To mitigate the spatiotemporal mismatch between renewable energy supply and building heating demand, this study proposes a novel non-pressurized shell-and-tube latent heat storage (NP-LHS) device coupled with an air-source heat pump (ASHP) system. To overcome the inherent low thermal conductivity of organic phase change materials (PCMs), the thermal performances of plain, corrugated, and finned tubes were systematically compared using both computational fluid dynamics (CFD) simulations and full-scale experiments. Numerical results indicate that the optimal tube spacing ratio ranges from 1.0 to 1.5. Among the evaluated geometries, the finned tube configuration exhibited superior comprehensive performance. It achieved an exceptionally high PCM volume fraction of 92.5% and dramatically reduced the complete melting time to 180 min—significantly faster than both corrugated (280 min) and bare tubes—while attaining a higher terminal temperature. Full-cycle dynamic experiments further demonstrated that integrating the finned tube NP-LHS into the ASHP system yielded a peak-shaving power reduction rate of 98.0%, effectively maintaining indoor thermal comfort. These findings conclude that expanding the conductive surface area via fins is practically more effective than inducing fluid turbulence for low-conductivity PCMs in non-pressurized storage applications.

With the increasing intelligence of modern air-conditioning systems, the difficulty of acquiring data from air-conditioning systems has been significantly reduced. However, analyzing the massive amounts of data collected and obtaining more valuable information still remains challenging, especially considering the internal relationships behind the data. The purpose of this study was to conduct operational experiments on VRF systems under different indoor set temperatures, indoor set air speeds, and terminal load rates. Then, the patterns of various operating parameters and energy consumption of VRF systems during winter operation were analyzed based on unsupervised methods. Three machine learning methods were primarily employed in this study, including correlation analysis, data regression analysis, and association rule analysis. Finally, a regression model was constructed for energy consumption based on eight typical characteristic parameters. The experimental results showed that the system was stable to a certain degree at different wind speeds. Among the characteristic parameters, fixed frequency 1 exhaust temperature, compressor frequency, and other parameters have a significant positive effect on energy consumption, while fixed frequency 1 shell top oil temperature, inlet and outlet pipe temperature difference, and other parameters have a negative effect. The research results provide a reference for air conditioning system data mining and building sustainability.