SolExplore: A Successive Refinement Approach for Sizing of PV and Storage Systems in EV-Enabled Homes

The growing accessibility of solar photovoltaic (PV) systems offers a promising pathway for homeowners to decarbonize their buildings. However, determining the appropriate size of a PV system and battery storage remains a complex task, influenced by household energy demand, daily activity patterns, and local solar potential. This decision becomes more complex with the increasing adoption of electric vehicles (EVs), as commute patterns and charging strategies, including bidirectional charging, significantly influence electricity demand profiles. Existing approaches to sizing PV and battery systems rely on detailed simulations that, while accurate, are computationally intensive and often take several minutes to hours to complete. This latency reduces interactivity and limits users' ability to explore various scenarios. In this work, we introduce SolExplore, an interactive application that delivers instant, high-accuracy sizing recommendations based on simple user-provided inputs. SolExplore leverages a simple dual-branch MLP as a surrogate model to generate a wide range of sizing predictions for different scenarios that users can explore in real time. Our model enables large-scale scenario evaluations in milliseconds, representing a speedup of 600,000 times over traditional methods that require several hours of computation. By drastically reducing computation time, our approach enables users to efficiently evaluate multiple configurations and identify system designs that best meet their needs and preferences. To ensure reliability, the selected configuration is subsequently verified using detailed simulations. This combined approach of fast and approximate prediction followed by careful verification empowers users to make well-informed decisions and supports broader adoption of residential solar and battery technologies.

• Publication year

  2025

• Venue

  International Conference on Systems for Energy-Efficient Built Environments

• Publication date

  2025-11-11

• Fields of study

  Computer Science, Engineering, Environmental Science

• Identifiers
  DOI 10.1145/3736425.3770101
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Fast Optimal Sizing of Domestic PV Energy Systems✱

  2025influential reference
• SOPEVS: Sizing and Operation of PV-EV-Integrated Modern Homes

  2024influential reference
• Faraday: Synthetic Smart Meter Generator for the smart grid

  2024influential reference
• SPAGHETTI: a synthetic data generator for post-Covid electric vehicle usage

  2024cited by this paper
• Photovoltaic sizing using machine learning

  2023cited by this paper
• Solar PV adoption at household level: Insights based on a systematic literature review

  2023cited by this paper
• Machine learning in photovoltaic systems: A review

  2022cited by this paper
• Electric

  2020cited by this paper
• Short-Term Photovoltaic Power Forecasting Using an LSTM Neural Network and Synthetic Weather Forecast

  2020cited by this paper
• Multi-objective mathematical programming for optimally sizing and managing battery energy storage for solar photovoltaic system integration of a multi-apartment building

  2020cited by this paper
• A Multi-Agent Reinforcement Learning-Based Data-Driven Method for Home Energy Management

  2020cited by this paper
• Computational framework for behind-the-meter DER techno-economic modeling and optimization: REopt Lite

  2020cited by this paper
• Very Short-Term Solar Generation Forecasting Based on LSTM with Temporal Attention Mechanism

  2019cited by this paper
• Reinforcement Learning-Based Energy Management of Smart Home with Rooftop Solar Photovoltaic System, Energy Storage System, and Home Appliances

  2019cited by this paper
• Comparison of Different Approaches for Solar PV and Storage Sizing

  2019cited by this paper
• Timing of eating across ten European countries – results from the European Prospective Investigation into Cancer and Nutrition (EPIC) calibration study

  2018cited by this paper
• Robust and Practical Approaches for Solar PV and Storage Sizing

  2018cited by this paper
• Factors responsible for solar PV adoption at household level: A case of Lahore, Pakistan

  2017cited by this paper
• Optimal Design of Solar PV Farms With Storage

  2015cited by this paper
• Photovoltaic self-consumption in buildings : A review

  2015cited by this paper
• An Improved Method for Sizing Standalone Photovoltaic Systems Using Generalized Regression Neural Network

  2014cited by this paper
• Electric vehicles and the electric grid: A review of modeling approaches, Impacts, and renewable energy integration

  2013cited by this paper
• google,我,萨娜

  2006cited by this paper

• No citing papers are available for this paper.