High-altitude highway emergency resource allocation method, device, medium and program product

Abstract

The present application relates to the technical field of traffic emergency management, and in particular to a high-altitude highway emergency resource configuration method, device, medium and program product. The high-altitude highway emergency resource configuration method comprises: S1, obtaining basic data such as original emergency resource configuration scheme, traffic flow data, traffic blockage event data, road environment data; S2, constructing an emergency resource configuration optimization model, comprising: constructing a reliability evaluation index system; determining the weight of each evaluation index; constructing a reliability evaluation model; establishing a target function; establishing a constraint condition function; S3, inputting the original emergency resource configuration scheme into the emergency resource configuration optimization model, and using a genetic algorithm and a particle swarm algorithm to solve and obtain an optimal configuration scheme of emergency resources. The present application can timely grasp the reliability of different highway sections and provide a decision basis for highway traffic emergency resource configuration, ensure the scientific and reasonable configuration of highway traffic emergency resources, and improve the regional emergency rescue capability.

Description

Technical Field

[0001] This invention relates to the field of traffic emergency management technology, and in particular to a method, equipment, medium and program product for allocating emergency resources on high-altitude highways. Background Technology

[0002] In recent years, extreme weather events such as torrential rains, blizzards, and strong winds, as well as geological disasters such as mudslides, landslides, and earthquakes, have occurred frequently, especially in high-altitude areas (above 3,000 meters). Due to harsh climate conditions, complex geological environments, and the susceptibility of drivers to altitude sickness, emergency rescue operations on highways face even greater challenges in the event of sudden incidents. Related surveys indicate that approximately two-thirds of seriously injured individuals lose their lives due to delayed rescue efforts. Rescue work is even more difficult in high-altitude areas, not only because of the complex terrain and thin air, but also because of the frequent occurrence of extreme weather events, which easily damages infrastructure such as roads and communications, hindering the rapid arrival of rescue forces and supplies.

[0003] Currently, most methods for allocating highway emergency resources are based on simple or fixed factors such as the frequency of accidents, the severity of their consequences, or the time it takes for rescue teams to arrive. These methods do not fully consider the fluctuations and uncertainties in highway traffic conditions during actual operation, especially in high-altitude areas where traffic conditions frequently change due to low temperatures, snow, and geological disasters, resulting in low reliability. Existing resource allocation methods lack the capacity to cope with such dynamic changes. Furthermore, due to management mechanisms and cost control reasons, the types and quantities of emergency supplies are often arranged irrationally. Coupled with the sparse distribution of emergency stations and poor transportation conditions in high-altitude areas, resources are unevenly distributed, and some areas suffer from insufficient emergency supplies.

[0004] In the actual operation of high-altitude highways, the occurrence of emergencies often leads to more severe consequences due to the unique geographical environment and weak disaster resistance of road facilities. Severe incidents may damage roads, bridges, and other infrastructure, while even minor incidents can cause traffic congestion, reduced traffic efficiency, and a significant impact on the stability of the entire transportation system. Existing resource allocation methods for addressing such problems typically focus only on rescue speed or cost, neglecting the ability to restore transportation and maintain service levels after a disaster. They also fail to fully consider the actual conditions at high altitudes, such as thin air, low equipment operating efficiency, and difficulties for personnel operations, resulting in unscientific resource allocation and unsatisfactory emergency response.

[0005] Therefore, existing highway emergency resource allocation methods are significantly inadequate when applied in high-altitude areas, failing to adapt to complex and variable environments and traffic conditions, and thus unable to effectively guarantee rescue efficiency and system recovery capabilities. To improve the timeliness and effectiveness of emergency response and reduce casualties and property damage, it is necessary to propose a new resource allocation method that can combine the actual operational conditions in high-altitude areas with consideration of traffic fluctuations, rationally allocate the types and quantities of emergency resources, and enable resources to be deployed more effectively to the most needed road sections, thereby enhancing overall emergency rescue capabilities. Summary of the Invention

[0006] The purpose of this invention is to overcome the shortcomings of existing highway emergency resource allocation methods when applied in high-altitude areas, such as difficulty in adapting to complex and changing environments and traffic conditions, and inability to effectively guarantee rescue efficiency and system recovery capabilities. This invention provides a method, equipment, medium, and program product for high-altitude highway emergency resource allocation.

[0007] First, this invention provides a method for allocating emergency resources on high-altitude highways, comprising the following steps:

[0008] S1. Obtain basic data; wherein, the basic data includes at least: original emergency resource allocation plan, traffic flow data, traffic disruption event data, and road environment data;

[0009] S2. Construct an emergency resource allocation optimization model, which should include at least:

[0010] S21. Construct a reliability assessment index system;

[0011] S22. Determine the weight of each evaluation indicator;

[0012] S23. Construct a reliability assessment model;

[0013] S24. Establish the objective function;

[0014] S25. Establish constraint function;

[0015] S3. Input the original emergency resource allocation scheme into the emergency resource allocation optimization model, and use the genetic algorithm and particle swarm algorithm to solve for the optimal emergency resource allocation scheme.

[0016] According to a preferred embodiment, the traffic flow data includes flow rate, speed, inbound / outbound traffic volume at nodes, and highway capacity. The disruption event data includes passage time, number of disruptions, and disruption distance. The road environment data includes altitude, road segment length, number of historical disasters, and severity of historical disasters.

[0017] According to a preferred embodiment, the reliability assessment index system includes four dimensions: time, space, traffic, and environment and disaster. Preferably, the time dimension includes: travel time, blockage frequency, and blockage probability. The space dimension includes: road segment length, linear continuity, and percentage of blocked mileage. The traffic dimension includes: node flow, road segment saturation, and vehicle ratio. The environment and disaster dimension includes: altitude, number of historical disasters, and severity of historical disasters.

[0018] According to a preferred embodiment, S22 includes: standardizing and quantifying different evaluation indicators; constructing a covariance matrix based on standardized data, performing eigenvalue decomposition using principal component analysis, extracting principal components, obtaining eigenvalues ​​and corresponding eigenvectors, and sorting them according to the size of the eigenvalues; and combining the contribution ratio of each principal component with the coefficient of its corresponding factor to calculate the comprehensive weight of each evaluation indicator.

[0019] According to a preferred embodiment, S23 includes: mapping each evaluation index value to the [0,1] interval through a normalization method; and constructing a comprehensive evaluation model integrating four dimensions: time, space, transportation, environment, and disaster based on the normalized index values.

[0020] According to a preferred embodiment, the objective function established in S24 includes: constructing a cost minimization objective based on standardized equipment cost coefficients and personnel cost coefficients; aiming to maximize traffic operation reliability based on a reliability assessment model; and constructing a comprehensive objective function after normalizing cost and reliability indicators.

[0021] According to a preferred embodiment, the constraint function established in S25 includes: resource input restrictions, including the maximum amount of equipment and personnel input for each road segment; reliability restrictions, the reliability of each road segment in the optimal configuration scheme of emergency resources is not lower than its reliability in the original emergency resource configuration scheme; total resource restrictions, including the total amount of available equipment and personnel; emergency rescue resources are indivisible, and the quantity of each type of resource is an integer.

[0022] The present invention also provides an electronic device. The electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to execute the high-altitude highway emergency resource allocation method provided by the invention.

[0023] The present invention also provides a computer-readable storage medium. The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the high-altitude highway emergency resource allocation method provided by the invention.

[0024] The present invention also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the high-altitude highway emergency resource allocation method provided by the present invention.

[0025] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0026] This invention provides a method, equipment, medium, and program product for allocating emergency resources for high-altitude highways. It establishes an evaluation model for traffic operation reliability, using the minimization of emergency costs and the maximization of traffic operation reliability as objective functions for resource allocation. An emergency resource optimization model is constructed with constraints on resource allocation costs, reliability, and total resource volume. By combining genetic algorithms and particle swarm optimization, the optimal allocation scheme for emergency resources on high-altitude highways is solved, achieving a scientific and rational allocation of highway emergency resources. This invention can promptly grasp the reliability of different highway sections and provide a decision-making basis for highway traffic emergency resource allocation, ensuring the scientific and rational allocation of highway traffic emergency resources and improving regional emergency rescue capabilities. Attached Figure Description

[0027] Figure 1 This is a schematic diagram of a preferred embodiment of the high-altitude highway emergency resource allocation method of the present invention.

[0028] Figure 2 This is a detailed flowchart illustrating the high-altitude highway emergency resource allocation method of the present invention.

[0029] Figure 3 This is a schematic diagram illustrating the specific solution process of the hybrid intelligent heuristic algorithm of the present invention.

[0030] Figure 4 This is a schematic diagram illustrating the convergence analysis of a hybrid intelligent heuristic algorithm. Detailed Implementation

[0031] The present invention will now be described in further detail with reference to specific embodiments. However, this should not be construed as limiting the scope of the present invention to the following embodiments; all technologies implemented based on the content of the present invention fall within the scope of the present invention.

[0032] Unless otherwise specified, the use of terms such as "upper," "lower," "left," "right," "center," "inner," and "outer" to indicate orientation or positional relationships in the description of specific embodiments of the present invention is based on the orientation or positional relationships shown in the accompanying drawings, or the orientation or positional relationship in which the product / equipment / device is typically placed during use. These terms are merely for the purpose of facilitating the description of the present invention or simplifying the description in specific embodiments, enabling those skilled in the art to quickly understand the solution, and do not indicate or imply that a particular device / component / element must have a specific orientation, or be constructed and operated in a specific positional relationship. Therefore, they should not be construed as limitations on the present invention.

[0033] Furthermore, the use of terms such as "horizontal," "vertical," "suspended," and "parallel" does not imply that the corresponding device / component / element must be absolutely horizontal, vertical, suspended, or parallel, but rather that it can be slightly tilted or have a deviation. For example, "horizontal" merely means that its direction is more horizontal relative to "vertical," not that the structure must be completely horizontal, but that it can be slightly tilted. Alternatively, it can be simplified to mean that the corresponding device / component / element, when set in a "horizontal," "vertical," "suspended," or "parallel" direction, can have an error / deviation of ±10% relative to the corresponding direction, more preferably within ±8%, more preferably within ±6%, more preferably within ±5%, and more preferably within ±4%. As long as the corresponding device / component / element is within the error / deviation range, it can still achieve its function in the present invention.

[0034] Furthermore, the use of terms such as "first," "second," and "third" in terminology is merely for distinguishing descriptions of identical or similar components and should not be interpreted as emphasizing or implying the relative importance of a particular component.

[0035] Furthermore, in the description of the embodiments of the present invention, "several", "more than", and "a number of" represent at least two. The number can be any number, such as 2, 3, 4, 5, 6, 7, 8, or 9, and can even exceed nine.

[0036] Furthermore, in the description of the technical solution of this invention, unless otherwise explicitly specified / limited / restricted, the terms "set up," "install," "connect," "link," "provided with," "laid out," and "arranged" should be interpreted broadly. For example, they can refer to fixed connections, detachable connections, or integral connections; they can refer to common connection methods in the art, such as welding, riveting, bolting, and threaded connections. Such connections can be mechanical, electrical, or communication connections; they can be direct connections or indirect connections through an intermediate medium; and they can refer to the internal communication between two components.

[0037] Example 1

[0038] This embodiment provides a method for emergency resource allocation on high-altitude highways. (See also...) Figure 1 The emergency resource allocation method for high-altitude highways includes the following steps:

[0039] S1. Obtain basic data;

[0040] S2. Construct an emergency resource allocation optimization model;

[0041] S3. Input the original emergency resource allocation scheme into the emergency resource allocation optimization model, and use the genetic algorithm and particle swarm algorithm to solve for the optimal emergency resource allocation scheme.

[0042] Preferably, the basic data includes at least: the original emergency resource allocation plan, traffic flow data, traffic disruption event data, and road environment data.

[0043] Preferably, the construction of an emergency resource allocation optimization model includes at least the following: S21, constructing a reliability assessment index system; S22, determining the weight of each assessment index; S23, constructing a reliability assessment model; S24, establishing an objective function; and S25, establishing constraint function.

[0044] The high-altitude highway emergency resource allocation method provided in this embodiment establishes a traffic operation reliability assessment model. It uses minimizing emergency costs and maximizing traffic operation reliability as the objective functions for resource allocation. An emergency resource optimization model is constructed with constraints on resource allocation cost, reliability, and total resource volume. By combining genetic algorithms and particle swarm optimization algorithms, the optimal allocation scheme for high-altitude highway emergency resources is solved, achieving a scientific and rational allocation of highway emergency resources. This invention can promptly grasp the reliability of different highway sections and provide a decision-making basis for highway traffic emergency resource allocation, ensuring the scientific and rational allocation of highway traffic emergency resources and improving regional emergency rescue capabilities.

[0045] Example 2

[0046] This embodiment is a further improvement on embodiment 1, and the repeated content will not be described again.

[0047] Preferably, traffic flow data includes volume, speed, inbound / outbound traffic volume at nodes, and highway capacity. Disruption event data includes passage time, number of disruptions, and disruption distance. Road environment data includes altitude, road segment length, number of historical disasters, and severity of historical disasters.

[0048] See Figure 2Preferably, after acquiring basic data, a reliability assessment index system is constructed based on data such as traffic flow data, disruption event data, and road environment data. Preferably, the reliability assessment index system includes four dimensions: time, space, traffic, and environment and disaster. The constructed reliability assessment index system can analyze the reliability of traffic operations from these four dimensions.

[0049] Preferably, the time dimension includes: passage time, blocking frequency, and blocking probability. Preferably, the time dimension selects passage time, blocking frequency, and blocking probability as core indicators, where the blocking probability is:

[0050]

[0051] In the formula: Historical data statistics period, unit: hours; For the first i Traffic disruption duration, in hours; n This represents the number of traffic disruptions that occurred within the historical data period, expressed in times.

[0052] The spatial dimensions include: road segment length, alignment continuity, and the percentage of road obstruction mileage. Preferably, the spatial dimension uses the rate of change of curvature of horizontal curves between adjacent road segments as an indicator to assess road alignment continuity.

[0053] Percentage of blocking mileage:

[0054]

[0055] In the formula: For the first i The distance of each traffic disruption, in km; The length of the road segment is expressed in km.

[0056] Rate of change of curvature of horizontal curves of adjacent road segments:

[0057] ,

[0058] In the formula: The radius of the horizontal curve; This refers to the length of the road segment.

[0059] The traffic dimension includes: node flow, road segment saturation, and vehicle ratio. Preferably, the traffic dimension uses macro-level traffic volume indicators as influencing factors, and node flow, road segment saturation, and the proportion of large vehicles as core indicators. Preferably, large vehicles may include: passenger vehicles with more than 19 seats, freight vehicles with a load capacity of more than 7 tons, etc.

[0060] The environment and disaster dimension includes: altitude, number of historical disasters, and severity of historical disasters. Preferably, altitude, number of historical disasters, and severity of historical disasters are selected as the core indicators of the environment and disaster dimension.

[0061] Severity of historical disasters:

[0062]

[0063] In the formula, For the first i The severity of a disaster is quantified based on the duration of disruption, the affected area, economic losses, or other relevant indicators.

[0064] Preferably, S22 includes: standardizing and quantifying different evaluation indicators; constructing a covariance matrix based on standardized data, performing eigenvalue decomposition using principal component analysis, extracting principal components, obtaining eigenvalues ​​and corresponding eigenvectors, and sorting them according to the size of the eigenvalues; and combining the contribution ratio of each principal component with the coefficient of its corresponding factor to calculate the comprehensive weight of each evaluation indicator.

[0065] See Figure 2 Preferably, after obtaining each evaluation index in the reliability evaluation index system, the index is standardized.

[0066] Preferably, the Z-score standardization method is used to preprocess each evaluation index, so that the evaluation indexes of different scales have a unified quantitative standard, corresponding to 12 influencing factors in four dimensions, and constructing the original data matrix of multi-dimensional influencing factors. X The standardized matrix Z for:

[0067]

[0068] In the formula, For the first i The first section of the road j The value of each factor, For the first j The mean of the column, For the first j Standard deviation of the column.

[0069] A covariance matrix was constructed based on standardized data. Principal component analysis (PCA) was used to decompose eigenvalues, extract principal components, obtain eigenvalues ​​and corresponding eigenvectors, and sort them according to the magnitude of the eigenvalues. A cumulative contribution rate of 80% was used as the critical value for selecting principal components.

[0070]

[0071] In the formula: For cumulative contribution rate, Let be the eigenvalue of the i-th principal component, representing the variance of the original data explained by that principal component; The number of principal components selected; The total number of all principal components.

[0072] By combining the contribution ratio of each principal component with the coefficient of its corresponding factor, the comprehensive weight of each influencing factor (each evaluation indicator) is calculated:

[0073]

[0074] In the formula, For the first j The combined weight of each influencing factor For the first k Each principal component eigenvalue, For the first k The th principal component corresponds to the eigenvector of the th eigenvector. j Each component.

[0075] Preferably, S23 includes: mapping each evaluation index value to the [0,1] interval through a normalization method; and constructing a comprehensive evaluation model integrating four dimensions: time, space, transportation, environment, and disaster based on the normalized index values.

[0076] See Figure 2 After obtaining the comprehensive weights of each influencing factor, a reliability assessment model is constructed.

[0077] Preferably, the index values ​​are mapped to the [0,1] interval using the min-max normalization method. Based on the normalized index values, a comprehensive assessment model integrating four dimensions—time, space, transportation, environment, and disaster—is constructed.

[0078]

[0079] In the formula, For road section i Overall reliability; , , , The weights are assigned to the time dimension, spatial dimension, transportation dimension, and environmental and disaster dimension, respectively.

[0080] The time dimension influence function is:

[0081]

[0082] The spatial dimension influence function is:

[0083]

[0084] The influence function for the traffic dimension is:

[0085]

[0086] The influence function for the environmental and disaster dimensions is:

[0087]

[0088] In the formula, , , , These represent the weights of each factor in the time, space, transportation, environment, and disaster dimensions, respectively. N Indicates the blocking frequency, in seconds; T Indicates travel time, in hours; Indicates the probability of blocking;

[0089] L Indicates the length of the road segment, in km; Indicates linear continuity; Indicates the percentage of blocked mileage, %

[0090] The number of traffic entering and leaving a node is represented by pcu. Indicates the saturation level of the road section; This indicates the percentage of large vehicles, %

[0091] H Altitude, expressed in meters (m); Indicates the number of disasters, in times; Indicates the severity of the disaster.

[0092] Preferably, the objective function established in S24 includes: constructing a cost minimization objective based on standardized equipment cost coefficients and personnel cost coefficients; aiming to maximize traffic operation reliability based on a reliability assessment model; and constructing a comprehensive objective function after normalizing cost and reliability indicators.

[0093] See Figure 2 A multi-objective function is established, which comprehensively considers both resource input costs and system reliability improvement. Based on standardized equipment cost coefficients and personnel cost coefficients, a cost minimization objective is constructed:

[0094]

[0095] In the formula, , These represent the costs of a single piece of mechanical equipment and a single person during the interruption period, respectively. , The first iThe number of equipment and personnel deployed on this road section; n This refers to the number of road segments.

[0096] Regarding system reliability, after determining the reliability level through a reliability assessment model, the goal is to maximize traffic operation reliability, ensuring that the investment of emergency resources can effectively improve the traffic operation reliability of each road segment.

[0097]

[0098] Considering the differences in dimensions and orders of magnitude between cost and reliability indicators, a comprehensive objective function is constructed after normalization to ensure that the optimization model can balance resource costs and traffic operation reliability:

[0099]

[0100] In the formula, This represents the upper limit of the cost of the allocated resources. This represents the maximum reliability for each road segment. , As the weights for resource allocation and traffic operation reliability, under the overall optimization objective, the importance of equipment and personnel allocation is equivalent to the importance of ensuring road traffic operation reliability, and their values ​​are both 1.

[0101] Preferably, the constraint function established in S25 includes: resource input restrictions, including the maximum amount of equipment and personnel input for each road segment; reliability restrictions, the reliability of each road segment in the optimal configuration scheme of emergency resources is not lower than its reliability in the original emergency resource configuration scheme; total resource restrictions, including the total amount of available equipment and personnel; emergency rescue resources are indivisible, and the quantity of each type of resource is an integer.

[0102] Preferably, after establishing the multi-objective function, it is also necessary to establish the constraint function.

[0103] See Figure 2 Preferably, four constraints are proposed from the aspects of resource input, total resource limit, reliability requirements, and integer limit.

[0104] Constraint 1: Resource Input Limitation. Considering the limited space available for highway operations, there is an upper limit to the amount of resources that can be invested.

[0105]

[0106]

[0107] In the formula, , These represent the maximum equipment and personnel input for the i-th road segment, respectively.

[0108] Constraint 2: Reliability Limitation. After optimizing resource allocation, the reliability of each road segment is improved to a certain extent compared to the original reliability, namely:

[0109]

[0110] In the formula, To ensure the reliability of the current road section, , This represents the reliability enhancement factor of equipment and personnel. After emergency resource allocation, the reliability of each road section will not be lower than the minimum reliability requirement, i.e.:

[0111]

[0112] In the formula, For the first i The minimum reliability requirement for this road segment is set after consulting with several experts engaged in road risk research and operation management. The value in this model is 0.35.

[0113] Constraint 3: Total Resource Limitation. Under total cost control, the total amount of resources at the system level also faces strict constraints:

[0114]

[0115]

[0116] In the formula, , These represent the total amount of available equipment and personnel resources, respectively.

[0117] Constraint 4: Emergency rescue resources are indivisible, and the quantities of all types of resources invested must be integers, i.e.:

[0118]

[0119] In the formula, It represents the set of positive integers.

[0120] Preferably, after establishing the multi-objective function and constraint function, the optimal resource allocation scheme is obtained by using the genetic algorithm and particle swarm algorithm.

[0121] See Figure 2 Preferably, the genetic algorithm (GA) and the particle swarm optimization (PSO) algorithm are combined to obtain the hybrid intelligent heuristic algorithm (Hybrid GA-PSO). The Hybrid GA-PSO algorithm is used to solve the problem, fully leveraging the global search capability of the genetic algorithm (GA) and the local fine-grained search capability of the particle swarm optimization algorithm (PSO). By combining the two, the optimal allocation of emergency resources for high-altitude highways under complex and multi-constraint conditions can be solved.

[0122] 1) Quantitative coding of influencing factors and constraints

[0123] Through the aforementioned multi-dimensional reliability assessment model, various influencing factors related to traffic operation reliability (such as travel time, blockage frequency, road segment length, node flow, altitude, number of disasters, etc.) have been standardized and subjected to principal component analysis to obtain their respective weights, ultimately forming a quantitative value for the traffic operation reliability of each road segment.

[0124] In the hybrid algorithm, chromosome or particle positions are encoded using integers, with each individual represented as a string of length 1. n The vector, n This represents the number of road segments, with each component representing the equipment and personnel input for the corresponding road segment:

[0125]

[0126] in, The first i The number of equipment and personnel in the road section, all variables are positive integers.

[0127] Various constraints (such as resource input limits, total resource constraints, reliability limits, and integer constraints) are incorporated into the fitness function through a penalty function method. The corresponding fitness function is:

[0128]

[0129] In the formula, Z The objective function value, M The penalty coefficient is... P To constrain the degree of violation.

[0130] 2) Iterative solution

[0131] In the design of genetic operators (GAs), a sorting-based roulette wheel selection method is adopted, and an elite retention strategy is introduced. To address the diverse needs of resource allocation schemes, adaptive crossover and mutation operators are designed. Crossover probability... and mutation probability All adopt an adaptive approach:

[0132]

[0133]

[0134] In the formula, Average fitness of the population For maximum fitness, , These are the upper and lower bounds of the crossover probability. , These are the upper and lower limits of the mutation probability.

[0135] As the number of iterations increases, a particle swarm optimization (PSO) algorithm is introduced for local fine-grained search, using the optimal individual obtained in the genetic algorithm stage as the initial particle swarm for the PSO algorithm. The particle velocity and position update formulas are as follows:

[0136]

[0137]

[0138] In the formula, For the position of the i-th particle in the k-th iteration, For the corresponding speed, For inertial weights, , Individual learning factors and group learning factors, , A uniformly random number within the interval [0,1]. For the individual's historical best position, This is the best position in the history of the population.

[0139] To further improve algorithm performance, inertia weights A linear decreasing strategy is adopted, that is:

[0140]

[0141] In the formula, , These are the initial and final values ​​of the inertia weight, respectively. This represents the current iteration number. This represents the maximum number of iterations for the algorithm. By dynamically adjusting the inertia weights, a smooth transition from global exploration to refined local search is achieved.

[0142] The hybrid intelligent heuristic algorithm employs a strategy of alternating between Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) during the iterative process. In the initial stage (the first 50% of iterations), GA is dominant, with PSO introduced for short-term iterations (3-5 generations) after a certain number of generations (10 generations) to quickly and accurately locate potential optimal solution regions. In the later stage (the last 50% of iterations), the proportion of PSO gradually increases (GA and PSO alternate for 5 generations each) to rapidly converge to the vicinity of the global optimum. Throughout the entire iteration process, the global optimum is continuously updated and preserved to ensure the algorithm's robustness and efficient convergence performance.

[0143] Preferably, considering the characteristics of decision variables being integers and having numerous constraints in the optimal allocation of emergency resources in high-altitude areas, the hybrid optimization algorithm requires verification and repair of constraints after each individual (chromosome or particle) update to ensure that the solution generated by the algorithm always meets the constraints: for resource input upper limit constraints, truncation is used to ensure that the resource carrying capacity of each road segment is not exceeded; for reliability constraints, a repair method that prioritizes meeting the reliability requirements of key road segments is adopted; for total resource constraints, a dynamic adjustment mechanism based on resource importance is used; and for integer constraints, rounding is performed. Therefore, the specific solution process of the hybrid intelligent heuristic algorithm is as follows: Figure 3 As shown.

[0144] See Figure 3 Preferably, the solution process includes:

[0145] First, initialize the population, randomly generate an initial solution set, and calculate the fitness function;

[0146] Entering the genetic algorithm stage, selection, crossover, and mutation operators are used to calculate and update the population;

[0147] Determine whether the particle swarm algorithm triggering condition has been met. If yes, proceed to the particle swarm algorithm stage; otherwise, continue to the genetic algorithm stage.

[0148] Entering the particle swarm optimization stage, the particle velocity and position are updated using the current optimal solution as the initial particles.

[0149] Check and fix the constraints;

[0150] Update and save the current global optimal solution;

[0151] Determine if the termination condition has been triggered. If yes, end the process; otherwise, continue into the genetic algorithm phase for looping.

[0152] Preferably, the emergency resource allocation method for high-altitude highways provided in this embodiment is verified and analyzed using a highway in a high-altitude area, including the following steps:

[0153] 1. Basic Data Acquisition. Through on-site surveys and historical data collection, basic data for 11 road sections over the past two years were obtained, including the number of times traffic was blocked, the duration of the blockage, the passage time, and the traffic volume entering / exiting the road sections and key nodes.

[0154] 2. Combining basic information such as altitude and road length, an evaluation system containing 12 influencing factors was constructed from four dimensions: time, space, transportation, environment, and disaster.

[0155] 3. Determination of Influencing Factor Weights. Based on the constructed reliability assessment model, principal component analysis was used to determine the weights of each influencing factor. The calculation results of the weights of each factor are shown in Table 1.

[0156] Table 1. Weight Calculation Results for a Certain Road Section

[0157]

[0158] 4. Reliability Calculation Results for Each Road Segment. Based on the weights of influencing factors and the reliability assessment model, the traffic operation reliability of 11 road segments was calculated, and the results are shown in Table 2.

[0159] Table 2 Reliability calculation results for each road section

[0160]

[0161] 5. Establish resource allocation constraints. Based on actual operating conditions and budget constraints, the total number of devices in the system is 30, and the total number of personnel is 50. The minimum reliability requirement for each road section is set at 0.80. Based on historical data fitting analysis, the reliability improvement coefficients for equipment and personnel are set at 0.02 and 0.03, respectively. In addition, the upper limit of resource input for each road section is determined by considering the road section length, operating space, and environmental carrying capacity, as shown in Table 3.

[0162] Table 3 Summary of the Maximum Resource Input for Each Sub-section

[0163]

[0164] 6. Model Solving. The proposed Hybrid GA-PSO algorithm is used to solve the model. The key parameters of the algorithm are set as follows: population size is 100, maximum number of iterations is 500, the adaptive range of crossover probability in the GA stage is [0.6, 0.9], the adaptive range of mutation probability is [0.01, 0.1], the inertia weight in the PSO stage decreases linearly, with an initial value of 0.9 and a termination value of 0.4, and the learning factor C1=C2=2.0. The convergence analysis of the Hybrid GA-PSO algorithm is as follows. Figure 4 As shown, convergence is achieved in approximately 320 generations, demonstrating good overall convergence performance.

[0165] 7. Optimal Resource Allocation Scheme. Based on the model solution results, the final resource allocation schemes for each road segment are shown in Table 4.

[0166] Table 4 Optimized Resource Allocation Scheme

[0167]

[0168] To address the problems of unscientific allocation of types and quantities of existing emergency critical resources and insufficient consideration of factors in resource allocation models, this embodiment provides a high-altitude highway emergency resource allocation method. First, it proposes a traffic operation reliability assessment index system and reliability assessment model to evaluate the current reliability of road sections. Then, it uses minimum cost and maximum traffic operation reliability as the objective function of resource allocation, constructs an emergency resource optimization model with highway traffic operation reliability as the core constraint, and combines genetic algorithm and particle swarm optimization algorithm to form a hybrid intelligent heuristic algorithm (Hybrid GA-PSO) for solving the problem, finally obtaining the optimal resource allocation scheme.

[0169] This embodiment constructs a traffic operation reliability assessment model, which can promptly and accurately grasp the highway traffic operation status. The emergency resource optimization allocation model proposed in this embodiment can efficiently allocate resources to various emergency points, improve the efficiency of rescue work, reduce losses, and has important practical significance for highway emergency decision-making and management.

[0170] Example 3

[0171] This embodiment provides an electronic device. The electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor. Preferably, the memory stores a computer program executable by the at least one processor, which is executed by the at least one processor to enable the at least one processor to perform the high-altitude highway emergency resource allocation method involved in Embodiments 1 and 2.

[0172] Example 4

[0173] This embodiment provides a computer-readable storage medium. The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the high-altitude highway emergency resource allocation method described in Embodiments 1 and 2.

[0174] Example 5

[0175] This embodiment provides a computer program product, characterized in that the computer program product includes a computer program, which, when executed by a processor, implements the high-altitude highway emergency resource allocation method involved in Embodiments 1 and 2.

[0176] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A high-altitude highway emergency resource allocation method, characterized in that, Includes the following steps: S1. Obtain basic data; wherein, the basic data includes at least: original emergency resource allocation plan, traffic flow data, traffic disruption event data, and road environment data; The traffic flow data includes flow rate, speed, inbound / outbound traffic volume at nodes, and highway capacity; The blocking event data includes passage time, number of blocking events, and blocking distance; The road environment data includes altitude, road length, number of historical disasters, and severity of historical disasters; S2. Construct an emergency resource allocation optimization model, which should include at least: S21. Construct a reliability assessment index system; the reliability assessment index system includes four dimensions: time, space, transportation, environment, and disaster; among which, The time dimension includes: passage time, blocking frequency, and blocking probability; Spatial dimensions include: road segment length, linear continuity, and percentage of road blockages; Traffic dimensions include: node traffic flow, road segment saturation, and vehicle ratio; The environmental and disaster dimensions include: altitude, number of historical disasters, and severity of historical disasters; S22. Determine the weight of each evaluation indicator; S23. Construct a reliability assessment model; S24. Establish the objective function, including: Based on standardized equipment cost coefficients and personnel cost coefficients, a cost minimization objective is constructed; Based on the reliability assessment model, the goal is to maximize the reliability of traffic operations; A comprehensive objective function is constructed after normalizing the cost and reliability indicators. S25. Establish constraint function; among which, the upper limit of resource input for each road segment is determined by considering the road segment length, working space and environmental carrying capacity. S3. Input the original emergency resource allocation scheme into the emergency resource allocation optimization model, and use the genetic algorithm and particle swarm algorithm to solve for the optimal emergency resource allocation scheme, and determine the final emergency resource allocation type and quantity for each road segment.

2. The method of claim 1, wherein, S22 includes: Standardize and quantify different evaluation indicators; A covariance matrix is ​​constructed based on standardized data. Principal component analysis is used to decompose eigenvalues, extract principal components, obtain eigenvalues ​​and corresponding eigenvectors, and sort them according to the size of the eigenvalues. The comprehensive weight of each evaluation index is calculated by combining the contribution ratio of each principal component with the coefficient of its corresponding factor.

3. The method for allocating emergency resources on high-altitude highways according to claim 2, characterized in that, S23 includes: The values ​​of each evaluation index are mapped to the [0,1] interval using a normalization method; Based on the normalized index values, a comprehensive assessment model integrating four dimensions—time, space, transportation, environment, and disaster—is constructed.

4. The method for allocating emergency resources for high-altitude highways according to claim 3, characterized in that, The constraint functions established in S25 include: Resource input constraints include the maximum amount of equipment and personnel required for each section of the road; Reliability constraints: the reliability of each road segment in the optimal allocation scheme of emergency resources shall not be lower than its reliability in the original emergency resource allocation scheme. Total resource constraints, including the total amount of available equipment and personnel; Emergency rescue resources are indivisible, and the quantity of each type of resource is an integer.

5. An electronic device, characterized in that, The electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the high-altitude highway emergency resource allocation method according to any one of claims 1 to 4.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the high-altitude highway emergency resource allocation method according to any one of claims 1 to 4.

7. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the high-altitude highway emergency resource allocation method as described in any one of claims 1 to 4.

Images