{"id":{"repo_id":"utahstate","oai_identifier":"oai:digitalcommons.usu.edu:etd-9036"},"canonical_url":"https://search.ndltd.org/etd/utahstate/oai:digitalcommons.usu.edu:etd-9036","repository":{"repo_id":"utahstate","name":"Utah State University","base_url":"https://digitalcommons.usu.edu/do/oai/"},"display":{"title":"Solar Irradiance Prediction Using Xg-boost With the Numerical Weather Forecast","abstract":"To defeat global warming, the world expects to look at renewable energy sources. Solar energy is one of the best renewable energy sources which causes no harm to the environment. As solar energy changes with atmospheric parameters like temperature, relative humidity, cloud coverage, dewpoint, sun position, day of the year, etc. It is difficult to understand its nature by science. Predicting solar irradiance which is directly proportional to solar energy using atmospheric parameters is the main goal of this work. Powerful artificial intelligence algorithms that won many coding competitions have been used to predict it. Using these methods and numerical weather forecast datasets one can predict solar irradiance up to ten days with the resolution of three hours. Two-day prediction is more reliable as error after that increases. As solar energy is not available all day there is a need to pre-plan the storage and utilization. From an electric charge station perspective, if he knows the energy generated by solar and the amount of load he needs to supply, he can take a wise decision to supply the maximum load with the available power. This will make him get more profits. This experimental study has been executed by driving solar energy predictions along with load predictions to an algorithm that gives an optimum charge and discharge schedule of the battery considering the profit of the electric vehicle charging station. Profit is calculated with solar predictions in different scenarios with the consideration of the price of the energy at a given time.","abstract_html":"To defeat global warming, the world expects to look at renewable energy sources. Solar energy is one of the best renewable energy sources which causes no harm to the environment. As solar energy changes with atmospheric parameters like temperature, relative humidity, cloud coverage, dewpoint, sun position, day of the year, etc. It is difficult to understand its nature by science. Predicting solar irradiance which is directly proportional to solar energy using atmospheric parameters is the main goal of this work. Powerful artificial intelligence algorithms that won many coding competitions have been used to predict it. Using these methods and numerical weather forecast datasets one can predict solar irradiance up to ten days with the resolution of three hours. Two-day prediction is more reliable as error after that increases. As solar energy is not available all day there is a need to pre-plan the storage and utilization. From an electric charge station perspective, if he knows the energy generated by solar and the amount of load he needs to supply, he can take a wise decision to supply the maximum load with the available power. This will make him get more profits. This experimental study has been executed by driving solar energy predictions along with load predictions to an algorithm that gives an optimum charge and discharge schedule of the battery considering the profit of the electric vehicle charging station. Profit is calculated with solar predictions in different scenarios with the consideration of the price of the energy at a given time.","abstract_has_math":false,"creators":["Kamarouthu, Pratyusha Sai"],"institution":"Hosted by Utah State University Libraries","degree_name":"Master of Science (MS)","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Nicholas Flann","John Edwards","Dan Watson"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T08:51:54Z","subjects":["solar irradiance prediction","xg-boost","cat-boost","support vector regression","numerical weather forecast","microgrid","Computer Sciences"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.26076/d306-aa2e"],"render_values":[{"text":"https://doi.org/10.26076/d306-aa2e","href":"https://doi.org/10.26076/d306-aa2e","code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.usu.edu/etd/7896","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://digitalcommons.usu.edu/etd/7896","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://digitalcommons.usu.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.usu.edu%3Aetd-9036","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Nicholas Flann","John Edwards","Dan Watson"]},{"key":"dc:creator","label":"Author","values":["Kamarouthu, Pratyusha Sai"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2010-01-01T08:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2020-08-01T07:00:00Z"]},{"key":"dc:publisher","label":"Institution","values":["Hosted by Utah State University Libraries"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science (MS)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["solar irradiance prediction","xg-boost","cat-boost","support vector regression","numerical weather forecast","microgrid","Computer Sciences"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.usu.edu/etd/7896"]},{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.26076/d306-aa2e"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["To defeat global warming, the world expects to look at renewable energy sources. Solar energy is one of the best renewable energy sources which causes no harm to the environment. As solar energy changes with atmospheric parameters like temperature, relative humidity, cloud coverage, dewpoint, sun position, day of the year, etc. It is difficult to understand its nature by science. Predicting solar irradiance which is directly proportional to solar energy using atmospheric parameters is the main goal of this work. Powerful artificial intelligence algorithms that won many coding competitions have been used to predict it. Using these methods and numerical weather forecast datasets one can predict solar irradiance up to ten days with the resolution of three hours. Two-day prediction is more reliable as error after that increases. As solar energy is not available all day there is a need to pre-plan the storage and utilization. From an electric charge station perspective, if he knows the energy generated by solar and the amount of load he needs to supply, he can take a wise decision to supply the maximum load with the available power. This will make him get more profits. This experimental study has been executed by driving solar energy predictions along with load predictions to an algorithm that gives an optimum charge and discharge schedule of the battery considering the profit of the electric vehicle charging station. Profit is calculated with solar predictions in different scenarios with the consideration of the price of the energy at a given time."]},{"key":"dc:title","label":"Title","values":["Solar Irradiance Prediction Using Xg-boost With the Numerical Weather Forecast"]}]}],"canonical_facts":{"dc:contributor":["Nicholas Flann","John Edwards","Dan Watson"],"dc:creator":["Kamarouthu, Pratyusha Sai"],"dc:date.available":["2010-01-01T08:00:00Z"],"dc:date.created":["2020-08-01T07:00:00Z"],"dc:description.abstract":["To defeat global warming, the world expects to look at renewable energy sources. Solar energy is one of the best renewable energy sources which causes no harm to the environment. As solar energy changes with atmospheric parameters like temperature, relative humidity, cloud coverage, dewpoint, sun position, day of the year, etc. It is difficult to understand its nature by science. Predicting solar irradiance which is directly proportional to solar energy using atmospheric parameters is the main goal of this work. Powerful artificial intelligence algorithms that won many coding competitions have been used to predict it. Using these methods and numerical weather forecast datasets one can predict solar irradiance up to ten days with the resolution of three hours. Two-day prediction is more reliable as error after that increases. As solar energy is not available all day there is a need to pre-plan the storage and utilization. From an electric charge station perspective, if he knows the energy generated by solar and the amount of load he needs to supply, he can take a wise decision to supply the maximum load with the available power. This will make him get more profits. This experimental study has been executed by driving solar energy predictions along with load predictions to an algorithm that gives an optimum charge and discharge schedule of the battery considering the profit of the electric vehicle charging station. Profit is calculated with solar predictions in different scenarios with the consideration of the price of the energy at a given time."],"dc:identifier":["https://digitalcommons.usu.edu/etd/7896"],"dc:identifier.doi":["https://doi.org/10.26076/d306-aa2e"],"dc:publisher":["Hosted by Utah State University Libraries"],"dc:subject":["solar irradiance prediction","xg-boost","cat-boost","support vector regression","numerical weather forecast","microgrid","Computer Sciences"],"dc:title":["Solar Irradiance Prediction Using Xg-boost With the Numerical Weather Forecast"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["Master of Science (MS)"]},"updated_at":"2026-11-19T08:51:54Z"}