Research on dynamic allocation strategy of urban smart parking resources based on multi-source big data and deep reinforcement learning

To address the parking challenges in the development of smart cities, this paper proposes a dynamic allocation strategy for urban intelligent parking resources based on multi-source big data and deep reinforcement learning. The study integrates diverse data sources including traffic flow patterns, real-time parking space availability, and user travel behaviors, employing advanced data mining techniques to extract critical information for resource allocation decisions. By introducing a deep reinforcement learning algorithm, an intelligent decision-making model is constructed, enabling real-time adaptive parking resource allocation strategies. This approach optimizes parking resource utilization, enhances operational efficiency of parking facilities, and reduces traffic congestion.