High-precision traffic flow prediction facilitates intelligent traffic control and refined management decisions. Previous research has built a variety of exquisite models with good prediction results. However, they ignore the reality that traffic flows can propagate backwards on road networks when modeling spatial relationships, as well as associations between distant nodes. In addition, more effective model components for modeling temporal relationships remain to be developed. To address the above challenges, we propose a local–global features fusion temporal convolutional network (LGTCN) for spatio-temporal traffic flow prediction, which incorporates a bidirectional graph convolutional network, probabilistic sparse self-attention, and a multichannel temporal convolutional network. To extract the bidirectional propagation relationship of traffic flow on the road network, we improve the traditional graph convolutional network so that information can be propagated in multiple directions. In addition, in spatial global dimensions, we propose probabilistic sparse self-attention to effectively perceive global data correlations and reduce the computational complexity caused by the finite perspective graph. Furthermore, we develop a multichannel temporal convolutional network. It not only retains the temporal learning capability of temporal convolutional networks, but also corresponds each channel to a node, and it realizes the interaction of node features through output interoperation. Extensive experiments on four open access benchmark traffic flow datasets demonstrate the effectiveness of our model.
The growing ownership of electric vehicles in urban areas leads to increasing demand for public charging spaces. With existing charging facilities failing to match the constantly increasing demand for charging, it is necessary to plan for new charging infrastructure. A two-stage approach is proposed for public charging infrastructure planning from both macro and micro perspectives. Firstly, a linear regression model with an exponential elasticity function is used to estimate charging demand, considering comprehensive charging demand factors. Secondly, effective served charging demand (ESCD) is proposed to accurately calculate the charging demand of effective service areas, considering the distance impact factor and competition among neighbouring charging stations. A capacitated maximal service location model (CMSLM) is proposed to optimise the spatial layout of public charging stations by maximizing their ESCD while considering investment budget and charging station capacity limits. CMSLM is solved using sparrow search algorithm from both macro and micro perspectives. The proposed approach is applied to Guangzhou, China, as a case study. Results show that when the investment budget is increased to 5 million CNY, the ESCD of all districts under the macro and micro optimisation perspectives increases by an average of 41.0% and 34.1%, respectively. Optimised charging stations can remedy the spatial imbalance between charging demand and existing charging station distribution, laying the foundation for further construction implementation.