In response to the global demand for energy efficiency and the trend toward reducing energy consumption, there is a growing need for straightforward yet effective methods to manage building systems. Among these systems, lighting control plays ones of a pivotal role in achieving functional and operational goals. This study focuses on the development of predictive models for estimating illumination intensity at workplace using neural networks. Neural networks have emerged as powerful tools for optimization and addressing complex problems in this domain. The research centers on creating two independent predictive models based on neural networks, which reliably and accurately predict the behavior and distribution of light in workplace environments. The developed models demonstrate remarkable accuracy for the given input parameters, making them highly suitable for addressing lighting challenges in interior spaces. The results of this study provide a foundational step toward adaptive lighting control systems in intelligent buildings. Moreover, the findings contribute significantly to enhancing workplace comfort and reducing the energy demands of buildings. This research contributes valuable insights into the integration of advanced illumination intensity techniques and supports the broader goal of sustainable and energy-efficient buildings operations.
Belány et al. (Thu,) studied this question.