Low-altitude infrastructure operation cost optimization method for quantitative engineering model

Abstract

This invention discloses a method for optimizing the operating costs of low-altitude infrastructure based on a quantitative engineering model, comprising the following steps: obtaining a structured dataset; constructing a set of operating elements for low-altitude infrastructure; establishing a quantitative engineering model; performing demand modeling and load analysis to obtain the demand distribution of the service area set on a time series set; establishing an operating cost optimization model; solving the operating cost optimization model using a symplectic geometrical structure-preserving optimization algorithm to obtain resource allocation results and operation scheduling results; performing simulation evaluation to obtain operating cost results and resource utilization rate indicators, and updating the parameters of the quantitative engineering model; outputting the operating cost optimization results to improve resource utilization and demand satisfaction rate, and enhance the stability and intelligence level of the low-altitude infrastructure system operation.

Description

Technical Field

[0001] This invention relates to the field of low-altitude infrastructure operation and management, and in particular to a method for optimizing the operation cost of low-altitude infrastructure based on a quantitative engineering model. Background Technology

[0002] With the rapid development of the low-altitude economy, application scenarios such as drone transportation, low-altitude logistics, urban air traffic, and emergency support are constantly expanding. The construction and operation of low-altitude infrastructure is gradually becoming a key foundation supporting the development of related industries. Low-altitude infrastructure typically includes take-off and landing points, energy supply facilities, communication and surveillance equipment, and operation support nodes. It is characterized by its wide distribution, large number of nodes, and significant dynamic changes in operational status. In actual operation, different infrastructure nodes need to allocate resources and schedule operations according to business needs at different times to meet the business demands of the service area. Therefore, how to reduce overall operating costs while ensuring service capabilities has become one of the core technical issues in the current operation and management of low-altitude infrastructure.

[0003] In existing technologies, the analysis and optimization of infrastructure operating costs typically employ static cost accounting methods or resource allocation approaches based on empirical rules. For example, average cost indicators are obtained through statistical analysis of historical operating data, and infrastructure is configured accordingly; or heuristic rules are used for resource scheduling based on simple demand forecasts. However, these methods mostly focus on single-dimensional cost analysis and lack unified modeling of the complex relationships between multiple factors such as infrastructure nodes, service areas, resource types, and time series, making it difficult to accurately reflect the dynamic characteristics of low-altitude infrastructure during actual operation. Summary of the Invention

[0004] One objective of this invention is to propose a method for optimizing the operating costs of low-altitude infrastructure based on quantitative engineering models. This invention fully utilizes big data analysis technology, quantitative engineering modeling methods, and symplectic geometric structure-preserving optimization algorithms to uniformly model and solve the resource allocation relationship, demand distribution relationship, and operating cost relationship in the operation process of low-altitude infrastructure. It realizes the optimization calculation of resource allocation and operation scheduling under multiple constraints, and has the advantages of high modeling accuracy, strong stability of optimization results, high resource utilization efficiency, and low overall operating costs.

[0005] A method for optimizing the operating costs of low-altitude infrastructure based on a quantitative engineering model, according to an embodiment of the present invention, includes the following steps: Acquire and preprocess multi-source data related to low-altitude infrastructure operations to obtain a structured dataset; Based on structured datasets, a set of operational elements for low-altitude infrastructure is constructed. A quantitative engineering model is established based on the set of operational elements of low-altitude infrastructure. By using business demand data and environmental data from multiple sources, demand modeling and load analysis are performed to obtain the demand distribution of the service area set on the time series set. Based on the quantitative engineering model and demand distribution, an operating cost optimization model is established; The symplectic geometric structure-preserving optimization algorithm is used to solve the operation cost optimization model, and the resource allocation results and operation scheduling results are obtained. Based on the resource allocation results and operation scheduling results, simulation evaluation is conducted to obtain the operating cost results and resource utilization rate indicators, and the parameters of the quantitative engineering model are updated based on the operating cost results and resource utilization rate indicators. Based on the updated quantitative engineering model, the results of operational cost optimization are output.

[0006] Optionally, the multi-source data includes infrastructure node data, equipment operating status data, business demand data, environmental data, and historical operating cost data, and the preprocessing includes data cleaning, time alignment, and standardization.

[0007] Optionally, the construction of the set of low-altitude infrastructure operation elements specifically includes: Based on structured datasets, spatial distribution information, node attribute information, resource attribute information, and timestamp information associated with low-altitude infrastructure operations are extracted. Based on spatial distribution information and node attribute information, nodes of low-altitude infrastructure are identified and classified to construct an infrastructure node set. Based on spatial distribution information and business demand data, the low-altitude service area is divided into regions to construct a service area set; Based on resource attribute information and equipment operation status data, the resources involved in the operation of low-altitude infrastructure are identified and classified, and a set of resource types is constructed. Based on timestamp information, the data records during the operation of low-altitude infrastructure are discretized over time to construct a time series set; By combining the sets of infrastructure nodes, service areas, resource types, and time series, a set of operational elements for low-altitude infrastructure is formed.

[0008] Optionally, the establishment of the quantitative engineering model specifically includes: Based on the set of infrastructure nodes and the set of service areas in the set of low-altitude infrastructure operation elements, establish the service association relationship between the set of infrastructure nodes and the set of service areas; Resource allocation variables are constructed by using the set of infrastructure nodes, resource types, and time series data from the set of low-altitude infrastructure operation elements. Based on the service area set and time series set in the set of low-altitude infrastructure operation elements, a demand function is constructed. Based on the set of infrastructure nodes and resource allocation variables, construct facility capacity constraints; Based on service relationships, resource configuration variables, and requirement functions, construct requirement satisfaction constraints. A cost parameter function is constructed based on the set of infrastructure nodes, the set of resource types, and the set of time series data. Based on service relationships, resource allocation variables, demand functions, facility capacity constraints, demand satisfaction constraints, and cost parameter functions, a unified model is used to model the operation process of low-altitude infrastructure, resulting in a quantitative engineering model.

[0009] Optionally, obtaining the demand distribution specifically includes: Obtain business demand data and environmental data from multi-source data, and match the business demand data and environmental data according to the service area set and time series set to obtain the original demand data and environmental impact data of each service area under each time slice; Based on the original demand data of each service area under each time slice, the basic demand of each service area under each time slice is calculated. Based on the environmental impact data of each service area under each time slice, the environmental impact coefficient of each service area under each time slice is quantified. Based on the basic demand and environmental impact coefficient of each service area under each time slice, determine the adjusted demand of each service area under each time slice; Based on the correction demand of each service area under each time slice, they are arranged in chronological order to obtain the demand distribution of the service area set on the time series set.

[0010] Optionally, the establishment of the operating cost optimization model specifically includes: Based on the resource allocation variables, demand function, and cost parameter function in the quantitative engineering model, an operating cost objective function is constructed. Based on the facility capacity constraints in the quantitative engineering model, resource allocation constraints are constructed. Based on the requirement satisfaction constraints in the quantitative engineering model, construct the requirement satisfaction constraints. Based on the demand distribution of the service area set on the time series set, the operating cost objective function is weighted and modified to construct a demand-weighted objective function. An operational cost optimization model is constructed based on the operational cost objective function, resource allocation constraints, demand satisfaction constraints, and demand weighted objective function.

[0011] Optionally, obtaining the resource configuration results and operation scheduling results specifically includes: The resource allocation variables in the operating cost optimization model are used as the solution objects of the symplectic geometrical structure-preserving optimization algorithm, and the operating cost objective function, resource allocation constraints, and demand satisfaction constraints are used as the inputs of the symplectic geometrical structure-preserving optimization algorithm. Based on resource configuration variables, construct state variables and covariates that correspond one-to-one with the resource configuration variables; A Hamiltonian function is constructed based on state variables, covariates, operating cost objective function, resource allocation constraints, and demand satisfaction constraints. Based on the Hamiltonian function, a symplectic geometric evolution relationship between state variables and covariates is constructed, and the symplectic geometric evolution relationship is expanded step by step according to the structure-preserving discretization method. The symplectic geometric structure-preserving numerical integration method is adopted to discretize the symplectic geometric evolution relationship after step-by-step expansion, so as to obtain the discrete iterative update relationship of state variables and covariates, and to iteratively update the state variables and covariates according to the discrete iterative update relationship. After each iteration update, calculate the resource configuration constraint residual and the demand satisfaction constraint residual corresponding to the updated state variable, and perform constraint correction on the updated state variable based on the resource configuration constraint residual and the demand satisfaction constraint residual to obtain the corrected state variable. Convergence is determined based on the change in the corrected state variables between two adjacent iterations. When the change is less than the preset convergence threshold, and the residuals of the resource allocation constraint and the requirement satisfaction constraint are both less than the preset constraint threshold, the iteration stops, and the resource allocation result is determined based on the converged corrected state variables. Based on the temporal changes of resource allocation results in the time series set, the operation scheduling results are generated.

[0012] Optionally, the parameter update of the quantitative engineering model specifically includes: Based on the resource allocation results and operation scheduling results, a simulation evaluation is conducted to build a simulation operation environment. The operation status of each infrastructure node in the simulation operation environment is simulated and calculated to obtain the simulation calculation results. Based on the simulation results, the actual operating status of each infrastructure node for each resource type under each time slice is extracted, and the operating cost of each infrastructure node under each time slice is calculated by combining the cost parameter function. The total operating cost of low-altitude infrastructure is obtained by summing up the operating costs of each infrastructure node in each time slice and within the time series set. Based on the simulation results, the resource usage of each infrastructure node under each time slice is extracted, and the resource utilization rate of each infrastructure node under each time slice is calculated. By summarizing and analyzing the resource utilization rate of each infrastructure node in each time slice, the overall resource utilization rate index of low-altitude infrastructure within the time series set is obtained. Based on total operating cost and overall resource utilization indicators, the cost parameter function and demand function in the quantitative engineering model are updated.

[0013] Optionally, the updated quantitative engineering model is used as the new calculation basis. Resource allocation variables, cost parameter functions, and demand functions in the model are re-extracted. Based on the updated parameters, the resource allocation status and operation scheduling status of low-altitude infrastructure within the time series set are calculated. According to the configuration of each infrastructure node for each resource type in each time slice, the corresponding resource allocation results are generated. Combining the changes of resource allocation results in the time series set, operation scheduling results are generated. The resource allocation results and operation scheduling results are summarized and organized to form a comprehensive result of the resource allocation method and scheduling arrangement of low-altitude infrastructure in different time slices. The comprehensive result is output as the operation cost optimization result.

[0014] The beneficial effects of this invention are: This invention constructs a set of operational elements for low-altitude infrastructure and establishes a quantitative engineering model based on this set. It unifies and correlates multiple dimensions, including infrastructure node sets, service area sets, resource type sets, and time series sets, effectively addressing the lack of systematic modeling methods in existing technologies. By processing multi-source data and fusing business demand data with environmental data in the model, the demand distribution of service areas over time series sets more realistically reflects actual operational conditions, significantly improving the accuracy of demand modeling and providing a reliable data foundation for subsequent operational cost optimization.

[0015] This invention constructs an operational cost optimization model that includes an operational cost objective function, resource allocation constraints, and demand satisfaction constraints. This model unifies and integrates the resource allocation relationships, demand satisfaction relationships, and cost variation relationships of low-altitude infrastructure, achieving collaborative optimization under multiple constraints and overcoming the problems of simple optimization models and insufficient constraint consideration in existing technologies. Furthermore, by introducing a symplectic geometrical structure-preserving optimization algorithm to solve the operational cost optimization model, the stability of the model structure is maintained during the iteration process. This ensures that the resource allocation variables exhibit good convergence and numerical stability during optimization, effectively avoiding convergence instability and local optima problems that are prone to occur in traditional optimization methods, thereby improving the reliability of the optimization results.

[0016] This invention simulates and evaluates resource allocation and operational scheduling results to obtain operating cost results and resource utilization indicators. Based on these results, it updates the parameters of a quantitative engineering model, enabling dynamic adjustment of model parameters according to operational status, thus achieving closed-loop optimization control of the low-altitude infrastructure operation process. Through this technical solution, this invention not only reduces overall operating costs while meeting service demands but also improves resource utilization efficiency, making the operation of low-altitude infrastructure more efficient, stable, and intelligent, demonstrating significant engineering application value. Attached Figure Description

[0017] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings: Figure 1 This is an overall flowchart of a method for optimizing the operating costs of low-altitude infrastructure based on a quantitative engineering model, as proposed in this invention. Figure 2 This is a schematic diagram illustrating the construction of a quantitative engineering model for a method to optimize the operating costs of low-altitude infrastructure based on a quantitative engineering model, as proposed in this invention. Figure 3 This diagram illustrates the construction of resource allocation and operation scheduling results for a low-altitude infrastructure operation cost optimization method based on a quantitative engineering model proposed in this invention. Detailed Implementation

[0018] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, illustrating only the basic structure of the invention, and therefore only show the components relevant to the invention.

[0019] refer to Figures 1-3 A method for optimizing the operating costs of low-altitude infrastructure based on quantitative engineering models includes the following steps: Acquire and preprocess multi-source data related to low-altitude infrastructure operations to obtain a structured dataset; Based on structured datasets, a set of operational elements for low-altitude infrastructure is constructed. A quantitative engineering model is established based on the set of operational elements of low-altitude infrastructure. By using business demand data and environmental data from multiple sources, demand modeling and load analysis are performed to obtain the demand distribution of the service area set on the time series set. Based on the quantitative engineering model and demand distribution, an operating cost optimization model is established; The symplectic geometric structure-preserving optimization algorithm is used to solve the operation cost optimization model, and the resource allocation results and operation scheduling results are obtained. Based on the resource allocation results and operation scheduling results, simulation evaluation is conducted to obtain the operating cost results and resource utilization rate indicators, and the parameters of the quantitative engineering model are updated based on the operating cost results and resource utilization rate indicators. Based on the updated quantitative engineering model, the results of operational cost optimization are output.

[0020] In this embodiment, the multi-source data includes infrastructure node data, equipment operation status data, business demand data, environmental data, and historical operating cost data. Preprocessing includes data cleaning, time alignment, and standardization.

[0021] In this embodiment, the construction of the set of operational elements for low-altitude infrastructure specifically includes: Based on structured datasets, spatial distribution information, node attribute information, resource attribute information, and timestamp information associated with low-altitude infrastructure operations are extracted. The process of extracting spatial distribution information, node attribute information, resource attribute information, and timestamp information is as follows: Field identification, field filtering, and field mapping are performed on various fields in the structured dataset. Data representing the geographical location, coverage, and regional distribution of infrastructure nodes are extracted as spatial distribution information. Data representing the category, capacity, service capability, operating status, and connection relationship of infrastructure nodes are extracted as node attribute information. Data representing the category, quantity, capacity, usage status, and location of resources are extracted as resource attribute information. Based on spatial distribution information and node attribute information, nodes of low-altitude infrastructure are identified and classified to construct an infrastructure node set. The construction process of the infrastructure node set is as follows: Based on the geographical location, coverage boundary and regional distribution of each infrastructure object in the spatial distribution information, and combined with the node category, service capacity, operation status, connection relationship and capacity parameters of each infrastructure object in the node attribute information, each infrastructure object in the structured dataset is identified one by one. Infrastructure objects with independent service functions, independent operation attributes and independent spatial locations are identified as infrastructure nodes. The infrastructure nodes are then classified according to node category, service capacity range and regional distribution characteristics. All classified infrastructure nodes are uniformly numbered and represented in a set to obtain the infrastructure node set. Based on spatial distribution information and business demand data, the low-altitude service area is divided into regions to construct a service area set; The process of constructing the service area set is as follows: Based on the geographical location, coverage boundary, spatial adjacency and service reach of each infrastructure node in the spatial distribution information, combined with the business demand intensity, frequency, type and time period distribution of different locations in the business demand data, the spatial units within the low-altitude service range are aggregated and divided. Areas with similar business demand distribution, consistent service coverage and spatial continuity are identified as the same service area. The service areas obtained are uniformly identified and aggregated to obtain the service area set. Based on resource attribute information and equipment operation status data, the resources involved in the operation of low-altitude infrastructure are identified and classified, and a set of resource types is constructed. The process of constructing the resource type set is as follows: Based on the resource name, resource function, resource capacity, resource configuration location and infrastructure node to which the resource belongs in the resource attribute information, and combined with the activation status, occupancy status, load status, maintenance status and fault status of the various resources in the equipment operation status data, the various resources involved in the operation of low-altitude infrastructure are identified item by item, and resources with the same functional attributes, configuration methods and operation characteristics are classified into the same resource type. The various resource types obtained are uniformly identified and collectively represented to obtain the resource type set. Based on timestamp information, the data records during the operation of low-altitude infrastructure are discretized over time to construct a time series set; The construction process of the time series set is as follows: based on the generation time, update time and operating segment of each data record in the timestamp information, the continuous time in the operation of the low-altitude infrastructure is divided into intervals according to a unified time scale. Data records in the same time interval are grouped into the same time slice, and the time slices are arranged sequentially and uniformly identified according to the time sequence. All time slices are represented in a set to obtain the time series set. The set of infrastructure nodes, service areas, resource types, and time series are combined to form a set of low-altitude infrastructure operation elements; The formation process of the low-altitude infrastructure operation element set is as follows: taking each infrastructure node in the infrastructure node set as the operation carrier, each service area in the service area set as the service object, each resource type in the resource type set as the configuration object, and each time slice in the time series set as the time sequence dimension, the correspondence between infrastructure nodes, service areas, resource types and time slices is uniformly associated and combined to represent the correspondence. Various elements that represent the low-altitude infrastructure's resource allocation and operation scheduling in different service areas under different time slices are integrated to form a low-altitude infrastructure operation element set that includes spatial, resource and time dimensions.

[0022] In this embodiment, the establishment of the quantitative engineering model specifically includes: Based on the set of infrastructure nodes and the set of service areas in the set of low-altitude infrastructure operation elements, establish the service association relationship between the set of infrastructure nodes and the set of service areas; The process of establishing service associations is as follows: taking each infrastructure node in the infrastructure node set as the service provider and each service area in the service area set as the service recipient, based on the geographical location, service coverage, service capability boundary, and operational reach of each infrastructure node, and combined with the spatial location, regional boundary, and business carrying capacity of each service area, the service reachability between each infrastructure node and each service area is matched one by one. When the service coverage of an infrastructure node reaches the service area and the service capability of the infrastructure node meets the business carrying requirements of the service area, it is determined that there is a service association between the infrastructure node and the service area; otherwise, it is determined that there is no service association between the infrastructure node and the service area, thus forming a service association between the infrastructure node set and the service area set. Resource allocation variables are constructed by using the set of infrastructure nodes, resource types, and time series data from the set of low-altitude infrastructure operation elements. The specific process of constructing resource configuration variables is as follows: taking each infrastructure node in the infrastructure node set as the resource configuration carrier, each resource type in the resource type set as the resource configuration object, and each time slice in the time series set as the time sequence dimension of resource configuration, the configuration status of each infrastructure node corresponding to each resource type in each time slice is associated and represented, and the resource configuration quantity, resource activation status and resource occupancy status corresponding to the combination of infrastructure node, resource type and time slice are defined as resource configuration variables; Based on the service area set and time series set in the set of low-altitude infrastructure operation elements, a demand function is constructed. The specific process of constructing the demand function is as follows: taking each service area in the service area set as the demand carrier, and each time slice in the time series set as the demand time sequence dimension, the business demand situation corresponding to each service area under each time slice is associated and represented, the business demand quantity, business demand frequency and business demand intensity of each service area under different time slices are uniformly represented, and the demand value corresponding to the combination relationship between service area and time slice is defined as the demand function. Based on the set of infrastructure nodes and resource allocation variables, construct facility capacity constraints; The construction of facility capacity constraint relationship is as follows: taking each infrastructure node in the set of infrastructure nodes as the capacity constraint object, and combining the configuration of each infrastructure node in each time slice with the configuration of each resource type in each resource configuration variable, extracting the node capacity, resource carrying capacity limit, operating load limit and service capacity boundary of each infrastructure node, and constraining the total resource demand corresponding to all resource types configured by each infrastructure node in the same time slice with the maximum carrying capacity of the infrastructure node, forming a facility capacity constraint relationship that represents the resource configuration boundary of each infrastructure node. Based on service relationships, resource configuration variables, and requirement functions, construct requirement satisfaction constraints. The specific process of constructing the demand satisfaction constraint relationship is as follows: taking the service reachability correspondence between each infrastructure node and each service area in the service association relationship as the basis for demand allocation, combining the configuration of each infrastructure node in each time slice of each resource type in the resource configuration variable, and the business demand of each service area in each time slice in the demand function, the resource supply capacity configured by each infrastructure node providing services in the same service area in the same time slice is summarized, and the summarized resource supply capacity is constrained with the business demand of the service area in the corresponding time slice to form the demand satisfaction constraint relationship; A cost parameter function is constructed based on the set of infrastructure nodes, the set of resource types, and the set of time series data. The construction process of the cost parameter function is as follows: taking each infrastructure node in the infrastructure node set as the cost-bearing object, each resource type in the resource type set as the cost classification object, and each time slice in the time series set as the cost time series dimension, the operation cost corresponding to each infrastructure node configured with each resource type under each time slice is represented by association, the resource usage cost, operation and maintenance cost, energy consumption cost and scheduling cost corresponding to the combination of infrastructure node, resource type and time slice are uniformly collected, and the comprehensive cost value corresponding to the combination of the three is defined as the cost parameter function, thus forming the cost parameter function; Based on service relationships, resource allocation variables, demand functions, facility capacity constraints, demand satisfaction constraints, and cost parameter functions, a unified model is used to model the operation process of low-altitude infrastructure, resulting in a quantitative engineering model. The quantitative engineering model is derived as follows: It uses service relationships as the basis for service correspondence between the set of infrastructure nodes and the set of service areas; resource allocation variables as the representation basis for the allocation of resource types by the set of infrastructure nodes under a time-series data set; demand functions as the representation basis for the business demands of the set of service areas under a time-series data set; facility capacity constraints as the capability boundary for resource allocation by the set of infrastructure nodes under a time-series data set; demand satisfaction constraints as the constraint basis for the fulfillment of business demands by the set of service areas under a time-series data set; and cost parameter functions as the representation basis for the operating costs incurred by the set of infrastructure nodes in allocating resource types under a time-series data set. This unified association and integrated expression of service coverage relationships, resource allocation relationships, business demand relationships, capacity constraint relationships, demand satisfaction relationships, and operating cost relationships during the operation of low-altitude infrastructure forms the quantitative engineering model.

[0023] In this embodiment, obtaining the demand distribution specifically includes: Obtain business demand data and environmental data from multi-source data, and match the business demand data and environmental data according to the service area set and time series set to obtain the original demand data and environmental impact data of each service area under each time slice; The acquisition of raw demand data and environmental impact data is specifically as follows: For each record in the business demand data, the corresponding business occurrence location, business occurrence time, business demand type, and business demand quantity are matched one-to-one with each service area in the service area set and each time slice in the time series set. For each record in the environmental data, the corresponding environmental occurrence location, environmental occurrence time, and environmental status information are matched one-to-one with each service area in the service area set and each time slice in the time series set. Business demand data matched within the same service area and time slice are aggregated as the raw demand data for that service area within that time slice. Environmental data matched within the same service area and time slice are collected as the environmental impact data for that service area within that time slice. Based on the original demand data of each service area under each time slice, the basic demand of each service area under each time slice is calculated. The process of obtaining the basic demand is as follows: the original demand data of each service area under each time slice is classified, summarized and counted, the quantity of various business demands corresponding to the same service area under the same time slice is accumulated, and the basic demand of the service area under the time slice is obtained by uniformly counting according to the frequency of business demand occurrence, the quantity corresponding to the type of business demand and the scale of business demand. Based on the environmental impact data of each service area under each time slice, the environmental impact coefficient of each service area under each time slice is quantified. The process of obtaining the environmental impact coefficient is as follows: Environmental impact data for each service area under each time slot is categorized and extracted to obtain meteorological status data, visibility data, wind speed and direction data, precipitation data, temperature and humidity data, and airspace environmental status data related to the operation of low-altitude infrastructure. Environmental impact data is then aggregated according to service area and time slot, and various environmental indicators for the same service area under the same time slot are uniformly mapped. Each environmental indicator is numerically processed, converting indicators representing the strength of the environmental state into corresponding environmental indicator values, and non-numerical environmental state information is graded and assigned values ​​according to its impact level. Based on the direction and degree of impact of each environmental indicator on the operation of low-altitude infrastructure, the values ​​of each environmental indicator are homogenized. The environmental impact values ​​for the same service area under the same time slot are weighted and summarized to obtain the comprehensive environmental impact value for the corresponding service area under the corresponding time slot. The comprehensive environmental impact value is then mapped to the environmental impact coefficient. Based on the basic demand and environmental impact coefficient of each service area in each time slot, the adjusted demand of each service area in each time slot is determined. The adjusted demand of each service area in each time slot is the product of the corresponding basic demand and the corresponding environmental impact coefficient. Based on the correction demand of each service area under each time slice, they are arranged in chronological order to obtain the demand distribution of the service area set on the time series set.

[0024] In this embodiment, the establishment of the operating cost optimization model specifically includes: Based on the resource allocation variables, demand function, and cost parameter function in the quantitative engineering model, an operating cost objective function is constructed. The construction process of the operating cost objective function is as follows: Using the resource configuration of each infrastructure node in each time slice as the basis for cost calculation, the resource configuration quantity corresponding to each resource type configured by each infrastructure node in each time slice is extracted one by one; using the cost value corresponding to the infrastructure node, resource type, and time slice in the cost parameter function as the unit cost parameter, the correspondence between the resource configuration quantity and the unit cost parameter is established; for different resource types configured by the same infrastructure node in the same time slice, the resource usage cost, operation and maintenance cost, energy consumption cost, and scheduling cost corresponding to each resource type are calculated separately, and the costs corresponding to each resource type of the same infrastructure node in the same time slice are summarized to obtain the node operating cost of the infrastructure node in that time slice; the node operating costs of all infrastructure nodes in all time slices are accumulated to form the total operating cost of the low-altitude infrastructure over the entire time series; and the total operating cost is used as the function value of the operating cost objective function to form the operating cost objective function. Based on the facility capacity constraints in the quantitative engineering model, resource allocation constraints are constructed. The process of constructing resource allocation constraints is as follows: taking each infrastructure node in the infrastructure node set as the constraint object, and combining the configuration of each infrastructure node for each resource type in each time slice in the resource allocation variables, the resource allocation quantity of each infrastructure node for each resource type in each time slice is extracted one by one; based on the maximum resource carrying capacity, resource capacity limit and operating load limit of each infrastructure node in the facility capacity constraint relationship, the resource allocation quantity corresponding to all resource types configured by the same infrastructure node in the same time slice is summarized, and the summarized resource allocation quantity is correspondingly limited with the maximum resource carrying capacity of the infrastructure node in the corresponding time slice to form resource allocation constraints; Based on the requirement satisfaction constraints in the quantitative engineering model, construct the requirement satisfaction constraints. The specific process of constructing the demand satisfaction constraint conditions is as follows: taking each service region in the service region set as the demand constraint object, and combining the business demand volume of each service region in each time slice in the demand function, the demand data of each service region in each time slice is extracted one by one; based on the service association relationship, the set of infrastructure nodes that provide services to each service region is determined; combined with the resource configuration variables, the resource supply capacity corresponding to each resource type configured by the infrastructure nodes in the corresponding time slice is extracted, and the resource supply capacity provided by multiple infrastructure nodes for the same service region in the same time slice is summarized; the summarized resource supply capacity is correspondingly limited with the business demand volume of the service region in the corresponding time slice to form the demand satisfaction constraint conditions; Based on the demand distribution of the service area set on the time series set, the operating cost objective function is weighted and modified to construct a demand weighted objective function. The demand weighted objective function is the sum of the products of the business demand of each service area in each time slice and the corresponding demand weight coefficient. An operation cost optimization model is constructed based on the objective function of operating costs, resource allocation constraints, demand satisfaction constraints, and demand weighted objective function. The construction process of the operation cost optimization model is as follows: The operation cost objective function is used as the objective expression for optimization, with the total operation cost of low-altitude infrastructure within the time series set as the optimization objective; resource allocation constraints are used as boundary limits for resource allocation, restricting the total resource allocation of each infrastructure node in each time slice; demand satisfaction constraints are used as business demand guarantee constraints, limiting the business demand satisfaction of each service area in each time slice; a demand weighted objective function is used as a demand priority adjustment factor, weighting the business demand of different service areas in different time slices; the operation cost objective function and the demand weighted objective function are combined to construct a unified objective expression, and the resource allocation constraints and demand satisfaction constraints are used as a constraint set. Resource allocation variables are introduced as decision variables, and the objective expression and constraint set are uniformly integrated. The resource allocation relationship, demand satisfaction relationship, and cost change relationship among the infrastructure node set, service area set, resource type set, and time series set are represented holistically, forming an operation cost optimization model with the objective of minimizing operation cost and the condition of satisfying demand and resource constraints.

[0025] In this embodiment, obtaining the resource allocation results and operation scheduling results specifically includes: The resource allocation variables in the operating cost optimization model are used as the solution objects of the symplectic geometrical structure-preserving optimization algorithm, and the operating cost objective function, resource allocation constraints, and demand satisfaction constraints are used as the inputs of the symplectic geometrical structure-preserving optimization algorithm. Based on resource configuration variables, construct state variables and covariates that correspond one-to-one with the resource configuration variables; The construction process of state variables and covariates is as follows: Based on the number of each infrastructure node's configuration of each resource type in each time slice, each resource configuration variable is indexed and expanded according to the combination relationship of infrastructure node, resource type and time slice, and each expanded resource configuration variable is directly mapped to the corresponding state variable. Each state variable represents the configuration status of each infrastructure node for each resource type in each time slice, and a corresponding covariate is introduced for each state variable. A Hamiltonian function is constructed based on state variables, covariates, operating cost objective function, resource allocation constraints, and demand satisfaction constraints. The construction process of the Hamiltonian function is as follows: the operating cost objective function is used as the objective term in the Hamiltonian function, and the resource allocation cost change relationship corresponding to each state variable is introduced into the objective term; covariates are used as constraint transitive variables, and the resource allocation constraints and demand satisfaction constraints are mapped to the evolution process of each state variable, and each covariate is associated with the corresponding constraint term; the state variables, covariates, operating cost objective term, resource allocation constraints and demand satisfaction constraints of each infrastructure node, each resource type and each time slice are uniformly combined to form a Hamiltonian function that includes resource allocation status, constraint effect and cost change relationship; Based on the Hamiltonian function, a symplectic geometric evolution relationship between state variables and covariates is constructed, and the symplectic geometric evolution relationship is expanded step by step according to the structure-preserving discretization method. The step-by-step unfolding process of the symplectic geometric evolution relationship is as follows: Based on the coupling relationship between state variables and covariates in the Hamiltonian function, a change relationship is established for each state variable relative to its corresponding covariate, and a change relationship is established for each covariate relative to its corresponding state variable. The change of the state variable is driven by the corresponding covariate, and the change of the covariate is jointly driven by the change of the corresponding state variable and the operating cost objective function, thus forming the symplectic geometric evolution relationship. The symplectic geometric evolution relationship is decomposed, and the overall evolution process is broken down into sub-evolution steps. In each sub-evolution step, some state variables or some covariates are updated respectively, thus completing the construction of the symplectic geometric evolution relationship and the structure-preserving step-by-step unfolding. The symplectic geometric structure-preserving numerical integration method is adopted to discretize the symplectic geometric evolution relationship after step-by-step expansion, so as to obtain the discrete iterative update relationship of state variables and covariates, and to iteratively update the state variables and covariates according to the discrete iterative update relationship. The iterative update process is as follows: For each sub-evolution step after step-by-step expansion, each state variable and each covariate is discretely calculated sequentially according to the set integration step size. In each sub-evolution step, the corresponding state variable is updated based on the change in the covariate under the current iteration step, and the corresponding covariate is updated based on the change in the updated state variable, and the corresponding state variable is updated based on the change in the updated covariate. After completing the state variable update and covariate update of a sub-evolution step, the update result is used as the input of the next sub-evolution step, until the continuous calculation of all sub-evolution steps is completed, and the discrete update results of all state variables and all covariates under the current iteration step are obtained. The discrete update results under the current iteration step are used as the initial values ​​of the next iteration step, and the state variable update, covariate update and sub-evolution step propagation are repeatedly executed to form the iterative update process of state variables and covariates. After each iteration update, calculate the resource configuration constraint residual and the demand satisfaction constraint residual corresponding to the updated state variable, and perform constraint correction on the updated state variable based on the resource configuration constraint residual and the demand satisfaction constraint residual to obtain the corrected state variable. The process of obtaining the corrected state variables is as follows: After each iteration update, the updated state variables are substituted into the resource allocation constraints, and the difference between the resource allocation result corresponding to each updated state variable and the resource allocation constraints is compared item by item to obtain the resource allocation constraint residual; the updated state variables are substituted into the demand satisfaction constraints, and the difference between the resource supply result corresponding to each updated state variable and the demand satisfaction constraints is compared item by item to obtain the demand satisfaction constraint residual; based on the resource allocation constraint residual and the demand satisfaction constraint residual, the updated state variables are corrected item by item. For updated state variables that cause the resource allocation result to exceed the resource allocation constraints, the corresponding resource allocation constraints are corrected. The conditional residuals are adjusted by decreasing the updated state variable; for the updated state variable that causes the resource supply result to be lower than the demand satisfaction constraint, the updated state variable is adjusted by increasing the corresponding demand satisfaction constraint residual; after one adjustment, the adjusted state variable is substituted into the resource allocation constraint and the demand satisfaction constraint, the resource allocation constraint residual and the demand satisfaction constraint residual are recalculated, and the adjusted state variable is further corrected according to the recalculated resource allocation constraint residual and the demand satisfaction constraint residual, until the resource allocation constraint residual and the demand satisfaction constraint residual corresponding to the adjusted state variable both meet the set requirements, and the corrected state variable is obtained; Convergence is determined based on the change in the corrected state variables between two adjacent iterations. When the change is less than the preset convergence threshold, and the residuals of the resource allocation constraint and the requirement satisfaction constraint are both less than the preset constraint threshold, the iteration stops, and the resource allocation result is determined based on the converged corrected state variables. Based on the temporal changes of resource allocation results in the time series set, the operation scheduling results are generated; The specific process for generating the operation scheduling results is as follows: The resource configuration status corresponding to each time slice in the resource configuration results is read sequentially; the configuration changes of the same infrastructure node for each resource type under different time slices are extracted; and the resource configuration increases / decreases, switching changes, and unchanged resource configurations between adjacent time slices are compared item by item. Based on the order of changes in resource configuration results between time slices, the resource input time, resource exit time, resource adjustment time, and continuous resource configuration period for each infrastructure node in the time series set are determined. The configuration change processes of each infrastructure node for each resource type under each time slice are connected in chronological order to form a time-series scheduling arrangement reflecting the order and change process of resource configuration, thus obtaining the operation scheduling results.

[0026] In this embodiment, the parameter update of the quantitative engineering model specifically includes: Based on the resource allocation results and operation scheduling results, a simulation evaluation is conducted to build a simulation operation environment. The operation status of each infrastructure node in the simulation operation environment is simulated and calculated to obtain the simulation calculation results. The process of obtaining the simulation results is as follows: The configuration of each infrastructure node in the resource allocation results for each resource type under each time slice is imported into the simulation environment. The resource input order, resource adjustment order, resource exit order, and continuous configuration period of each infrastructure node in the time series set are also imported into the simulation environment. Based on the set of low-altitude infrastructure operation elements and the quantitative engineering model, the operational relationships between each infrastructure node, the service correspondence between each infrastructure node and its service area, and the resource operation constraints of each infrastructure node under each time slice are established in the simulation environment. The results are then processed according to the time series set. The simulation sequentially executes resource configuration and scheduling processes matching the corresponding time slices within each infrastructure node in the simulation environment, based on the time sequence. Within each time slice, the simulation calculates the input, usage, idle, switching, and exit status of each infrastructure node for each resource type. Combining the demand distribution of each service area within each time slice, the simulation synchronously calculates the resource response, service coverage, and demand fulfillment of each infrastructure node within the corresponding time slice. Finally, it summarizes the operational status data, resource change data, and service response data of each infrastructure node for each resource type within each time slice to obtain the simulation results. Based on the simulation results, the actual operating status of each infrastructure node for each resource type under each time slice is extracted. Combined with the cost parameter function, the operating cost of each infrastructure node under each time slice is calculated. The operating cost of each infrastructure node under each time slice is equal to the sum of the product of the resource configuration quantity of each resource type of the corresponding infrastructure node under the corresponding time slice and the corresponding unit operating cost. The total operating cost of low-altitude infrastructure is obtained by summing the operating costs of each infrastructure node in each time slice. The total operating cost is the sum of the operating costs of each infrastructure node in each time slice. Based on the simulation results, the resource usage of each infrastructure node in each time slice is extracted, and the resource utilization rate of each infrastructure node in each time slice is calculated. The resource utilization rate of each infrastructure node in each time slice is equal to the ratio of the actual amount of resources used by the corresponding infrastructure node in the corresponding time slice to the total amount of resources configured. By summarizing and analyzing the resource utilization rate of each infrastructure node in each time slice, the overall resource utilization rate index of low-altitude infrastructure within the time series set is obtained. Based on the total operating cost and overall resource utilization rate indicators, the cost parameter function and demand function in the quantitative engineering model are updated. The cost parameter function is adjusted according to the difference between the total operating cost and the target cost, and the demand function is adjusted according to the difference between the overall resource utilization rate indicator and the target utilization rate, thus completing the parameter update of the quantitative engineering model.

[0027] In this embodiment, the updated quantitative engineering model is used as the new calculation basis. The resource allocation variables, cost parameter functions, and demand functions in the model are re-extracted. Based on the updated parameters, the resource allocation status and operation scheduling status of the low-altitude infrastructure within the time series set are calculated. According to the configuration of each infrastructure node for each resource type in each time slice, the corresponding resource allocation results are generated. Combining the changes of the resource allocation results in the time series set, the operation scheduling results are generated. The resource allocation results and operation scheduling results are summarized and organized to form a comprehensive result of the resource allocation method and scheduling arrangement of the low-altitude infrastructure in different time slices. The comprehensive result is output as the operation cost optimization result.

[0028] Example 1: In a scenario integrating low-altitude logistics delivery and urban aerial inspection in a coastal city, multiple low-altitude infrastructure nodes have been constructed, including drone take-off and landing points, energy supply stations, communication relay nodes, and operation and maintenance support nodes. The city is divided into several service areas, and the business needs of different areas vary significantly at different times. For example, during the morning rush hour, logistics delivery demand is concentrated in commercial areas, while nighttime inspection demand is concentrated in industrial and port areas. Simultaneously, the city is significantly affected by the marine climate, with environmental factors such as wind speed, rainfall, and visibility having a significant impact on low-altitude operations. Traditional operation methods rely heavily on experience for resource allocation, resulting in resource redundancy in some areas and resource shortages in others, leading to high overall operating costs and low resource utilization efficiency.

[0029] First, operational data of low-altitude infrastructure nodes, historical business demand data, and environmental data are collected. This multi-source data is then cleaned and standardized to obtain a structured dataset. Based on this structured dataset, a set of operational elements for low-altitude infrastructure is constructed, uniformly organizing infrastructure nodes, service areas, resource types, and time slices. On this basis, a quantitative engineering model is established to uniformly model resource allocation relationships, demand relationships, and cost relationships. Combining business demand data and environmental data, the demand distribution of each service area under different time slices is calculated, thus obtaining a more realistic picture of demand changes.

[0030] An operational cost optimization model is constructed based on a quantitative engineering model and demand distribution, and the symplectic geometrically preserved structure optimization algorithm is used to solve the model. During the solution process, the resource allocation variables are updated while maintaining their structure, ensuring good stability in the optimization process. The solution results output resource allocation schemes and operational scheduling strategies for each infrastructure node under different time slices. For example, long-distance delivery tasks are reduced during periods of high wind speed, resource allocation is increased in peak demand areas, and resource input is reduced in low demand areas. Subsequently, the resource allocation results and operational scheduling results are input into a simulation environment for verification. By simulating the actual operation process, operational cost results and resource utilization indicators are obtained, and the model parameters are updated based on the simulation results, thus forming a dynamic optimization closed loop.

[0031] In this embodiment, the method of the present invention is compared with the traditional experience-based scheduling method, and 30 consecutive days of operational data are used for verification. The results show that after adopting the method of the present invention, the demand satisfaction rate of each service area is significantly improved, while the overall operating cost is significantly reduced and resource utilization efficiency is improved.

[0032] Table 1 Comparative Analysis of the Operational Optimization Effects of Low-Altitude Infrastructure

[0033] As shown in Table 1, the method of this invention outperforms traditional methods in several key indicators. Regarding operating costs, the average daily operating cost decreased from RMB 1.285 million to RMB 1.023 million, a reduction of over 20%, indicating that the combination of quantitative engineering models and optimization algorithms can effectively reduce resource waste and lower overall costs. In terms of resource utilization, it increased from 62.7% to 81.5%, indicating more rational resource allocation and a more balanced load on infrastructure nodes across different time slices, avoiding situations where some nodes are overloaded while others are idle.

[0034] Regarding demand fulfillment rate, it improved from 85.2% to 96.8%, indicating that by combining environmental data with business demand data for modeling, demand changes can be predicted more accurately, allowing for proactive resource scheduling and ensuring service quality. Meanwhile, the resource congestion rate during peak hours decreased significantly, demonstrating that the optimized scheduling strategy effectively distributes the load and improves system operating efficiency. The decrease in the proportion of idle resources further indicates that the resource redundancy problem has been effectively alleviated.

[0035] The scheduling response time was reduced from 12.5 minutes to 7.2 minutes, indicating that the method of this invention has higher efficiency in dynamic scheduling and can quickly respond to changes in demand. In summary, this invention, through unified modeling, data-driven analysis, and structure-preserving optimization algorithms, effectively controls the operating costs of low-altitude infrastructure and significantly improves resource utilization efficiency and system stability, verifying its significant technical effects in practical applications.

[0036] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A method for optimizing the operating costs of low-altitude infrastructure based on quantitative engineering models, characterized in that, Includes the following steps: Acquire and preprocess multi-source data related to low-altitude infrastructure operations to obtain a structured dataset; Based on structured datasets, a set of operational elements for low-altitude infrastructure is constructed. A quantitative engineering model is established based on the set of operational elements of low-altitude infrastructure. By using business demand data and environmental data from multiple sources, demand modeling and load analysis are performed to obtain the demand distribution of the service area set on the time series set. Based on the quantitative engineering model and demand distribution, an operating cost optimization model is established; The symplectic geometric structure-preserving optimization algorithm is used to solve the operation cost optimization model, and the resource allocation results and operation scheduling results are obtained. Based on the resource allocation results and operation scheduling results, simulation evaluation is conducted to obtain the operating cost results and resource utilization rate indicators, and the parameters of the quantitative engineering model are updated based on the operating cost results and resource utilization rate indicators. Based on the updated quantitative engineering model, the results of operational cost optimization are output.

2. The method for optimizing the operating costs of low-altitude infrastructure based on a quantitative engineering model according to claim 1, characterized in that, The multi-source data includes infrastructure node data, equipment operation status data, business demand data, environmental data, and historical operating cost data. The preprocessing includes data cleaning, time alignment, and standardization.

3. The method for optimizing the operating costs of low-altitude infrastructure based on a quantitative engineering model according to claim 1, characterized in that, The construction of the set of operational elements for low-altitude infrastructure specifically includes: Based on structured datasets, spatial distribution information, node attribute information, resource attribute information, and timestamp information associated with low-altitude infrastructure operations are extracted. Based on spatial distribution information and node attribute information, nodes of low-altitude infrastructure are identified and classified to construct an infrastructure node set. Based on spatial distribution information and business demand data, the low-altitude service area is divided into regions to construct a service area set; Based on resource attribute information and equipment operation status data, the resources involved in the operation of low-altitude infrastructure are identified and classified, and a set of resource types is constructed. Based on timestamp information, the data records during the operation of low-altitude infrastructure are discretized over time to construct a time series set; By combining the sets of infrastructure nodes, service areas, resource types, and time series, a set of operational elements for low-altitude infrastructure is formed.

4. The method for optimizing the operating costs of low-altitude infrastructure based on a quantitative engineering model according to claim 1, characterized in that, The establishment of the quantitative engineering model specifically includes: Based on the set of infrastructure nodes and the set of service areas in the set of low-altitude infrastructure operation elements, establish the service association relationship between the set of infrastructure nodes and the set of service areas; Resource allocation variables are constructed by using the set of infrastructure nodes, resource types, and time series data from the set of low-altitude infrastructure operation elements. Based on the service area set and time series set in the set of low-altitude infrastructure operation elements, a demand function is constructed. Based on the set of infrastructure nodes and resource allocation variables, construct facility capacity constraints; Based on service relationships, resource configuration variables, and requirement functions, construct requirement satisfaction constraints. A cost parameter function is constructed based on the set of infrastructure nodes, the set of resource types, and the set of time series data. Based on service relationships, resource allocation variables, demand functions, facility capacity constraints, demand satisfaction constraints, and cost parameter functions, a unified model is used to model the operation process of low-altitude infrastructure, resulting in a quantitative engineering model.

5. The method for optimizing the operating costs of low-altitude infrastructure based on a quantitative engineering model according to claim 1, characterized in that, The determination of the demand distribution specifically includes: Obtain business demand data and environmental data from multi-source data, and match the business demand data and environmental data according to the service area set and time series set to obtain the original demand data and environmental impact data of each service area under each time slice; Based on the original demand data of each service area under each time slice, the basic demand of each service area under each time slice is calculated. Based on the environmental impact data of each service area under each time slice, the environmental impact coefficient of each service area under each time slice is quantified. Based on the basic demand and environmental impact coefficient of each service area under each time slice, determine the adjusted demand of each service area under each time slice; Based on the correction demand of each service area under each time slice, they are arranged in chronological order to obtain the demand distribution of the service area set on the time series set.

6. The method for optimizing the operating cost of low-altitude infrastructure based on a quantitative engineering model according to claim 1, characterized in that, The establishment of the operating cost optimization model specifically includes: Based on the resource allocation variables, demand function, and cost parameter function in the quantitative engineering model, an operating cost objective function is constructed. Based on the facility capacity constraints in the quantitative engineering model, resource allocation constraints are constructed. Based on the requirement satisfaction constraints in the quantitative engineering model, construct the requirement satisfaction constraints. Based on the demand distribution of the service area set on the time series set, the operating cost objective function is weighted and modified to construct a demand-weighted objective function. An operational cost optimization model is constructed based on the operational cost objective function, resource allocation constraints, demand satisfaction constraints, and demand weighted objective function.

7. The method for optimizing the operating cost of low-altitude infrastructure based on a quantitative engineering model according to claim 1, characterized in that, The acquisition of the resource allocation results and operation scheduling results specifically includes: The resource allocation variables in the operating cost optimization model are used as the solution objects of the symplectic geometrical structure-preserving optimization algorithm, and the operating cost objective function, resource allocation constraints, and demand satisfaction constraints are used as the inputs of the symplectic geometrical structure-preserving optimization algorithm. Based on resource configuration variables, construct state variables and covariates that correspond one-to-one with the resource configuration variables; A Hamiltonian function is constructed based on state variables, covariates, operating cost objective function, resource allocation constraints, and demand satisfaction constraints. Based on the Hamiltonian function, a symplectic geometric evolution relationship between state variables and covariates is constructed, and the symplectic geometric evolution relationship is expanded step by step according to the structure-preserving discretization method. The symplectic geometric structure-preserving numerical integration method is adopted to discretize the symplectic geometric evolution relationship after step-by-step expansion, so as to obtain the discrete iterative update relationship of state variables and covariates, and to iteratively update the state variables and covariates according to the discrete iterative update relationship. After each iteration update, calculate the resource configuration constraint residual and the demand satisfaction constraint residual corresponding to the updated state variable, and perform constraint correction on the updated state variable based on the resource configuration constraint residual and the demand satisfaction constraint residual to obtain the corrected state variable. Convergence is determined based on the change in the corrected state variables between two adjacent iterations. When the change is less than the preset convergence threshold, and the residuals of the resource allocation constraint and the requirement satisfaction constraint are both less than the preset constraint threshold, the iteration stops, and the resource allocation result is determined based on the converged corrected state variables. Based on the temporal changes of resource allocation results in the time series set, the operation scheduling results are generated.

8. The method for optimizing the operating cost of low-altitude infrastructure based on a quantitative engineering model according to claim 1, characterized in that, The parameter updates of the quantitative engineering model specifically include: Based on the resource allocation results and operation scheduling results, a simulation evaluation is conducted to build a simulation operation environment. The operation status of each infrastructure node in the simulation operation environment is simulated and calculated to obtain the simulation calculation results. Based on the simulation results, the actual operating status of each infrastructure node for each resource type under each time slice is extracted, and the operating cost of each infrastructure node under each time slice is calculated by combining the cost parameter function. The total operating cost of low-altitude infrastructure is obtained by summing up the operating costs of each infrastructure node in each time slice and within the time series set. Based on the simulation results, the resource usage of each infrastructure node under each time slice is extracted, and the resource utilization rate of each infrastructure node under each time slice is calculated. By summarizing and analyzing the resource utilization rate of each infrastructure node in each time slice, the overall resource utilization rate index of low-altitude infrastructure within the time series set is obtained. Based on total operating cost and overall resource utilization indicators, the cost parameter function and demand function in the quantitative engineering model are updated.

9. The method for optimizing the operating cost of low-altitude infrastructure based on a quantitative engineering model according to claim 1, characterized in that, Using the updated quantitative engineering model as the new computational basis, the resource allocation variables, cost parameter functions, and demand functions in the model are re-extracted. Based on the updated parameters, the resource allocation status and operation scheduling status of low-altitude infrastructure within the time series set are calculated. According to the configuration of each infrastructure node for each resource type in each time slice, the corresponding resource allocation results are generated. Combining the changes of resource allocation results in the time series set, operation scheduling results are generated. The resource allocation results and operation scheduling results are summarized and organized to form a comprehensive result of the resource allocation method and scheduling arrangement of low-altitude infrastructure in different time slices. The comprehensive result is output as the operation cost optimization result.

Images