A ramp closure control scheme optimization method for an expressway and a related device

Abstract

The application is suitable for the field of urban road network active control technology, and provides a ramp closure control scheme optimization method for expressway and related equipment, which comprises the following steps: obtaining an initial population; updating the initial population to obtain an intermediate population; merging the initial population and the intermediate population, and sorting the population individuals in the merged intermediate population, determining a new intermediate population according to the sorting result; calculating the first average fitness of the discoverer in the new intermediate population, obtaining new population individuals of multiple categories of discoverers based on the first average fitness; calculating the second average fitness of the joiner, obtaining new population individuals of multiple categories of joiners based on the second average fitness; performing a selection operation on the new population individuals to obtain a selected intermediate population; determining the optimal population individual according to a pre-set multi-objective optimization function, and simulating the corresponding ramp control scheme to obtain a road network state evaluation index. The application can improve the passing efficiency of the expressway.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of traffic information management, and particularly relates to a ramp closure control scheme optimization method for an expressway and related equipment. BACKGROUND

[0002] In recent years, the construction of expressways has entered a period of rapid development. Compared with other urban roads, an expressway is a road with a higher level, good accessibility and fast driving speed, and is a key to improving urban passenger and freight transportation and optimizing urban network structure, so various countries are actively developing effective expressway active control strategies to improve the operation efficiency of urban expressways.

[0003] However, with the rapid increase in the number of vehicles, the phenomenon that the demand for road traffic is much greater than the supply of road resources is becoming increasingly serious.

[0004] At present, in the construction process of a large number of urban expressways, the planning and design of import and export ramps do not take into account the actual road network traffic flow characteristics, lack scientific matching of express ramps and regional road networks, and the setting of many ramps will cause serious imbalance in traffic flow distribution in the road network, and no effective active control strategy is taken in time, resulting in the gradual loss of efficiency and accessibility of the expressway network, and serious traffic congestion problems occur from time to time.

[0005] Under this background, how to adjust the opening and closing of ramp entrances through active traffic control means to maximize the role of each import and export ramp in the road network is an important issue currently faced. SUMMARY

[0006] The application provides a ramp closure control scheme optimization method for an expressway and related equipment, which can solve the problem of low traffic efficiency of the expressway.

[0007] In a first aspect, the application provides a ramp closure control scheme optimization method for an expressway, comprising:

[0008] Step 1, collecting ramp information of a target expressway, and constructing an initial population according to the ramp information and a Logistic chaotic mapping algorithm; the initial population includes a plurality of population individuals, the plurality of population individuals correspond to a plurality of ramp control schemes, different ramp control schemes corresponding to different population individuals are different from each other, and the ramp control scheme includes the state of all ramps on the target expressway, and the state is opening or closing;

[0009] Step 2, sorting the population individuals of the initial population by using a fast non-dominated sorting algorithm, obtaining a population sequence of the initial population, calculating the fitness of the population individuals of the initial population, and determining the category of each population individual in the initial population according to the fitness and the population sequence; the category is a discoverer or a joiner;

[0010] Step 3, update the initial population based on the sparrow search algorithm to obtain an intermediate population;

[0011] Step 4, merge the initial population and the intermediate population to obtain a merged intermediate population, sort the population individuals in the merged intermediate population using a fast non-dominated algorithm and a crowding degree calculation algorithm, and determine a new intermediate population according to the sorting result, update the new intermediate population using the sparrow search algorithm to obtain an updated intermediate population;

[0012] Step 5, calculate the first average fitness of all population individuals of the discoverer category in the updated intermediate population, and perform a crossover operation on the population individuals of the discoverer category whose fitness is greater than or equal to the first average fitness to obtain multiple new population individuals of the discoverer category;

[0013] Step 6, calculate the second average fitness of all population individuals of the joiner category in the updated intermediate population, and perform a mutation operation on the population individuals of the joiner category whose fitness is less than or equal to the second average fitness to obtain multiple new population individuals of the joiner category;

[0014] Step 7, perform a selection operation on the multiple new population individuals of the discoverer category and the multiple new population individuals of the joiner category to obtain a selected intermediate population, if the selected intermediate population meets a preset iteration termination condition, execute step 8; otherwise, return to execute step 4 for the population individuals in the selected intermediate population;

[0015] Step 8, determine an optimal population individual from the selected intermediate population according to a pre-set multi-objective optimization function, input the ramp control scheme corresponding to the optimal population individual into VISSIM micro-simulation software to obtain a road network state evaluation index, if the road network state evaluation index meets a preset index condition, perform ramp control on the target expressway according to the ramp control scheme corresponding to the optimal population individual; otherwise, take the intermediate population as the initial population in step 4, take the updated intermediate population as the intermediate population in step 4, and return to execute step 4; the multi-objective optimization function includes total expressway delay and average delay of main roads and main road intersections.

[0016] Optionally, the initial population is constructed according to ramp information and a Logistic chaotic mapping algorithm, comprising:

[0017] According to the ramp information, a plurality of ramp control schemes are randomly generated;

[0018] For each ramp control scheme, a calculation formula is used to calculate the fitness of the ramp control scheme

[0019]

[0020] Get the binary value of the ramp control solution Where S(·) represents the S-type transfer function, t represents the number of iterations, id represents the dimension d of the i-th ramp control scheme, and rd represents a random number between [0, 1].

[0021] The binary value is used as the gene of the population individual corresponding to the ramp control scheme to obtain the original individual x k ; k = 1, 2, ..., N, N represents the total number of multiple ramp control schemes;

[0022] By calculating the formula x k+1 =μx k (1-x k ), get the new original individual x k+1 ; where μ∈(0,4];

[0023] By calculating the formula X=X lb +(X ub -X lb )X k +1, we get the initial population X; where X lb represents the upper limit of the ramp control solution dimension corresponding to each new original individual, X ub Indicates the lower limit of the ramp control solution dimension corresponding to each new original individual.

[0024] Optionally, the category to which each individual in the initial population belongs is determined based on fitness and population sequence, including:

[0025] Determine the category of the population individuals whose fitness is greater than or equal to the preset fitness threshold among all the population individuals in the population sequence as discoverers;

[0026] The categories of population individuals whose fitness is less than a preset fitness threshold among all population individuals in the population sequence are determined as joiners.

[0027] Optionally, a crossover operation is performed on the population individuals of the discoverer category whose fitness is greater than or equal to the first average fitness, including:

[0028] By calculating the formula

[0029]

[0030] Get a new population of individuals whose category is discoverer in, represents the population individuals after mutation, represents the original population individuals, and CR represents the crossover probability.

[0031] Optionally, the population individuals of the joiner category with fitness less than or equal to the second average fitness are subjected to a mutation operation, including:

[0032] The new population individual V of the joiner category is obtained by the calculation formula i , represents the population individual of the joiner category, c = 1, 2, 3, r c represents three random integers different from each other in 1 to N, N represents the number of ramp closure schemes in a population, and F represents a mutation probability.

[0033] Optionally, the selection operation is performed on the plurality of new population individuals of the discoverer category and the plurality of new population individuals of the joiner category, including:

[0034] The population individual of the intermediate population is obtained by the calculation formula

[0035]

[0036] wherein f(·) represents a fitness function.

[0037] Optionally, the expression of the multi-objective optimization function is as follows:

[0038] min{W x ,Z x |x∈X}

[0039] s.t.G[x,W x ,Z x ]≤0

[0040]

[0041] s.t.g[m b ,W x ,Z x ]≤0

[0042] wherein G[x,W x ,Z x ]≤0 represents a first constraint condition, x represents a ramp control scheme, X represents an updated intermediate population, m b represents the traffic volume of the bth ramp in the target expressway, g[m b ,W x ,Z x ]≤0 represents a second constraint condition, W x represents the total delay of the system road network, and Z x represents the total delay of the expressway main road intersection:

[0043] ​​

[0044] where T ab represents the travel time between the a-th ramp and the b-th ramp, V ab represents the speed of vehicles on the road segment between the a-th ramp and the b-th ramp, I represents the number of ramps of the target freeway, C ab represents the capacity of vehicles on the road segment between the a-th ramp and the b-th ramp, S ab represents other delay factors from the a-th ramp to the b-th ramp, a, b represent weight parameters, K represents the number of intersections of the target freeway, d k represents the delay factor of the k-th intersection, T wait,k represents the waiting time of the k-th intersection, T stop,k represents the stopping time of the k-th intersection, Q k represents the queue length of the k-th intersection, a, b represent weight parameters;

[0045] The first constraint condition G[x, W x , Z x ]≤0 includes:

[0046] Traffic capacity constraint: the total traffic volume on the road segment passed by vehicles cannot exceed the capacity of the road segment, and the expression is:

[0047]

[0048] Maximum queue length constraint: the queue length of any one flow direction in the intersection at any time cannot exceed the preset maximum queue length Q max , and the expression is:

[0049]

[0050] where Q k represents the queue length of any one flow direction of the k-th intersection;

[0051] Green light duration constraint: the duration of the green light should meet the vehicle passing demand of each direction, while being limited by the preset minimum green light duration T green,min and the maximum green light duration T green,max , and the expression is:

[0052] T green,min ≤T green ≤T green,max

[0053] where T green represents the green light duration;

[0054] Ramp switching constraint: each ramp on the freeway presents two states, i.e., open and closed states, where x ais the switch state of the a-th ramp, which can only be closed or opened, and the expression is:

[0055] x a ∈{0,1},a=1,2,…,I

[0056] Wherein, 0 represents the closed state, and 1 represents the opened state.

[0057] Optionally, the preset iteration termination condition in step 7 is a preset maximum iteration number.

[0058] In a second aspect, the present application provides a terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the ramp closure control scheme optimization method described above when executing the computer program.

[0059] In a third aspect, the present application provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the ramp closure control scheme optimization method described above.

[0060] The above-mentioned scheme of the present application has the following beneficial effects:

[0061] The ramp closure control scheme optimization method of the expressway provided by the present application can effectively avoid the population individuals from falling into local optimum, improve the uniformity of the population individuals, and improve the rationality of the ramp control scheme, which is conducive to improving the traffic efficiency of the expressway; the multi-objective optimization function constructed fully considers the road network traffic flow characteristics, realizes the scientific matching of the expressway ramp and the regional road network, and is conducive to improving the traffic efficiency of the expressway.

[0062] Other beneficial effects of the present application will be described in detail in the subsequent specific embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0063] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0064] Figure 1 The flow chart of the ramp closure control scheme optimization method of the expressway provided by an embodiment of the present application;

[0065] Figure 2 The interaction schematic diagram of the COM interface model provided by an embodiment of the present application;

[0066] Figure 3 Figure 1 is an execution flow chart of a ramp closure control scheme optimization method for a freeway in an embodiment of the present application;

[0067] Figure 4 Figure 1 is an execution flow chart of a ramp closure control scheme optimization method for a freeway in an embodiment of the present application; DETAILED DESCRIPTION

[0068] In the following description, for purposes of explanation and not limitation, specific details are set forth such as particular architectures, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application can be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known methods, devices, circuits, and

[0069] It is to be understood that the terminology "includes", "has", "holds", "contains" or "comprising", "comprised of" or "comprising", as used in the specification and in the following claims, indicates the presence of the described features, integers, steps, operations, elements, and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0070] It is also to be understood that the terminology "and / or" as used in the specification and in the following claims, indicates any combination of the associated listed items, as well as all possible combinations of the items.

[0071] As used in the specification and in the following claims, the term "if" can be interpreted as meaning "when", or "upon", or "in response to determining", or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [the described condition or event] is detected" can be interpreted as meaning "upon determining", or "in response to determining", or "upon detecting [the described condition or event]", or "in response to detecting [the described condition or event]", depending on the context.

[0072] In addition, in the description of the specification and in the following claims, the terms "first", "second", "third", etc. are used only to distinguish descriptions, and cannot be understood as indicating or implying relative importance.

[0073] Reference within this specification to "one embodiment" or "an embodiment" or "some embodiments" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment. The appearances of the phrase "in one embodiment" or "in some embodiments" within this specification do not necessarily refer to the same embodiment, although it can. The terms "including," "comprising," "having," and variations thereof mean "including but not limited to," unless expressly specified otherwise.

[0074] In view of the low traffic efficiency of the expressway, the application provides an expressway ramp closure control scheme optimization method and related equipment, wherein the method constructs an initial population according to ramp information and a Logistic chaotic mapping algorithm, which can effectively avoid the population individuals from falling into local optimization, improve the uniformity of the population individuals, improve the rationality of the ramp control scheme, and is conducive to improving the traffic efficiency of the expressway; the multi-objective optimization function constructed fully considers the road network traffic flow characteristics, realizes scientific matching of the express ramp and the regional road network, and is conducive to improving the traffic efficiency of the expressway.

[0075] The expressway ramp closure control scheme optimization method provided by the application will be described in detail below.

[0076] As shown in Figure 1 The expressway ramp closure control scheme optimization method specifically includes the following steps:

[0077] Step 1, collecting ramp information of a target expressway, and constructing an initial population according to the ramp information and a Logistic chaotic mapping algorithm.

[0078] In the embodiments of the application, the above-mentioned ramp information can be obtained from the traffic survey electric police portal flow data, which specifically includes the number of ramps of the target expressway, the state of each ramp, and the traffic flow data of each ramp.

[0079] The initial population includes a plurality of population individuals, and the plurality of population individuals correspond to a plurality of ramp control schemes. The ramp control schemes corresponding to different population individuals are different from each other. The ramp control scheme includes the state of all ramps on the target expressway, and the state is open or closed.

[0080] Since the ramp control problem is essentially a binary problem (for example: 0 represents the ramp closed, 1 represents the ramp open), the present application introduces a Sigmoidal (S-shaped) transfer function, according to the behavior of the prey and anti-prey of the sparrow, the transfer function provides the probability value of the sparrow position vector from 0 to 1, in order to update the position of the sparrow. In the sparrow optimization algorithm (SSA, SParrow Search Algorithm), the new position of the global or local search sparrow will have continuous solutions, so these continuous values must be converted into corresponding binary values, in the embodiment of the present application, this conversion is realized by using S-shaped transfer function to apply compression to continuous solutions in each dimension, which will force the sparrow to move in the binary search space.

[0081] In addition, for swarm intelligence algorithms, the quality and stability of the initial solution selection directly affect the convergence speed of the algorithm, in view of this problem, the present application tries to use Logistic chaotic mapping algorithm to replace the random initialization of SSA, the use of Logistic chaotic mapping algorithm for initialization can make the initial population of SSA more abundant, more uniform in distribution, and more extensive in search range, and overall more suitable for handling ramp control problems.

[0082] Step 2, using the fast non-dominated sorting algorithm, sorting the population individuals of the initial population to obtain the population sequence of the initial population, calculating the fitness of the population individuals of the initial population, and determining the category of each population individual in the initial population according to the fitness and the population sequence.

[0083] The above category is a discoverer or a joiner.

[0084] For example, the above fitness can be calculated by multi-objective optimization techniques such as NSGA-II (Non-dominated Sorting Genetic Algorithm II).

[0085] Specifically, the category of the population individual with fitness greater than or equal to the preset fitness threshold in all population individuals of the population sequence is determined as a discoverer, and the category of the population individual with fitness less than the preset fitness threshold in all population individuals of the population sequence is determined as a joiner.

[0086] It should be understood that in the traditional sparrow search algorithm, the population individuals need to be sorted by using the fast non-dominated sorting algorithm, and then the fitness of each population individual is calculated according to the sorting result, and then the category of each population individual is determined according to the fitness.

[0087] Step 3, updating the initial population based on the sparrow search algorithm to obtain an intermediate population.

[0088] Exemplarily, the sparrow search algorithm can be run by using computer software such as matlab, the initial population is updated, and the intermediate population is output.

[0089] Step 4, the initial population and the intermediate population are combined to obtain a combined intermediate population, the population individuals in the combined intermediate population are sorted by using the fast non-dominated sorting algorithm and the crowding distance calculation algorithm, and a new intermediate population is determined according to the sorting result, the new intermediate population is updated by using the sparrow search algorithm to obtain an updated intermediate population.

[0090] In some embodiments of the present application, the step of sorting the population individuals in the combined intermediate population by using the fast non-dominated sorting algorithm and the crowding distance calculation algorithm and determining the new intermediate population according to the sorting result is specifically: the population individuals in the combined intermediate population are fast non-dominated sorted to obtain multiple frontiers, the crowding distance of each population individual is calculated by using the crowding distance calculation algorithm, all population individuals corresponding to the first frontier are added to the new population, if the number of population individuals in the new population is greater than the preset number, all population individuals are arranged in descending order according to the crowding distance of each population individual, and the first preset number of population individuals are reserved to obtain the new intermediate population; if the number of population individuals in the new population is equal to the preset number, the new population is directly taken as the new intermediate population; if the number of population individuals in the new population is less than the preset number, multiple population individuals corresponding to the second frontier are added to the new population, and whether the number of population individuals in the new population is less than the preset number is determined, and so on, until the number of population individuals in the new population is greater than or equal to the preset number.

[0091] Step 5, the first average fitness of all population individuals of the discoverer category in the updated intermediate population is calculated, and the population individuals of the discoverer category with fitness greater than or equal to the first average fitness are subjected to crossover operation to obtain multiple new population individuals of the discoverer category.

[0092] Exemplarily, the calculation formula of the first average fitness is:

[0093]

[0094] Wherein, Fitness1 represents the first average fitness, T represents the total number of population individuals of the discoverer category, m = 1, 2,..., T, F m represents the fitness of the mth population individual of the discoverer category.

[0095] This can enhance the ability of SSA to jump out of a local optimal solution.

[0096] Specifically, the calculation formula is

[0097]

[0098] obtaining new population individuals of the discoverer category wherein, denotes the population individual after mutation, denotes the original population individual, and CR denotes a crossover probability.

[0099] Step 6, calculating a second average fitness of all population individuals of the joiner category in the updated intermediate population, and performing a mutation operation on the population individuals of the joiner category with fitness less than or equal to the second average fitness, to obtain a plurality of new population individuals of the joiner category.

[0100] For example, the calculation formula of the second average fitness is as follows:

[0101]

[0102] wherein, Fitness2 denotes the second average fitness, M denotes the total number of population individuals of the joiner category, l = 1, 2,.., Q, and F l denotes the fitness of the lth population individual of the joiner category.

[0103] Specifically, the new population individual V i of the joiner category is obtained by the calculation formula c denotes the population individual of the joiner category, c = 1, 2, 3, and r c denotes three random integers different from each other in 1 to N, N denotes the number of ramp closure schemes in a population, and F denotes a mutation probability.

[0104] By performing the above steps 3 to 4, the sparrow population is crossed and mutated in each iteration, which makes the high-quality solution further high-quality, the poor-quality solution further eliminated, the local optimal solution originally unable to continue to update further updated, the population diversity increased, the ability of the algorithm to jump out of the local optimal solution improved, and the traffic efficiency of the expressway improved.

[0105] Step 7, performing a selection operation on the plurality of new population individuals of the discoverer category and the plurality of new population individuals of the joiner category, to obtain a selected intermediate population, and if the selected intermediate population meets a preset iteration termination condition, performing step 8; otherwise, returning to perform step 4 for the population individuals in the selected intermediate population.

[0106] The preset iteration termination condition is a maximum number of iterations preset in advance.

[0107] For the population individuals in the intermediate population, the category of the population individual with the fitness (calculated in the same way as above) greater than or equal to the preset fitness threshold is determined as a discoverer, and the category of the population individual with the fitness less than the preset fitness threshold is determined as a joiner.

[0108] Specifically, the selection operation is performed on the plurality of new population individuals of the category of discoverer and the plurality of new population individuals of the category of joiner, including:

[0109] by the calculation formula

[0110]

[0111] obtaining the population individuals of the intermediate population wherein f(·) represents a fitness function.

[0112] Step 8, determining the optimal population individual from the selected intermediate population according to a preset multi-objective optimization function, inputting the ramp control scheme corresponding to the optimal population individual into VISSIM micro-simulation software to obtain a road network state evaluation index, and if the road network state evaluation index meets a preset index condition, performing ramp management and control on the target expressway according to the ramp control scheme corresponding to the optimal population individual; otherwise, taking the intermediate population as the initial population in step 4, taking the updated intermediate population as the intermediate population in step 4, and returning to step 4.

[0113] The multi-objective optimization function includes total delay of the expressway, average delay of the main road and the main road intersection.

[0114] The expression of the multi-objective optimization function is as follows:

[0115] min{W x ,Z x |x∈X}

[0116] s.t.G[x,W x ,Z x ]≤0

[0117]

[0118] s.t.g[m b ,W x ,Z x ]≤0

[0119] wherein G[x,W x ,Z x ]≤0 represents a first constraint condition, x represents a ramp control scheme, X represents an updated intermediate population, m b represents the traffic volume of the bth ramp in the target expressway, and g[m b ,W x ,Zx ]≤0 represents the second constraint condition, W x represents the total delay of the system road network, Z x represents the total delay of the main road intersection of the expressway:

[0120]

[0121] wherein, T ab represents the passing time between the a ramp and the b ramp, V ab represents the traffic flow of the road section between the a ramp and the b ramp, I represents the number of ramps of the target expressway, C ab represents the vehicle capacity of the road section between the a ramp and the b ramp, S ab represents other delay factors from the a ramp to the b ramp, α, β represent weight parameters, K represents the number of intersections of the target expressway, δ k represents the delay factor of the k intersection, T wait,k represents the waiting time of the k intersection, T stop,k represents the stopping time of the k intersection, Q k represents the queue length of the k intersection, λ, γ represent weight parameters;

[0122] The first constraint condition G[x, W x , Z x ]≤0 includes:

[0123] Traffic capacity constraint: the total traffic flow on the road section passed by the vehicle cannot exceed the capacity of the road section, and the expression is:

[0124]

[0125] Maximum queue length constraint: the queue length of any one flow direction in the intersection at any time cannot exceed the preset maximum queue length Q max , and the expression is:

[0126]

[0127] wherein, Q k represents the queue length of any one flow direction of the k intersection;

[0128] Green light duration constraint: the duration of the green light should meet the vehicle passing demand of each direction, and is limited by the preset minimum green light duration T green,min and the maximum green light duration T green,max , and the expression is:

[0129] T green,min ≤T green ≤T green,max

[0130] wherein, T green represents the green light duration;

[0131] Ramp switch constraint: each ramp on the expressway presents two states, i.e. open and closed state, wherein x a is the switch state of the a-th ramp, which can only be closed or open, and the expression is:

[0132] x a ∈{0,1},a=1,2,…,I

[0133] wherein, 0 represents the closed state, and 1 represents the open state.

[0134] In some embodiments of the present application, the above-mentioned ramp control scheme corresponding to all population individuals in the selected intermediate population can be substituted into the above-mentioned multi-objective optimization function, and the ramp control scheme in which the values of the two optimization functions in the multi-objective optimization function are both less than the optimization function threshold value is selected as the optimal population individual, and if there are multiple ramp control schemes in which the values of the two optimization functions are both less than the optimization function threshold value, the ramp control scheme in which the average value of the values of the two optimization functions is the smallest is selected as the optimal population individual.

[0135] The above-mentioned step of inputting the ramp control scheme corresponding to the optimal population individual into the VISSIM microscopic simulation software to obtain the road network state evaluation index specifically includes:

[0136] A microscopic traffic simulation model is constructed through the VISSIM microscopic simulation software. In the embodiments of the present application, the microscopic traffic simulation model comprehensively considers roads, driving behavior, traffic control, vehicles, and multiple factors. In order to ensure the accuracy and feasibility of the model, traffic investigation, data analysis, parameter correction, and repeated tests are also required.

[0137] Then, the component object model (COM, component object model) provided by VISSIM is used to realize the reading and writing of internal objects through external programs, and the COM interface is used to dynamically adjust the switch state of the ramp according to the ramp closing scheme, so as to control the output of simulation running and road network optimization evaluation. The interaction of the above-mentioned COM interface model is as shown in Figure 2 .

[0138] The simulation results of the simulation model are evaluated to obtain the road network state evaluation index, and if the road network state evaluation index meets the preset index condition (such as being greater than the preset evaluation index value), the ramp control scheme corresponding to the optimal population individual is used to control the target expressway.

[0139] The process of constructing the initial population according to the ramp information and the Logistic chaotic mapping algorithm in step 1 is described in detail as follows:

[0140] Step 1.1, according to ramp information, randomly generate multiple ramp control schemes.

[0141] Exemplarily, a random counting generation algorithm can be used to generate multiple groups of numerical values, and the numerical values in each group correspond to one ramp. At this time, the numerical value is a randomly generated number and does not have physical meaning. Subsequently, binary conversion needs to be performed on each group of numerical values. For details, refer to step 1.2.

[0142] Exemplarily, in an embodiment of the present application, the target expressway has 5 ramps, and one of the generated multiple ramp control schemes is ramp 1: state 1, ramp 2: state 2, ramp 3: state 3, ramp 4: state 4, and ramp 5: state 5.

[0143] Step 1.2, respectively for each ramp control scheme, through the calculation formula

[0144]

[0145] The binary value of the ramp control scheme is obtained

[0146] Wherein, S(·) represents the S-type transfer function, t represents the iteration number, id represents the dimension d of the i-th ramp control scheme, and rd represents a random number between 0 and 1.

[0147] Step 1.3, taking the binary value as the gene of the individual corresponding to the ramp control scheme, to obtain the original individual x k .

[0148] k=1, 2,..., N, N represents the total number of multiple ramp control schemes.

[0149] Step 1.4, through the calculation formula x k+1 = μx k (1-x k ), obtain the new original individual x k+1 .

[0150] Wherein, μ∈(0, 4].

[0151] This step uses the Logistic chaotic system to replace the random initialization of SSA, which can make the initial population of SSA more abundant, more uniform in distribution, and more extensive in search range, and overall more suitable for handling ramp control problems.

[0152] Step 1.5, through the calculation formula X=X lb +(X ub -X lb )X k +1, obtain the initial population X. Wherein, Xlb represents the upper limit of the ramp control scheme dimension corresponding to each new original individual, X ub represents the lower limit of the ramp control scheme dimension corresponding to each new original individual.

[0153] The upper limit of the ramp control scheme dimension is the total number of ramps.

[0154] It is worth noting that as the slope of the transfer function increases, the probability of the transfer function changing the position of the population individual according to the fitness value is also rising, and the transfer function is in such a way to increase the diversity of the solution to the ramp control problem, and thus improve the performance of the swarm intelligence algorithm.

[0155] The ramp closure control scheme optimization method for the expressway provided by the present application will be described in detail below with reference to specific embodiments.

[0156] As shown in the figure, first, the ramp information of the target expressway is collected, and the initial population is constructed according to the ramp information and the Logistic chaotic mapping algorithm, the fitness of each population individual is calculated, and the category to which each population individual belongs is determined according to the fitness, and then it is judged whether to generate offspring. Figure 3 If no offspring is generated, the offspring is generated through non-dominated sorting and SSA population updating.

[0157] For example, first, the individuals in the population are non-dominated sorted and divided into different front layers (or called non-dominated set), then in the non-dominated sorting, the individuals are divided into different levels according to the dominance relationship between the individuals, i.e. the first level contains individuals that are not dominated by other individuals, the second level contains individuals that are only dominated by the first level individuals, and so on, and then individuals are selected from the front layer to construct the offspring population. Usually, the earlier front layer is selected because these individuals usually have better fitness, then the selected individuals are updated using the SSA algorithm, and the new offspring population is generated by combining the selection operation and the result of the SSA population updating.

[0158] If the offspring can be generated, the initial population and the offspring are combined to obtain a new population.

[0159] Subsequently, it is judged whether the new population selects the offspring.

[0160]

[0161] ​If the new population selects offspring, the total population is updated based on SSA, the first average fitness of all population individuals of the category of discoverers is calculated, and the population individuals of the category of discoverers whose fitness is greater than or equal to the first average fitness are crossover operations to obtain multiple new population individuals of the category of discoverers. Then, the second average fitness of all population individuals of the category of joiners is calculated, and the population individuals of the category of joiners whose fitness is less than or equal to the second average fitness are mutated to obtain multiple new population individuals of the category of joiners. Then, the multiple new population individuals of the category of discoverers and the multiple new population individuals of the category of joiners are selected to obtain the intermediate population, until the intermediate population meets the preset iteration termination condition.

[0162] If the new population cannot select offspring, the new population is subjected to fast non-dominated sorting and crowding calculation, and then the best and worst position individuals are determined. Then suitable individuals are selected to form an individual population, and the fitness of the individual population is calculated using discrete binarization until the individual population (new population) can select offspring.

[0163] Finally, according to the pre-set multi-objective optimization function, the optimal population individual is determined from the intermediate population, and the ramp control of the target expressway is performed according to the ramp control scheme corresponding to the optimal population individual.

[0164] like Figure 4 As shown, an embodiment of the present application provides a terminal device, such as Figure 4 As shown, the terminal device D10 of this embodiment includes: at least one processor D100 ( Figure 4 Only one processor is shown in the figure), a memory D101, and a computer program D102 stored in the memory D101 and executable on at least one processor D100. When the processor D100 executes the computer program D102, the steps of any of the above method embodiments are implemented.

[0165] Specifically, when the processor D100 executes the computer program D102, step 1, the ramp information of the target expressway is collected, and an initial population is constructed according to the ramp information and the Logistic chaotic mapping algorithm; step 2, the population individuals of the initial population are sorted by using the fast non-dominated sorting algorithm, the population sequence of the initial population is obtained, the fitness of the population individuals of the initial population is calculated, and the category to which each population individual in the initial population belongs is determined according to the fitness and the population sequence; step 3, the initial population is updated based on the sparrow search algorithm to obtain an intermediate population; step 4, the initial population and the intermediate population are merged to obtain a merged intermediate population, the population individuals in the merged intermediate population are sorted by using the fast non-dominated sorting algorithm and the crowding degree calculation algorithm, and according to the sorting result, a new intermediate population is determined, the new intermediate population is updated by using the sparrow search algorithm to obtain an updated intermediate population; step 5, the first average fitness of the population individuals of all categories of discoverers in the updated intermediate population is calculated, and the population individuals of the categories of discoverers whose fitness is greater than or equal to the first average fitness are subjected to a crossover operation to obtain a plurality of new population individuals of the categories of discoverers; step 6, the second average fitness of the population individuals of all categories of joiners in the updated intermediate population is calculated, and the population individuals of the categories of joiners whose fitness is less than or equal to the second average fitness are subjected to a mutation operation to obtain a plurality of new population individuals of the categories of joiners; step 7, the plurality of new population individuals of the categories of discoverers and the plurality of new population individuals of the categories of joiners are subjected to a selection operation to obtain a selected intermediate population, and if the selected intermediate population meets a preset iteration termination condition, step 8 is executed; otherwise, for the population individuals in the selected intermediate population, step 4 is executed again; step 8, the optimal population individual is determined from the selected intermediate population according to a pre-set multi-objective optimization function, the ramp control scheme corresponding to the optimal population individual is input into the VISSIM micro-simulation software, the road network state evaluation index is obtained, and if the road network state evaluation index meets a preset index condition, the target expressway is subjected to ramp management and control according to the ramp control scheme corresponding to the optimal population individual; otherwise, the intermediate population is taken as the initial population in step 4, the updated intermediate population is taken as the intermediate population in step 4, and step 4 is executed again. The initial population constructed according to the ramp information and the Logistic chaotic mapping algorithm can effectively avoid the population individuals from falling into local optimum, improve the uniformity of the population individuals, and improve the rationality of the ramp control scheme, which is conducive to improving the passing efficiency of the expressway; the multi-objective optimization function constructed fully considers the road network traffic flow characteristics, realizes the scientific matching of the expressway ramp and the regional road network, and is conducive to improving the passing efficiency of the expressway.

[0166] The processor D100 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic components, discrete hardware components, etc. The general-purpose processor can be a microprocessor or can also be any conventional processor.

[0167] The memory D101 can be an internal storage unit of the terminal device D10 in some embodiments, for example, a hard disk or a memory of the terminal device D10. The memory D101 can also be an external storage device of the terminal device D10 in other embodiments, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the memory D101 can include both the internal storage unit and the external storage device of the terminal device D10. The memory D101 is used to store an operating system, an application program, a boot loader, data, and other programs, for example, program codes of the computer program, etc. The memory D101 can also be used to temporarily store data that has been output or will be output.

[0168] The embodiments of the present application further provide a computer readable storage medium, which stores a computer program. The computer program is executed by a processor to implement the steps in the above-mentioned various method embodiments.

[0169] The embodiments of the present application provide a computer program product. When the computer program product is run on a terminal device, the terminal device is caused to implement the steps in the above-mentioned various method embodiments.

[0170] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the present application can implement all or part of the processes in the above-mentioned embodiment methods through a computer program to instruct relevant hardware to complete, and the computer program can be stored in a computer readable storage medium. When the computer program is executed by a processor, the steps of each method embodiment described above can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable files or some intermediate forms. The computer readable medium at least includes any entity or device capable of carrying the computer program code to the terminal device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium. For example, U disk, mobile hard disk, magnetic disk or optical disk, etc. In some jurisdictions, according to legislation and patent practice, the computer readable medium can not be an electrical carrier signal and a telecommunication signal.

[0171] In the above embodiments, the description of each embodiment has its own focus, and the parts not described or recorded in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0172] Those of ordinary skill in the art can understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether the functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Professionals can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0173] In the embodiments provided by the present application, it should be understood that the disclosed apparatus / network device and method can be implemented in other ways. For example, the above-described apparatus / network device embodiments are merely schematic, for example, the division of the modules or units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed each other can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0174] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may also be distributed to multiple network units. Part or all of the units can be selected to achieve the purpose of the embodiment of the present application according to actual needs.

[0175] The above is the preferred embodiment of the present application. It should be pointed out that for ordinary skilled persons in the art, without departing from the principles described in the present application, a number of improvements and refinements can be made, which should also be considered as the protection scope of the present application.

Claims

1. A method for optimizing a ramp closure control scheme for an expressway, characterized in that: The method comprises the following steps: Step 1, collecting ramp information of a target expressway, and constructing an initial population according to the ramp information and a Logistic chaotic mapping algorithm; the initial population comprises a plurality of population individuals, the plurality of population individuals correspond to a plurality of ramp control schemes, different population individuals correspond to different ramp control schemes, and the ramp control scheme comprises the state of all ramps on the target expressway, and the state is opening or closing; Step 2, sorting the population individuals of the initial population by using a fast non-dominated sorting algorithm to obtain a population sequence of the initial population, calculating the fitness of the population individuals of the initial population, and determining the category of each population individual in the initial population according to the fitness and the population sequence; The category is a discoverer or a joiner; Step 3, updating the initial population based on a sparrow search algorithm to obtain an intermediate population; Step 4, merging the initial population and the intermediate population to obtain a merged intermediate population, sorting the population individuals in the merged intermediate population by using a fast non-dominated sorting algorithm and a crowding degree calculation algorithm, and determining a new intermediate population according to the sorting result, updating the new intermediate population by using the sparrow search algorithm to obtain an updated intermediate population; Step 5, calculating a first average fitness of the population individuals of the updated intermediate population in which the category is a discoverer, and performing a crossover operation on the population individuals in which the category is a discoverer and whose fitness is greater than or equal to the first average fitness to obtain a plurality of new population individuals in which the category is a discoverer; Step 6, calculating a second average fitness of the population individuals of the updated intermediate population in which the category is a joiner, and performing a mutation operation on the population individuals in which the category is a joiner and whose fitness is less than or equal to the second average fitness to obtain a plurality of new population individuals in which the category is a joiner; Step 7, performing a selection operation on the plurality of new population individuals in which the category is a discoverer and the plurality of new population individuals in which the category is a joiner to obtain a selected intermediate population, and if the selected intermediate population meets a preset iteration termination condition, executing Step 8; otherwise, returning to execute Step 4 for the population individuals in the selected intermediate population; Step 8, determining an optimal population individual from the selected intermediate population according to a pre-set multi-objective optimization function, inputting a ramp control scheme corresponding to the optimal population individual into VISSIM micro-simulation software to obtain a road network state evaluation index, and if the road network state evaluation index meets a preset index condition, performing ramp control on the target expressway according to the ramp control scheme corresponding to the optimal population individual; otherwise, taking the intermediate population as the initial population in Step 4 and taking the updated intermediate population as the intermediate population in Step 4, and returning to execute Step 4; the multi-objective optimization function comprises total delay of the expressway, average delay of the main road and the main road intersection; The initial population is constructed according to the ramp information and the Logistic chaotic mapping algorithm. According to the ramp information, a plurality of ramp control schemes are randomly generated; For each ramp control scheme, a fitness value of each population individual in the initial population is calculated by a formula obtaining a binary value of the ramp control scheme where S(·) denotes a sigmoid transfer function, t denotes an iteration number, id denotes a dimension d of the i-th ramp control scheme, and rd denotes a random number located between 0 and 1. obtaining a binary value corresponding to the ramp control scheme as a gene of a population individual corresponding to the ramp control scheme to obtain an original individual x k ; k = 1, 2, …, N, N represents the total number of the plurality of ramp control schemes; By calculating formula x k+1 = μx k (1-x k ), a new original individual x k+1 is obtained; wherein, μ ∈ (0, 4]; By calculating formula X=X lb +(X ub -X lb )X k +1, obtain the initial population X; wherein, X lb indicates the upper limit of the ramp control scheme dimension corresponding to each of the new original individuals, X ub indicates the lower limit of the ramp control scheme dimension corresponding to each of the new original individuals.

2. The ramp closure control scheme optimization method of claim 1, wherein, The determining of the category to which each population individual in the initial population belongs according to the fitness value and the population sequence comprises: The category of each population individual in the population sequence whose fitness value is greater than or equal to a preset fitness threshold is determined as a discoverer. The category of each population individual in the population sequence whose fitness value is less than the preset fitness threshold is determined as a joiner.

3. The ramp closure control scheme optimization method of claim 2, wherein, The cross operation on the population individual whose category is the discoverer and whose fitness value is greater than or equal to the first average fitness value comprises: The mutation operation on the population individual whose category is the joiner and whose fitness value is less than or equal to the second average fitness value comprises: Obtaining new population individuals of the class discoverer wherein, denotes a population individual after mutation, denotes an original population individual, CR denotes a crossover probability.

4. The ramp closure control scheme optimization method of claim 3, wherein, The selection operation on the new population individual whose category is the discoverer and the new population individual whose category is the joiner comprises: The new population individuals V of the category of joiners are obtained by the calculation formula The new population individuals V of the category of joiners are obtained by the calculation formula i , The population individuals of the category of joiners are represented as c = 1, 2, 3, r c Three random integers that are not equal to each other in 1 to N are represented, N represents the number of ramp closure schemes in a population, and F represents the mutation probability.

5. The ramp closure control scheme optimization method of claim 4, wherein, The expression of the multi-objective optimization function is as follows: Traffic capacity constraint: the total traffic volume of vehicles passing through a road section cannot exceed the capacity of the road section, and the expression is as follows: obtaining population individuals of an intermediate population where f(·) denotes a fitness function.

6. The ramp closure control scheme optimization method of claim 5, wherein, Wherein, 0 represents a closed state, and 1 represents an open state. min{W x ,Z x |x∈X} s.t. G[x, W x , Z x ] ≤ 0 s.t.g[m b ,W x ,Z x ]≤0 wherein G[x, W x , Z x ]≤0 represents a first constraint condition, x represents a ramp control scheme, X represents an updated intermediate population, m b represents a traffic volume of the bth ramp in the target expressway, g[m b , W x , Z x ]≤0 represents a second constraint condition, W x represents total delay of a system road network, and Z x represents total delay of expressway main road intersections: wherein, T ab denotes the travel time between the a-th ramp and the b-th ramp, V ab denotes the traffic flow of the road segment between the a-th ramp and the b-th ramp, I denotes the number of ramps of the target expressway, C ab denotes the vehicle capacity of the road segment between the a-th ramp and the b-th ramp, S ab denotes other delay factors from the a-th ramp to the b-th ramp, a, b denote weight parameters, K denotes the number of intersections of the target expressway, d k denotes the delay factor of the k-th intersection, T wait,k denotes the waiting time of the k-th intersection, T stop,k denotes the stopping time of the k-th intersection, Q k denotes the queue length of the k-th intersection, a, b denote weight parameters; The first constraint condition G[x, W x ,Z x ]≤0 includes: The preset iteration termination condition in step 7 is a preset maximum number of iterations. Max queue length constraint: the queue length of any one flow direction in the intersection at any time cannot exceed the preset maximum queue length Q max The expression is: where Q k represents the queue length of any flow at the kth intersection; Green light duration constraint: the duration of green light should meet the demand of vehicles passing in each direction, while being limited by a preset minimum green light duration T green,min and a maximum green light duration T green,max , and the expression is: T green,min ≤T green ≤T green,max T green represents the green light duration; On-ramp switch constraint: Each on-ramp on the freeway has two states, i.e., open and closed, where x a is the switch state of the ath on-ramp, which can only be closed or open, and the expression is: x a ∈ {0,1}, a = 1,2,..., I The processor executes the computer program to realize the ramp closure control scheme optimization method according to any one of claims 1 to 7.

7. The ramp closure control scheme optimization method of claim 1, wherein, The computer program is executed by the processor to realize the ramp closure control scheme optimization method according to any one of claims 1 to 7.

8. A terminal device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The computer program is executed by the processor to realize the ramp closure control scheme optimization method according to any one of claims 1 to 7.

9. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 8. ​

Images