IHPC Tech Hub

IHPC Tech Hub showcases IHPC's suite of in-house developed applications, tools or technology to help you unlock the possibilities to overcome business challenges. Through providing valuable insights, you can now predict and shape the commercial outcomes, automate processes, and free up resources for repetitive and labour-intensive tasks. 

Discover the power of computational modelling, simulation and AI that brings about positive impact to your business. 

Intelligent Solar Irradiation Evaluator (isolie)

Solar irradiation simulators are typically used in urban planning for solar heat gain estimation and solar farm potential evaluation. While typical solar irradiation simulators use numerical approaches to perform the calculations, the simulation time is usually an hour or more for complex 3D geometries at the district to town scale. The results generated in the solar irradiation maps can help planners to maximise shading and minimise solar heat gain. At the same time, quantitative evaluation gives the amount of solar energy that could potentially be harvested on deployed solar panels or building integrated photovoltaics. Recent research efforts have been focused on accelerating numerical computations with the secondary hardware (i.e., GPUs) without a trade-off in accuracy.

Recently, machine-learning-based techniques are applied to compact numerical models to predict sky illuminance and weather forecasting. However, the standard neural network or deep learning approaches for predicting the annual irradiation require a long training time, high computational load, and complicated machine learning (ML)/artificial intelligence (AI) algorithms if complex building geometries are considered. 

Intelligent solar irradiation evaluator (isolie) is a physics-based ML-driven application with a user-friendly graphical user interface (GUI) for predicting solar irradiation in complex three-dimensional (3D) urban environments. The app can achieve near real-time execution speed for the digital twin of cities for urban planners to evaluate their urban layouts and design solar heat gain and hotspots, not just a good-to-have visualisation.

  • User-friendly GUI
  • Parallel-computing preprocessor
  • First of its kind Physics-based ML engine that only requires small training dataset
  • 3D complex building geometries of arbitrary shapes and orientation are supported
  • >20 cities around the world
  • <10% statistical error deviation compared to numerical equivalent
  • Near real-time execution speed for hundreds to thousands of urban features, i.e., buildings, solar panels 

The Science Behind

Solar irradiation is a general term for the electromagnetic energy emitted from the sun for a specific duration. The amount of solar irradiation that reaches any one spot on the surface of urban environments varies according to geographic location, sky conditions, and local landscape. The physical background can be illustrated by geometrical optics, including directly radiating, diffusely radiating, and scattering. By quantifying the solar irradiation on the solar panel surfaces, the amount of electricity that can be generated from solar energy can be computed for both typical rooftop and building integrated photovoltaics.

Solar irradiation mapping predicted by isolie for a town

Fig 1. Solar irradiation mapping predicted by isolie for a town

Industry Applications

isolie can be applied into the following industry purposes:

  • Urban planning and design
  • Thermal comfort and mitigation evaluation
  • Solar and Building-Integrated Photovoltaics (BIPV) planning and deployment
For more info or collaboration opportunities, please write to enquiry@ihpc.a-star.edu.sg