Search

CN-121981502-A - Urban area supply-demand unbalance short-time prediction method and system for network vehicle platform

CN121981502ACN 121981502 ACN121981502 ACN 121981502ACN-121981502-A

Abstract

The invention discloses a city regional supply-demand unbalance short-time prediction method and system for a network vehicle platform, which relate to the technical field of supply-demand prediction and comprise the steps of obtaining intersection steering limit, topography gradient, remaining endurance mileage of a carrier, accumulated online time length of the carrier, spatial distribution data of the carrier, real-time order demand and regional traffic deviation in the current period; based on the intersection steering limit and the topography gradient, generating a path resistance variable, and constructing a performance attenuation reference table by utilizing the residual endurance mileage of the carrier and the accumulated online time length of the carrier.

Inventors

  • HUANG YIPING
  • HU QIANG

Assignees

  • 成都大学

Dates

Publication Date
20260505
Application Date
20260408

Claims (10)

  1. 1. The urban area supply-demand unbalance short-time prediction method for the network about vehicle platform is characterized by comprising the following steps of: Acquiring intersection turning limit, topography gradient, remaining endurance mileage of a carrier, accumulated online time length of the carrier, spatial distribution data of the carrier, real-time order demand and regional success deviation of the current period; Generating a path resistance variable based on the intersection turning limit and the topography gradient, and constructing a performance attenuation reference table by using the residual endurance mileage of the carrier and the accumulated online time length of the carrier; Injecting the path resistance variable into the efficiency attenuation reference table, calculating the physical power consumption increment of the carrier, and converting the space distribution data of the carrier into an effective supply energy value with the physical energy consumption attribute; calculating the difference value between the effective supply energy value and the real-time order demand, and generating an unbalance prediction intensity index for indicating the supply-demand contradiction intensity of the current period area; Reversely adjusting the data acquisition granularity of the residual endurance mileage of the carrier and the accumulated online time length of the carrier in the next period according to the fluctuation frequency of the unbalance prediction intensity index, and And correcting the influence operator weight in the effective supply energy value conversion process by using the regional intersection deviation, and circularly compensating the effective supply energy value by taking the corrected influence operator weight as an input parameter of the next period.
  2. 2. The urban area supply-demand imbalance short-term prediction method for a network-based vehicle platform according to claim 1, further comprising, prior to generating the imbalance prediction strength index: acquiring historical supply and demand distribution data of a current period; generating a dynamic weighting factor for correcting the effective supply energy value based on the historical supply-demand distribution data and the real-time order demand; obtaining weighted effective supply energy values based on the dynamic weight factors; And generating a corrected unbalance prediction intensity index according to the weighted effective supply energy value and the real-time order demand.
  3. 3. The urban area supply-demand imbalance short-term prediction method for a network-based vehicle platform according to claim 2, further comprising, after generating the corrected imbalance prediction strength index: Obtaining a linear deviation value based on the intersection deviation of the corrected unbalance prediction intensity index and the area; Correcting the dynamic weight factor of the next period in real time by utilizing the linear deviation value; and correcting the contribution weight of the effective supply energy value in generating the corrected unbalance prediction intensity index according to the linear deviation value.
  4. 4. The urban area supply-demand imbalance short-term prediction method for a network-based vehicle platform according to claim 1, wherein the conversion of the effective supply energy value comprises: Calculating expected power consumption variables of the capacity carrier in unit distance according to the number of intersection steering limits and the fluctuation frequency of the topography gradient; carrying out physical loss correction on the residual endurance mileage of the capacity carrier by utilizing the expected power consumption variable to obtain the residual service range of the capacity carrier; Determining the single-effect energy weight of the capacity carrier in the current period according to the accumulated online time length of the capacity carrier; And carrying out space-time efficiency aggregation on the residual service voyages positioned at different coordinate positions by utilizing the single-effect energy weight to generate the effective supply energy value.
  5. 5. The urban area supply and demand unbalance short-term prediction method for a network taxi platform according to claim 4, wherein the obtaining the remaining service range of the capacity carrier comprises: matching an energy consumption sensitivity coefficient corresponding to a power source type of the capacity carrier based on the expected power consumption variable; Performing time-dependent coupling on the energy consumption sensitivity coefficient and the expected power consumption variable, and determining the real-time energy consumption redundancy of the capacity carrier under the current road section; and carrying out dynamic threshold stripping on the residual endurance mileage by utilizing the real-time energy consumption redundancy quantity to obtain the residual service range.
  6. 6. The urban area supply-demand imbalance short-term prediction method for a network-based vehicle platform according to claim 1, wherein the inverse adjustment of the data acquisition granularity comprises: Determining a transient disturbance characteristic value by utilizing the time domain distribution of the unbalance prediction intensity index in the current period; mapping and matching the transient disturbance characteristic value with a preset sampling confidence interval, and determining the perceived resource scheduling weight of the next period; and reversely adjusting the data acquisition granularity of the residual endurance mileage of the capacity carrier and the accumulated online time length of the capacity carrier by using the perceived resource scheduling weight.
  7. 7. The urban area supply-demand imbalance short-term prediction method for a network-based vehicle platform according to claim 6, wherein the determining a transient disturbance characteristic value comprises: stripping trend items of the unbalance prediction intensity indexes in the time domain dimension to obtain a high-frequency residual error sequence of the unbalance prediction intensity indexes; Calculating the energy distribution entropy of the high-frequency residual sequence in the current period; And quantifying the fluctuation intensity of the unbalance prediction intensity index by using the energy distribution entropy to generate the transient disturbance characteristic value.
  8. 8. Urban area supply-demand unbalance short-time prediction system for network about vehicle platform, which is characterized by comprising: The multidimensional data acquisition module is used for acquiring intersection steering limit, land gradient, remaining endurance mileage of the carrier, accumulated online time length of the carrier, spatial distribution data of the carrier, real-time order demand and regional intersection deviation in the current period; the energy efficiency reference construction module is used for generating a path resistance variable based on the intersection steering limit and the topography gradient, and constructing a performance attenuation reference table by utilizing the remaining endurance mileage of the carrier and the accumulated online time length of the carrier; The effective supply conversion module is used for injecting the path resistance variable into the efficiency attenuation reference table, calculating the physical power consumption increment of the carrier, and converting the space distribution data of the carrier into an effective supply energy value with the physical energy consumption attribute; the unbalance strength prediction module is used for carrying out difference calculation on the effective supply energy value and the real-time order demand and generating an unbalance prediction strength index for indicating the supply and demand contradiction strength of the current periodic area; the feedback correction module is used for reversely adjusting the data acquisition granularity of the residual endurance mileage of the carrier and the accumulated online time length of the carrier in the next period according to the fluctuation frequency of the unbalance prediction intensity index, and the feedback correction module is used for acquiring the data of the residual endurance mileage of the carrier and the accumulated online time length of the carrier in the next period And correcting the influence operator weight in the effective supply energy value conversion process by using the regional intersection deviation, and circularly compensating the effective supply energy value by taking the corrected influence operator weight as an input parameter of the next period.
  9. 9. An electronic device comprising a memory and a processor, wherein the memory is configured to store computer-executable instructions and the processor is configured to execute the computer-executable instructions, the computer-executable instructions when executed by the processor performing the steps of the method according to any one of claims 1 to 7.
  10. 10. A computer storage medium having stored thereon computer executable instructions which when executed by a processor perform the steps of the method according to any of claims 1 to 7.

Description

Urban area supply-demand unbalance short-time prediction method and system for network vehicle platform Technical Field The invention relates to the technical field of supply and demand prediction, in particular to a method and a system for short-time prediction of urban area supply and demand unbalance for a network vehicle platform. Background With the deep integration of mobile internet and intelligent transportation technology, the internet vehicle platform has become an important way for urban residents to travel. In order to improve the dispatch efficiency and the service quality of the platform, the supply and demand balance state in a short time in a specific city area is accurately predicted, and the method becomes a core task of the network taxi dispatching system. Conventional prediction methods are generally based on historical order data, real-time position information, weather, time period and other macroscopic features, and by establishing a statistical model or a machine learning model, the capacity supply and the order demand in the future time period are evaluated, so that supply and demand gaps are calculated. The prediction mechanism aims at finding out potential capacity exhaustion or surplus areas in advance, provides data support for dynamic price adjustment, capacity scheduling and incentive policy of the platform, and has important significance for relieving urban traffic jams and optimizing resource allocation. The existing supply and demand prediction technology is often focused on static quantity statistics of the capacity carriers or macroscopic estimation based on ideal work efficiency when the capacity supply capacity is estimated, the mode mainly focuses on the space distribution quantity of the capacity carriers, but ignores the complexity of urban geographic topological environments and the coupling influence of the dynamic physical properties of the capacity carriers on actual service capacity, under the actual running environment, due to the lack of deep consideration of road network physical obstruction factors and the real-time energy efficiency attenuation degree of the carriers, the system is difficult to quantify the actual loss of the capacity in the process of executing tasks, so that the calculated supply capacity often has larger deviation from the actual releasable capacity efficiency, and the modeling mode of nominal capacity supply ends ensures that the prediction result cannot accurately anchor the effective supply level under the complex physical constraints, and limits the resource scheduling precision and the system robustness of the platform under the variable urban environment. Disclosure of Invention The present application has been made in view of the above-mentioned state of the art. The embodiment of the application provides a method and a system for predicting the supply and demand unbalance of an urban area for a network vehicle platform in short time, which can accurately anchor the collapse of service capacity of a transport capacity carrier due to physical power consumption increment under a complex geographic environment, so that a predicted unbalance strength index is closer to a real physical supply and demand level. According to one aspect of the application, there is provided a urban area supply-demand imbalance short-time prediction method for a network-based vehicle platform, comprising: Acquiring intersection turning limit, topography gradient, remaining endurance mileage of a carrier, accumulated online time length of the carrier, spatial distribution data of the carrier, real-time order demand and regional success deviation of the current period; Generating a path resistance variable based on the intersection turning limit and the topography gradient, and constructing a performance attenuation reference table by using the residual endurance mileage of the carrier and the accumulated online time length of the carrier; Injecting the path resistance variable into the efficiency attenuation reference table, calculating the physical power consumption increment of the carrier, and converting the space distribution data of the carrier into an effective supply energy value with the physical energy consumption attribute; calculating the difference value between the effective supply energy value and the real-time order demand, and generating an unbalance prediction intensity index for indicating the supply-demand contradiction intensity of the current period area; Reversely adjusting the data acquisition granularity of the residual endurance mileage of the carrier and the accumulated online time length of the carrier in the next period according to the fluctuation frequency of the unbalance prediction intensity index, and And correcting the influence operator weight in the effective supply energy value conversion process by using the regional intersection deviation, and circularly compensating the effective supply energy value by taking the corr