SolarGAN: Synthetic Annual Solar Irradiance Time Series on Urban Building Facades via Deep Generative Networks
This work addresses the need for robust Building Integrated Photovoltaics (BIPV) system design by reducing manual effort and computing time in solar irradiation assessment on urban building facades, though it is incremental as it applies existing deep generative methods to a specific domain problem.
The paper tackles the challenge of efficiently generating stochastic annual hourly solar irradiance time series on building facades for urban energy planning by proposing SolarGAN, a deep generative network model that uses simple fisheye images as input. The model produces high-fidelity results comparable to physics-based simulators, enabling real-time generative design under different climatic contexts.
Building Integrated Photovoltaics (BIPV) is a promising technology to decarbonize urban energy systems via harnessing solar energy available on building envelopes. While methods to assess solar irradiation, especially on rooftops, are well established, the assessment on building facades usually involves a higher effort due to more complex urban features and obstructions. The drawback of existing physics-based simulation programs is that they require significant manual modelling effort and computing time for generating time resolved deterministic results. Yet, solar irradiation is highly intermittent and representing its inherent uncertainty may be required for designing robust BIPV energy systems. Targeting on these drawbacks, this paper proposes a data-driven model based on Deep Generative Networks (DGN) to efficiently generate high-fidelity stochastic ensembles of annual hourly solar irradiance time series on building facades with uncompromised spatiotemporal resolution at the urban scale. The only input required is easily obtainable, simple fisheye images as categorical shading masks captured from 3D models. In principle, even actual photographs of urban contexts can be utilized, given they are semantically segmented. Our validations exemplify the high fidelity of the generated time series when compared to the physics-based simulator. To demonstrate the model's relevance for urban energy planning, we showcase its potential for generative design by parametrically altering characteristic features of the urban environment and producing corresponding time series on building facades under different climatic contexts in real-time.