To address the issue of inefficient parking space utilization resulting from temporal and spatial disparities in parking demand, shared parking emerges as an innovative traffic management paradigm. The core concept of shared parking lies in the strategic allocation of parking spaces. By analyzing the usage patterns of parking areas, the relationship between supply and demand over time can be represented in a binomial form. An integer programming model for parking allocation is formulated, where the objective at each allocation stage is to minimize walking distance and parking costs while maximizing the degree of temporal alignment with overall parking demand in the region. The weights of these three indices are calculated using the entropy weight method, and subsequently, the parking cost matrix is derived through linear weighting. It is proposed to utilize the Hungarian Algorithm as a method for solving the assignment problem to obtain the allocation scheme that minimizes total parking costs. A Python program is developed to execute the phased optimal allocation of parking spaces. At the conclusion of the operation, the results for overall parking demand satisfaction, parking space utilization, and parking costs are generated. The model is applied to parking space management in both real-world instances and simulation experiments. The results demonstrate that the model not only ensures a higher utilization rate of parking spaces but also effectively reduces overall parking costs and the idle rate of parking time compared to the current parking methods. This model is well-suited for the parking allocation processes of smart parking platforms.

In addressing the challenge of spatio-temporal correlation in traffic flow at signalized intersections, this study introduces an innovative methodology that integrates a SG-LSTM neural network with a particle swarm optimization algorithm. The proposed methodology involves the pre-processing of original traffic data to enhance its predictability, followed by the development of a short-term traffic flow prediction model utilizing the LSTM neural network. Utilizing the outcomes of the traffic flow predictions, a dynamic timing model for signalized intersections is formulated through the application of the particle swarm optimization algorithm. Furthermore, a multi-objective optimization model is established to refine the timing scheme of the signalized intersections, incorporating constraints that consider the maximization of overall intersection capacity, minimization of average delay, and reduction of average queuing times. The Pareto compromise programming method is employed to perform dimensionless processing of the three performance indicators, while the fuzzy preference method is utilized to ascertain the weight relationships among the objective functions. The optimized signal timing scheme is derived through the implementation of the particle swarm optimization algorithm in Matlab. Experimental results indicate that the proposed methodology surpasses the traditional Webster model in terms of performance indicators, thereby affirming the effectiveness and reliability of the approach.