CLIMATE CHANGE ALONG WITH THE LACK OF AVAILABILITY OF ELECTRICITY IN AGRICULTURAL LANDS HAVE LED TO INCREASED PRODUCTION COSTS FOR FARMERS. THESE FACTORS ARE LEADING FARMERS TO INCORPORATE THE USE OF NEW TECHNOLOGIES IN SEARCH OF MORE SUSTAINABLE SOLUTIONS FOR PRODUCTION. IN THIS CONTEXT, THE USE OF RENEWABLE ENERGY, IN PARTICULAR, PHOTOVOLTAIC SYSTEMS TO PROVIDE OFF-GRID SOLUTIONS FOR AGRICULTURE APPLICATIONS HAS GAINED RELEVANCE. CURRENTLY, SEVERAL PROGRAMS IMPULSED BY THE CHILEAN GOVERNMENT ARE IN PLACE TO INCENTIVE THE USE OF SOLAR ENERGY FOR FARMING APPLICATIONS; HOWEVER, SOME OF THESE INITIATIVES LACK TOOLS THAT MAY ALLOW FARMERS TO VALIDATE AND ASSESS THE EFFICACY OF THE PROPOSED SOLUTIONS. THIS WORK IS FOCUSED ON THE DEVELOPMENT OF A SIMPLE VALIDATION METHOD SUITABLE TO BE USED BY NON-EXPERTS TO ASSESS THE EFFICACY OF SOLAR ENERGY-BASED SOLUTIONS FOR FARMING APPLICATIONS. THE PROPOSED METHODOLOGY CONSIDERS TAKING ADVANTAGE CURRENTLY AVAILABLE TOOLS ALONG WITH COLLECTING AND ANALYZING SIMPLE MEASURES OVER THE INSTALLED GENERATION SYSTEM, IN ORDER TO PROVIDE A REASONABLE ASSESSMENT OF SYSTEM PERFORMANCE. THE PROPOSED METHOD IS ILLUSTRATED ON A REAL INSTALLATION USED TO SUPPLY POWER TO A WATERING SYSTEM FOR BERRIES. BASED ON THE OBTAINED RESULTS, THE DEVELOPED TOOLS SEEM SUITABLE TO BE USED BY NON-EXPERTS TO ASSESS PERFORMANCE AND TO IMPLEMENT SEASONAL PERFORMANCE IMPROVEMENTS.

CURRENTLY, SEVERAL COUNTRIES ARE SEEKING TO CHANGE THEIR ENERGY MATRICES TOWARDS MORE SUSTAINABLE SOURCES. IN CHILE, ONE OF THE RENEWABLE SOURCES WITH INCREASED PARTICIPATION IS PHOTOVOLTAICS. HOWEVER, PHOTOVOLTAIC ENERGY SOURCES HAVE AN INTRINSIC VARIABILITY, WHICH COMBINED WITH VARIABLE DEMAND IMPOSES A CHALLENGE FOR PROPER DESIGN. CURRENTLY, TOOLS AVAILABLE FOR THE STUDY OF THIS VARIABILITY ARE EITHER COMPLEX OR EXPENSIVE. WITH THE ADVENT OF DIGITALIZATION, THERE IS AN OPPORTUNITY TO INCORPORATE TOOLS BASED ON ARTIFICIAL INTELLIGENCE TO IMPROVE FORECASTING FOR MEDIUM AND LOW POWER INSTALLATIONS. THIS WORK PRESENTS AN APPLICATION OF MACHINE LEARNING TOOLS FOR IRRADIANCE AND POWER CONSUMPTION FORECASTING. THE METHODOLOGY IS INTENDED TO BE IMPLEMENTED AS A LOW COST SOLUTION FOR SMALL SCALE GENERATION. THE RESULTS SHOW THAT IT IS POSSIBLE TO PREDICT IRRADIANCE AND ENERGY CONSUMPTION THROUGH HISTORICAL DATA, CONCLUDING THAT THE METHODOLOGY BASED ON MACHINE LEARNING IS ABLE TO SUPPORT THE DECISION MAKING FOR THE IMPROVEMENT OF PHOTOVOLTAIC SYSTEMS.