What it does
The study will assess the economic benefits, reduce carbon emissions, minimize environmental degradation, and improve land use efficiency. With the combination of AI and CFD, it aims to improve renewable energy while supporting agriculture.
Your inspiration
1. Developing AI algorithms that will identify trends and patterns for optimization of energy yield in an agrivoltaics system. 2. To implement predictive maintenance strategies that will use process-collected sensor data to identify potential faults and risks before they occur. 3. Identifying AI and machine learning for early detection of potential issues for predictive maintenance of bifacial solar panels. 4. To integrate CFD simulations that will minimize performance disruptions caused by wind, temperature fluctuations, or duct accumulations.
How it works
(A) Data preprocessing: This is a process of collecting indoor data to ensure quality and make decisions. The sensor network will be installed on the bifacial solar to collect solar irradiance, shading conditions, temperature, humidity, and wind speeds. The preprocess data will ensure consistency, remove anomalies, and transform it into an AI-useable format. (B) Feature selection: To identify the features that may impact energy yield, like the panel configuration, weather conditions, and maintenance history. (C) Model selection: Applying AI algorithms for energy optimization, like regression analysis, neural networks, and decision trees (D) Developing AI-Powered Optimization Models: Predict predictive maintenance of the bifacial solar panel performance using machine algorithms like regression models, neural networks, and decision trees.
Design process
1. Data Collections (A) Panel-specific performance data: Current, Voltage, and resistance. They are used for solar panel monitoring and for identifying performance issues. (B) Meteorological data: wind speed, temperature fluctuations, solar irradiance, humidity, and cloud cover. These are used for analyzing environmental factors affecting the bifacial panel performance. 2. Computational Fluid Dynamics (CFD) Model Development A) Model Design: To evaluate the scope and complexity of the CFD model like the accurate size of the bifacial solar panel array, and the surrounding environment. (B) Geometry Creation: To determine the geometrical bifacial solar panel array and its surrounding environment using CFD software. C) Mesh Generation: The model geometry will be divided into small elements known as a mesh, which will enable the CFD solver to numerically approximate the behaviour of the fluid inside the domain (D) Model Setup: The fluid properties and the boundary conditions relevant for the CFD analysis will be defined, like the temperature, wind speed, and turbulence models. 3. Artificial Intelligence (AI) powered Computational Fluid Dynamics (CFD) (A) Data Exchange: The data exchange will utilize AI models and inform the CFD the potential failure.
How it is different
The difference is that I am using a computational fluid dynamics simulation together with artificial intelligence while previous works used machine learning techniques.This research will adopt a different methodological approach, including AI Algorithms for Energy yield optimization, data Collections, and computational fluid dynamics (CFD) model Development.By applying AI and CFD, this research will implement predictive maintenance strategies for bifacial solar panels in agrivoltaics systems, which will reduce downtime and increase the energy yield by detecting potential issues The CFD simulations will enable the airflow analysis in the bifacial solar panels, providing insights into the effects of wind turbulence, and optimizing panel configuration layouts to maximize energy yield efficiency and reduce maintenance needs.
Future plans
This research will contribute to a better understanding between bifacial solar panels, environmental conditions, and the agricultural activities in an agrivoltaics system with collected data and simulations, to provide insights into the factors that affect maintenance requirements and energy yield. This research work will increase energy efficiency and energy production in agrivoltaics systems. It will support and contribute to renewable energy transmission. The energy yield improvement and reduced maintenance save costs for agrivoltaics systems operators.
Share this page on