The week's pick
Random Articles
Reseach Article
Intelligent Sustainable Energy Solution (ISES): An AI-Driven Residential Solar Assessment via Multimodal Vision, Interactive 3D Spatial Modeling, and Competitive Bidding Marketplace
| International Journal of Applied Information Systems |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 13 - Number 4 |
| Year of Publication: 2026 |
| Authors: Sana Irshad, Muhammad Salman, Ruba Islahuddin, Fiza Nizami |
10.5120/ijca7d658fdaaaf9
|
Sana Irshad, Muhammad Salman, Ruba Islahuddin, Fiza Nizami . Intelligent Sustainable Energy Solution (ISES): An AI-Driven Residential Solar Assessment via Multimodal Vision, Interactive 3D Spatial Modeling, and Competitive Bidding Marketplace. International Journal of Applied Information Systems. 13, 4 ( Aug 2026), 23-36. DOI=10.5120/ijca7d658fdaaaf9
Abstract
The Intelligent Sustainable Energy Solution (ISES) is an advanced artificial intelligence platform specifically designed to revolutionize and streamline the residential and small-commercial solar energy adoption ecosystem in Pakistan. The conventional process of installing photovoltaic (PV) solar systems in developing nations suffers from severe inefficiencies, including manual and error-prone electrical load calculations, inadequate rooftop physical assessments, opaque vendor pricing, and incorrect sizing of solar inverters, battery storage, and panel arrays. ISES addresses these multi-faceted challenges by providing a unified, data-driven digital platform integrating real-time energy load profiling, computer vision rooftop image analysis via Google Gemini Vision API, WebGL/Three.js-driven interactive 3D spatial visualization, and a transparent competitive bidding vendor marketplace. Users input basic spatial and load specifications, including appliance usage parameters, property structural types, geographical coordinates, and rooftop orientation. The platform's Gemini Vision AI engine analyses uploaded rooftop images to automatically detect physical obstructions—such as concrete water tanks, staircase mumties, parapet walls, skylights, nearby building shadows, and vegetation—mapping out dead zones and isolating precise usable surface areas. Based on these spatial constraints and localized solar irradiance data, ISES calculates optimal system capacities, required panel counts, azimuth angles, and 25-degree south-facing tilt angles. Furthermore, an interactive 3D digital twin of the proposed installation allows users to preview equipment layouts prior to physical deployment. An integrated multi-vendor marketplace connects users with verified installers, facilitating transparent quote comparison and eliminating price monopolies. Managed by an enterprise backend architecture built on ASP.NET Core and SQL Server, ISES bridges the gap between technical complexity and user decision-making, accelerating clean energy adoption in South Asia.
References
- Smith, J. B., & Ali, A. (2024). Macroeconomic AI assessment of renewable energy transitions: Frameworks for predictive market analysis and capital cost optimization. Energy Economics, 118, 106510.
- EnergySage. (n.d.). Solar Marketplace and installer quotation comparison (Platform documentation). Renewable and Sustainable Energy Reviews.
- Ullah, H., & Kamran, M. (2023). Artificial Neural Network (ANN) based Maximum Power Point Tracking (MPPT) optimization for photovoltaic arrays under partial shading anomalies. IEEE Journal of Photovoltaics, 13(2), 290–302.
- Valentin Software. (n.d.). PVSOL Online – Photovoltaic system simulation tool.
- Google LLC. (n.d.). Project Sunroof – Solar rooftop potential analysis.
- ResearchGate. (2024). A review of AI-driven optimization technologies for distributed photovoltaic power generation systems.
- International Building Performance Simulation Association (IBPSA). (2021). Building Simulation 2021 Conference Paper.
- SSRG International Journal of Electrical and Electronics Engineering. (2024). Deep learning-based photovoltaic power forecasting.
- Salam, Z., & Aziz, M. J. (2021). Challenges and prospects of solar energy adoption in developing countries. Journal of Cleaner Production, 278, 123987.
- CEIC Data. (2024). Pakistan electricity generation and consumption.
- World Bank Group, ESMAP, & Solargis. (2017). Solar resource map: Direct normal irradiation of Pakistan. Global Solar Atlas.
- Khan, S., Aslam, M., & Malik, H. (2024). Long Short-Term Memory (LSTM) networks for smart grid load forecasting and efficiency optimization in distributed photovoltaic clusters. IEEE Transactions on Sustainable Energy, 14(3), 412–425.
- Ahmed, T., & Hussain, R. (2023). A comprehensive review on Reinforcement Learning (RL) utilization for dynamic resource allocation and load balancing in renewable power grids. Renewable and Sustainable Energy Reviews, 182, 113402.
- Fatima, M., Zaidi, Y., & Raza, S. (2024). Explainable AI frameworks for localized solar irradiance mapping and feature extraction under variable atmospheric dynamics. Solar Energy, 255, 88–101.
- Zhou, L., Tanaka, K., & Ahmad, S. (2023). Artificial intelligence applications in distributed photovoltaic sizing and infrastructure integration: A methodological review. Applied Energy, 340, 121015.
- Ramzan, N., Iqbal, S., & Ghaffar, A. (2023). Computer vision and deep learning approaches for shading mitigation and obstacle detection in urban solar micro-grids. Energy and Buildings, 295, 113310.
- Santos, F., Da Silva, M., & Lima, R. (2024). Hardware-efficient weightless neural network architectures for edge-based solar panel path tracking and structural monitoring. Journal of Real-Time Image Processing, 21(1), 45.
Index Terms
Keywords