Al-Dabbagh, Nayyef Sami NayyefAl-Musawi, Sura Saadi JaafarHamodat, Zaid2022-08-052022-08-052022Al-Dabbagh, N. S. N., Al-Musawi, S. S. J., Hamodat, Z. (2022). Forecasting annual solar power output from geographic location. In 2022 International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA), IEEE.9781665468350https://hdl.handle.net/20.500.12939/2781Power determining of environmentally friendly power plants is an exceptionally dynamic examination field, as dependable data about the future power age takes into consideration a protected activity of the power framework and assists with limiting the functional expenses of these energy sources. AI calculations have demonstrated to be exceptionally strong in anticipating errands, like financial time series or discourse acknowledgment. Using random forest regression method, daily mean solar output generation can yield promising result rather than conventional NWP model for forecasting. Using that in practice also the goal was to create a user-friendly application, with easy access, to provide accurate forecasting regarding saving and conservation. This paper's goal was accomplished in three stages: To begin with, make an AI model that predicts the yearly energy result of an expected sun based establishment. From that point onward, make a model that predicts establishment costs. Carrying out these models on an easy to use web application that shows clients the amount they can hope to save money on their yearly energy bill by changing to sun oriented. The random forest model out-performs its other rivals and also conventional models, thus providing a better suited model to run with for forecasting.eninfo:eu-repo/semantics/closedAccessAI ModelNWP ModelPower ForecastingConference Object2-s2.0-85133973372N/A