Residential energy use accounts for a substantial portion of global consumption, making its reduction critical for sustainable architectural design. However, existing generative models for residential layouts often overlook energy performance, resulting in inefficient designs and costly revisions. To address this, we propose an AI-based framework that integrates generative model, energy prediction, and evolutionary optimization. Our framework comprises three components: (1) Energy prediction: a deep learning model trained on energy simulations of 71,125 floor plans from the RPLAN dataset predicts monthly energy consumption across five categories with over 99% accuracy. (2) Generative model: a diffusion-based layout generator uses room blocks and residential contours to create diverse, high-quality floor plans under spatial constraints. (3) Optimization: a genetic algorithm iteratively refines floor plans by selecting low-energy solutions and regenerating new options, guided by the predictive model. Experiments show that our method reduces energy consumption by 17.5% compared to the best baseline model under identical conditions, demonstrating its effectiveness in reducing residential energy use. Our key contributions include the use of room blocks as chromosomes for layout evolution, and the integration of AI-based prediction and generation for energy-aware residential design.

Urban outdoor spaces are vital for our daily lives and activities. However, unlike indoor environments, outdoor spaces are characterized by unpredictable climatic conditions and a lack of mature control over environmental quality. Thus, this study explores the utilization of an intelligent kinetic canopy (KCP) to enhance the quality of the outdoor thermal environment. The KCP was conducted using various technologies, including the Internet of Things, motor automation control, web crawler, simulation, machine learning, optimization algorithms, and kinetic architecture theory. KCP can adjust its own form in real-time according to weather changes and can significantly improve thermal quality in local outdoor spaces. To quantify its ability, the effects of the three algorithms on the Universal Thermal Climate Index (UTCI) values and the associated annual thermal neutral hours on the original open-state site were compared. The control strategy based on genetic algorithms yielded leading performance, achieving 1193 h of annual thermal neutral time increments compared with the original site, approximately 3.3 h daily. Compared with the best static canopy, its neutral period is 696 h longer, or 140% better in creating additional thermally neutral hours. These findings demonstrate the ability of the KCP to further unleash the potential of space design to improve the thermal comfort of outdoor spaces, which broadens the conceptual scope for similar design and research on outdoor spaces and provides architects and designers with insights into specific technical applications and strategies for implementation.