Reliable and efficient modeling of residential space heating systems is crucial for optimizing building energy usage, especially during extreme cold snap events. Traditional white-box models require significant expertise and time-intensive parameterization, whereas simplified grey-box resistance-capacitance (RC) models often suffer from limited accuracy and frequent recalibrations. Although purely data-driven methods show promise in predictive performance, they lack scalability and interpretability. To address these limitations, the study proposes a physically consistent neural network (PCNN) that integrates fundamental heat transfer principles with data-driven learning. This study compares the performance of grey-box RC models, conventional data-driven models, and the proposed PCNN within a deep reinforcement learning (DRL) framework for space heating control. The evaluation focuses on each model’s predictive accuracy under severe cold snap conditions, as well as their impact on indoor comfort, grid imports, and photovoltaic (PV) utilization. Results show that the PCNN achieves up to a 93.9% reduction in mean absolute error (MAE) prediction errors compared to the RC model and exhibits greater robustness to abrupt temperature drops. When incorporated into DRL controllers, the PCNN enhances indoor temperature stability, increases on-site PV consumption, and reduces energy dependence. Additionally, the PCNN can be effectively trained with smaller datasets without sacrificing accuracy. Although the PCNN model demonstrates higher computational overhead during DRL optimization, its moderate complexity is offset by its enhanced reliability. Notably, the PCNN outperforms all other models in continuous control scenarios, maintaining a mean indoor temperature of 21.9 ℃ with a minimal deviation of −0.1 ℃, reaching a 69.2% PV consumption rate, lowering total grid imports by approximately 37%, and reducing overall energy costs by nearly 48% compared to measured results.

Using the behind-meter data, this study applied a comparison and optimization-based framework to evaluate the energy flexibility and resilience of distributed energy resources within existing houses during cold wave event. Comparative analysis demonstrates the effectiveness of high envelope insulation level in improving energy resilience, identifies impacts of distributed energy resources on variations of household electricity demand. Specifically, a 14.6% reduction in the median value of the normalized load of building group with low U-values, implementations of cogeneration system effectively suppressed variations of electricity load. Dynamic energy performances of on-site generators are evaluated based on high resolution data, energy flexibility of domestic hot water and thermostatically controlled loads were investigated through built demand response model. Results reveal that electrifying hot water demand offers additional power flexibility, the integration of fuel cell cogeneration system has proven to be an efficient energy resource, enabling on-site generation of both electricity and hot water, substantially reducing grid import. The extreme cold event resulted in significant spikes in space heating power consumption. The optimization results demonstrate that reducing the indoor setpoint temperature effectively decreases daily power consumption by approximately 5.0% per degree Celsius. These findings help acquire better understanding of interconnections between energy efficiency and resilience of residential energy-efficient measures.

Elderly health is increasingly recognized as a worldwide challenge with the continuous social aging trend. This study aimed to investigate the thermal conditions of the elderly in rural areas of Shandong, China. The thermal sensation and physiological response performances of elderly participants were examined in their own houses. Results show a clear seasonal pattern in cardiovascular disease mortality, cold stress increases the cardiovascular disease risk. The coal-based stoves serve as the main source of home heating and their limited coverage of the room area gave rise to poor quality of thermal comfort. The analysis of skin temperature for those under 65 and above did not reveal any significant difference in response to different indoor temperatures. The regression results confirm that a colder home leads to a rising value of the elderly’s systolic blood pressure, rising by more than 1 mmHg for every 1 ℃ decrease in indoor temperature and thus posing a greater risk of cardiovascular diseases. The systolic blood pressure value of older subjects rise more when they are exposed to decreasing indoor temperatures, possibly due to an age-related decline in their ability to maintain stability of blood pressure. It is noteworthy that the average blood velocity of older subjects reduces less in response to decreasing indoor temperatures, indicating a weakened capacity to resist cold stress and its associated high risk of hypertension. This investigation provides evidence in favor of improving the thermal environment of the elderly and reducing their risk of cardiovascular diseases.