optimized system designs, cost estimates, and generates detailed reports. The Data Layer consists of databases that store critical information, including solar irradiance data, energy consumption profiles, technical specifications of solar components, and pricing information. Data sources include third-party APIs, cloud storage, and local servers. The system also features a dynamic database of available solar products and real-time pricing updates through integrated APIs. The Computation and Simulation Layer simulates energy production, consumption, and storage across different scenarios, leveraging historical weather data and user consumption profiles to predict long-term system performance. Mathematical models were developed to establish the relationships among system components and to optimize system parameters for cost-effectiveness and reliability. These models were implemented using the Django framework and simulated via MATLAB. They form the core of the software's computation and optimization engine. The Optimization Engine, which utilizes advanced algorithms to compute the most efficient and cost-effective solar architecture. It processes user inputs, environmental data, and component specifications to determine optimal combinations of solar panels, batteries, and inverters. Lastly, the Back-End Services Layer manages the interaction between the user interface, optimization engine, and data storage. These services ensure smooth data flow, handle computation requests, and deliver results to the user in real time. The GUI was developed using the HTML, CSS and JavaScript’s framework, with MySQL used for database management. Designed for both residential and commercial applications, the tool streamlines decision- making for installers, energy consultants, and property owners. Its flexibility in accounting for various renewable energy sources and its detailed recommendations for system sizing and 5 installation positions it as a valuable resource for optimizing both performance and budget in solar energy projects. The software-optimized PV system configuration delivers significant performance and financial benefits, achieving 15–20% higher energy output and 90–95% battery utilization through intelligent energy management. By optimizing system design, it reduces upfront component costs by 10–15% and saves 8–10% on labor and materials during installation. End users experience 20–25% lower energy bills and 30–35% reduced grid dependency thanks to efficient load balancing and storage cycling, making it an ideal solution for both residential and commercial applications. Additionally, the tool provides key financial metrics such as return on investment (ROI), levelized cost of energy (LCOE), and payback period empowering informed decision-making. Field validation from over 150 survey respondents in Nigeria confirmed the tool’s user-friendliness and the strong market need for an integrated solar optimization platform. These results demonstrate a cost-effective, high- performance solution that enhances energy efficiency, cuts operational expenses, and accelerates the adoption of sustainable solar power

This project presents a comprehensive analysis of the deployment strategies involving serverlessand non-serverless hosting infrastructure within the context of Software as a Service (SaaS)implementation. The rapid advancements in cloud computing have introduced newparadigmsforhosting applications, and the comparison of serverless and non-serverless(traditional) hostingapproaches has gained significant attention in recent years. This study aims to evaluatetheperformance, scalability, cost-efficiency, and resource utilization of both serverless andnon-serverless architectures in the context of deploying SaaS applications with an implementationinthe form of an e-commerce site. The research methodology encompasses a series of experiments conducted on real-worldscenarios using popular cloud platforms. Performance metrics, such as response time, throughput, and scalability, are carefully measured and analyzed. Additionally, the consumptionofcomputing resources and associated costs are thoroughly assessed to provide a comprehensiveview of the two hosting infrastructures. The trade-offs between the two approaches are discussed, and guidelines are provided to aid decision-making processes when selecting the most appropriate hosting infrastructure for specific SaaS applications. The findings indicate that serverless hosting exhibits several advantages in terms of auto-scalability, reduced operational complexity, and cost-effectiveness for applications withvaryingworkloads. On the other hand, non-serverless hosting demonstrates better performanceinscenarios with predictable and consistent demands.

Renewable energy sources are a practical solution for addressing the ongoing supply gap in the power industry. Because of the availability of solar energy throughout the world, unlike other geographically restricted resources, solar energy is most beneficial of all renewable energy resources. The Internet of Things can be seen as a network of physical objects, which have access to the internet and communicate with each other sharing and collecting data (Madadi, 2021) . The application of this technology in solar panels can greatly enhance the monitoring, performance and maintenance of the panel. Since the greater part of them are set in areas that are inaccessible and therefore monitoring them is not possible from a specific location. Sophisticated frameworks for remote monitoring of the plant using web-based interface is required for this massive scale of solar system deployment systems. In this project, an online report station for solar energy plant was developed. The system was designed using three major layers of IOT architecture, which are perception layer, network layer, and application layer. The perception layer contains the sensor devices. This layer reads the value of the monitored parameters and converts it from analog to a digital signal. Three parameters, voltage, temperature and humidity are measured using Resistive voltage sensor, DHT11.The network layer acts as a gateway using a wireless network architecture like Wi-Fi. It receives the data from the perception layer and routes the data to the cloud using ESP8266. The
application layer delivers the processed data to the user in an interface the user can interact with. This project entails the design and implementation of an online report station that is capable of monitoring the status, condition and generated output of a solar energy plant. Three parameter, voltage, temperature and humidity are measured using the designed system. The result is displayed on the developed webpage and can be access by the user.

Renewable energy sources are a practical solution for addressing the ongoing supply gap in the power industry. Because of the availability of solar energy throughout the world, unlike other geographically restricted resources, solar energy is most beneficial of all renewable energy resources. The Internet of Things can be seen as a network of physical objects, which have
access to the internet and communicate with each other sharing and collecting data (Madadi, 2021) . The application of this technology in solar panels can greatly enhance the monitoring, performance and maintenance of the panel. Since the greater part of them are set in areas that are inaccessible and therefore monitoring them is not possible from a specific location. Sophisticated frameworks for remote monitoring of the plant using web-based interface is required for this massive scale of solar system deployment systems. In this project, an online report station for solar energy plant was developed. The system was designed using three major layers of IOT architecture, which are perception layer, network layer, and application layer. The perception layer contains the sensor devices. This layer reads the
value of the monitored parameters and converts it from analog to a digital signal. Three parameters, voltage, temperature and humidity are measured using Resistive voltage sensor, DHT11.The network layer acts as a gateway using a wireless network architecture like Wi-Fi. It receives the data from the perception layer and routes the data to the cloud using ESP8266. The
application layer delivers the processed data to the user in an interface the user can interact with. This project entails the design and implementation of an online report station that is capable of monitoring the status, condition and generated output of a solar energy plant. Three parameter, voltage, temperature and humidity are measured using the designed system. The result is displayed on the developed webpage and can be access by the user

Because of the disadvantages linked with the utilization of fossil fuels, eventually a rising interest in increasing the adoption of renewable energy systems. Nonetheless, integrating renewable energy systems into the grid poses numerous challenges concerning constancy, consistency, system operation, and power quality. Lesser hybrid renewable energy systems (HRES) are compact power systems that encompass energy sources and storage units to efficiently manage energy production and consumption. Real-time monitoring of HRES is crucial as it provides precise data for the system operator to assess overall performance and detect any anomalies. In this study, an IoT-based design for HRES is presented, comprising a wind turbine and a photovoltaic system. The suggested design comprises four distinct layers: power, data collection, communication network, and application. Given the wide display of communication technologies available and the lack of a standardized communication framework for HRES (Hybrid Renewable Energy Systems), this study introduces communication models specifically customized for HRES. The monitoring factors are grouped into three categories: electrical, grade, and environmental data. Additionally, the research incorporates network modeling and mockup, with special responsiveness to vital features like network arrangement, link capacity, and latency, all of which are widely analyzed and discussed. Besides, the collective interest in renewable energy systems is driven by the awareness of the downsides connected with the widespread use of remnant fuels, such as pollution and climate change. Governments, industries, and individuals have recognized the urgency to transition on the way to cleaner and more viable energy sources. As renewable energy systems become more prevalent, the integration of these systems into the existing power grid becomes a complex and multifaceted challenge. The successful integration requires addressing issues related to structure operation, ensuring steadiness and consistency, and continuing high power value to meet the demands of consumers. Small hybrid renewable energy systems (HRES) have emerged as a viable solution to harness energy from multiple sources and manage it efficiently. These compact systems