Irrigated Agrovoltaic System Using Multivariate Intelligent Control Techniques

• Grant number: 25/05905-9
• Support Opportunities: Scholarships in Brazil - Post-Doctoral
• Start date: June 01, 2025
• End date: May 31, 2027
• Field of knowledge: Interdisciplinary Subjects
• Principal Investigator: Jurandir Zullo Junior
• Grantee: Fabricio Theodoro Soares
• Host Institution: Centro de Pesquisas Meteorológicas e Climáticas Aplicadas à Agricultura (CEPAGRI). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil
• Company: Universidade Estadual de Campinas (UNICAMP). Faculdade de Engenharia Elétrica e de Computação (FEEC)
• Associated research grant: 20/09838-0 - BI0S - Brazilian Institute of Data Science, AP.PCPE

Abstract

Irrigated agrivoltaic systems combine photovoltaic energy generation and agricultural production, optimizing land use, water resource conservation, and production sustainability. This project proposes the development of an irrigated agrivoltaic system with multivariable intelligent control, based on advanced computational modeling, machine learning, and automation techniques, aiming to optimize shading, energy generation, and water use. The research includes system modeling and simulation to analyze its feasibility under different agroclimatic conditions. Physical aspects of the agrivoltaic arrangement, the impact of shading on agricultural productivity, and the energy efficiency of solar panels will be considered. The system will integrate sensors and agroclimatic data for autonomous control of irrigation and panel positioning, maximizing plant photosynthesis and solar energy capture. Energy production modeling will be performed using the pvlib library (Python), while shading evaluation and microclimatic impact analysis will be based on models developed in MATLAB/Octave. Crop water demand calculations will use the crop evapotranspiration equation (ETc), considering local meteorological data. Predictive control techniques and artificial intelligence methods, such as fuzzy systems and decision trees, will be explored for dynamic adjustment of irrigation and energy generation. The project aligns with national artificial intelligence and energy sustainability strategies, promoting an innovative model for the integration of agriculture and renewable energy. Expected key outcomes include defining an efficient architecture for irrigated agrivoltaic systems, implementing intelligent control strategies, and validating system performance in different operational scenarios. The research impacts technical-scientific, economic, and environmental fields, contributing to water consumption reduction, increased energy efficiency, and income diversification for rural producers. (AU)