Intelligent Dispatch Method and System for New Energy Logistics Fleets with Dynamic Task Allocation and Energy Replenishment Coordination

By constructing a four-dimensional task perturbation vector and Shannon entropy values ​​to divide the interval, and combining mixed integer linear programming and online learning, the new energy logistics fleet scheduling system is optimized. This solves the problems of vehicle allocation conflicts and inefficient resource utilization, realizes adaptive scheduling and battery health management under high entropy perturbation, and improves system adaptability and resource utilization efficiency.

CN122335138APending Publication Date: 2026-07-03GUANGZHOU ZHIKA LOGISTICS TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202610505762.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-04-16
Publication Date
2026-07-03

AI Technical Summary

Technical Problem

Existing new energy logistics fleet dispatching systems struggle to achieve real-time perception and flexible scheduling of task flow uncertainties when faced with dynamic task insertions and sudden peak disturbances. This results in frequent vehicle allocation conflicts, inefficient resource utilization, and a lack of adaptive mechanisms to optimize vehicle battery status and battery health management.

Method used

By constructing a four-dimensional task perturbation vector, calculating the Shannon entropy value within the sliding time window, dividing the region into a high-entropy perturbation zone and a low-entropy steady-state zone, and using a mixed-integer linear programming algorithm to optimize the continuity of vehicle paths and the uniqueness of task binding, a dynamic safety margin function and a battery aging degradation compensation term are introduced to generate an adaptive vehicle energy matching scheme, and the scheduling strategy is optimized by combining an online learning mechanism.

Benefits of technology

It significantly improves the system's adaptability and resource utilization efficiency in strong interference scenarios, ensures the timeliness of emergency missions, enhances the flexibility of energy dispatching and vehicle battery life, and achieves a dynamic balance between mission flexibility and system stability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122335138A_ABST
    Figure CN122335138A_ABST
Patent Text Reader

Abstract

This invention relates to an intelligent scheduling method and system for new energy logistics fleets that coordinates dynamic task allocation and energy replenishment. The invention constructs a multi-dimensional disturbance vector by collecting parameters such as the time window offset, spatial dispersion, load mutation rate, and emergency level transition of new tasks. Within a sliding time window, Shannon entropy is used to quantitatively characterize the uncertainty of the task flow, distinguishing between high-disturbance and steady-state regions. The invention adaptively adjusts the energy constraint set based on the task uncertainty state, dynamically relaxing the lower energy limit in high-entropy regions and compensating for the impact of battery aging and degradation in low-entropy regions. It achieves globally optimal vehicle-task-energy ternary matching under the constraints of path continuity and task uniqueness using mixed-integer linear programming, and realizes online adaptive correction of the entropy judgment threshold based on actual execution feedback. This invention improves the responsiveness and energy adaptability to complex dynamic scenarios, effectively reduces the impact of uncertainty, and optimizes operational efficiency.
Need to check novelty before this filing date? Find Prior Art