Dynamic Routing Optimization of Electric Garbage Collection and Transportation Vehicles Based on Smart Dumpster

The comprehensive deployment of smart garbage bins realizes the real-time monitoring of garbage generation and recycling demand, and the use of intelligent network connected collection and transportation vehicles can sense dynamic data such as vehicle location and load in real time. In this context, how to efficiently integrate these dynamic information to build a responsive scheduling system has become a key requirement of smart city management. Aiming at this requirement, this paper proposes a dynamic routing optimization model of electric garbage collection and transportation vehicles considering charging constraints, and designs a hybrid PSODE combining improved particle swarm optimization(PSO) and differential evolution(DE) to solve the model. By introducing a nonlinear decreasing strategy of inertia factor and a dynamic learning factor adjustment mechanism, an adaptive optimization framework of algorithm parameters is established to enhance the adaptability of the algorithm. Numerical example analysis shows that the PSO-DE can effectively deal with the change of garbage collection and transportation demand in dynamic environment. It provides an intelligent solution for the urban garbage collection and transportation scheduling system, and significantly improves the response ability and operation efficiency of the traditional collection and transportation system.