{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T14:03:29Z","timestamp":1771682609192,"version":"3.50.1"},"reference-count":0,"publisher":"Slovenian Association Informatika","issue":"7","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJCAI"],"abstract":"<jats:p>The rapid growth of distributed photovoltaic (PV) systems offers a sustainable solution to rural energydemands. However, integrating PV into rural distribution grids presents challenges related to powerquality and grid reliability. Traditional PV site selection approaches often neglect the impact ondistribution reliability metrics, resulting in suboptimal deployments. This paper proposes RuralGridPVO (Rural Grid Photovoltaic Optimization), an optimization modeling framework for PV gridconnection site selection in rural areas, incorporating distribution grid reliability considerations. TheRuralGrid-PVO method integrates the RTS-GMLC synthetic power system model with solar irradiancedata from the NSRDB to simulate realistic rural deployment scenarios. A multi-objective optimizationmodel combines a Genetic Algorithm (GA) with Deep Neural Networks (DNN) for fast reliabilityassessments, optimizing PV placement based on energy yield, voltage stability, power losses, andreliability indices (SAIDI\/SAIFI). GA-DNN framework incorporates SAIDI\/SAIFI into optimization,outperforming baseline GA, AHP-GIS, and ReliOpt-Hybrid in energy yield, voltage stability, andreliability improvements, though sensitivity to reliability weights requires further exploration. Thispaper proposes RuralGrid-PVO, a comprehensive six-module optimization pipeline for distributedphotovoltaic (PV) site selection in rural grids with a focus on enhancing grid reliability. The pipelineintegrates data acquisition, candidate site identification, capacity estimation via Random Forestregression (R\u00b2 = 0.93), reliability-aware grid simulation utilizing a Deep Neural Network (DNN) forSAIDI\/SAIFI prediction (MAE = 3.8 min\/year), multi-objective optimization with a Genetic Algorithm(GA), and final configuration selection. The methodology operates on a hardware\/software stackcomprising Python-based ML frameworks and power system simulation tools to ensure reproducibility.Experimental evaluation demonstrates that RuralGrid-PVO improves voltage profiles by 15.3%,reduces energy losses by 12.8%, decreases SAIFI by up to 9.6%, and lowers SAIDI by 39%, significantlyoutperforming baseline site selection methods. These results validate the framework's effectiveness inachieving reliable, energy-efficient rural PV integration.<\/jats:p>","DOI":"10.31449\/inf.v50i7.11442","type":"journal-article","created":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T13:16:01Z","timestamp":1771679761000},"source":"Crossref","is-referenced-by-count":0,"title":["RuralGrid-PVO: A Reliability-Conscious Multi-Objective Optimization Framework for Distributed PV Siting in Rural Grids"],"prefix":"10.31449","volume":"50","author":[{"given":"Yu","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinyue","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haitao","family":"Ge","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Geng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lulu","family":"Jia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"16141","published-online":{"date-parts":[[2026,2,21]]},"container-title":["Informatica"],"original-title":[],"link":[{"URL":"https:\/\/www.informatica.si\/index.php\/informatica\/article\/download\/11442\/6493","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.informatica.si\/index.php\/informatica\/article\/download\/11442\/6493","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T13:16:01Z","timestamp":1771679761000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.informatica.si\/index.php\/informatica\/article\/view\/11442"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,21]]},"references-count":0,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,2,21]]}},"URL":"https:\/\/doi.org\/10.31449\/inf.v50i7.11442","relation":{},"ISSN":["1854-3871","0350-5596"],"issn-type":[{"value":"1854-3871","type":"electronic"},{"value":"0350-5596","type":"print"}],"subject":[],"published":{"date-parts":[[2026,2,21]]}}}