Summary Deep borehole heat exchanger (DBHE) is attracting attention intensively owing to much more geothermal extraction, higher efficiency for heat pumps, and lesser land demand compared with shallow borehole heat exchanger. DBHE is usually dipped into several thousand meters in the subsurface, having a complicated heat transfer with surrounding rock–soil. However, the heat transfer characteristics below surface under different conditions are rarely studied. In this study, a numerical model considering the comprehensive effects of geothermal gradients and heat loss from inner pipe was proposed. The model was validated with experimental data and Beier analytical solution. Based on the model, the effects of primary design parameters on the heat transfer performance below surface along the pipe were investigated. The results indicate that temperature at pipe bottom increases with inlet flow rate decreasing, while the heat load cannot be extracted fully to the surface because of the heat loss of inner pipe. When the inlet flow rates decrease from 41.39 to 4.52 m3/h, the heat loss ratio increases from 25.5% to 63.7%. It is an effective way of insulating inner pipe to reduce heat loss under low inlet flow rates. Increasing the velocity in inner pipe by lessening the inner pipe diameter can also decline the heat loss well. While by this way, the increasing pumping power resulting from the higher velocity in inner pipe has to be considered. This study is significant to effective optimization of DBHE and energy conservation of buildings.

No abstract

No abstract

Nowadays, with the rapid development of IoT (Internet of Things) and CPS (Cyber-Physical Systems) technologies, big spatiotemporal data are being generated from mobile phones, car navigation systems, and traffic sensors. By leveraging state-of-the-art deep learning technologies on such data, urban traffic prediction has drawn a lot of attention in AI and Intelligent Transportation System community. The problem can be uniformly modeled with a 3D tensor (T, N, C), where T denotes the total time steps, N denotes the size of the spatial domain (i.e., mesh-grids or graph-nodes), and C denotes the channels of information. According to the specific modeling strategy, the state-of-the-art deep learning models can be divided into three categories: grid-based, graph-based, and multivariate timeseries models. In this study, we first synthetically review the deep traffic models as well as the widely used datasets, then build a standard benchmark to comprehensively evaluate their performances with the same settings and metrics. Our study named DL-Traff is implemented with two most popular deep learning frameworks, i.e., TensorFlow and PyTorch, which is already publicly available as two GitHub repositories https://github.com/deepkashiwa20/DL-Traff-Grid and https://github.com/deepkashiwa20/DL-Traff-Graph. With DL-Traff, we hope to deliver a useful resource to researchers who are interested in spatiotemporal data analysis.

No abstract