A maximum flow scheduling method and device for intelligent traffic flow scheduling

Abstract

The application discloses a maximum flow scheduling method and device for intelligent traffic flow scheduling, and the method comprises the following steps: constructing an intelligent traffic network directed graph; the intelligent traffic network directed graph comprises N network nodes and M directed edges, and N and M are positive integers; initializing the intelligent traffic network directed graph and the N network nodes to obtain initialized intelligent traffic network directed graph parameters and initialized network node parameters; processing the intelligent traffic network directed graph according to the initialized intelligent traffic network directed graph parameters and the initialized network node parameters to obtain a maximum flow scheduling result. The method can adapt to the intelligent traffic network environment, and can ensure the global optimality and synchronism of flow scheduling.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of traffic scheduling, in particular to a maximum traffic scheduling method and device for intelligent traffic scheduling. BACKGROUND

[0002] With the acceleration of urbanization and the rapid growth of the number of motor vehicles, the problem of urban traffic congestion is becoming increasingly serious. Traditional traffic flow scheduling methods, such as fixed-cycle signal control, are difficult to adapt to the dynamic changes in traffic flow. Although some existing traffic scheduling systems introduce inductive signal control, relying solely on a single vehicle detection device (such as a ground coil) to obtain traffic information, the data source is limited and cannot fully and accurately reflect the traffic situation. Moreover, these systems lack the ability to globally optimize traffic flow, and in the face of complex traffic scenarios, such as roads around large events or holiday traffic peaks, they are difficult to effectively alleviate traffic congestion, resulting in low vehicle traffic efficiency, increasing travel time and energy consumption, and causing adverse effects on the environment. SUMMARY

[0003] The technical problem to be solved by the present application is to provide a maximum traffic scheduling method and device for intelligent traffic scheduling, which realizes the optimal scheduling of traffic flow in the entire road network by constructing an intelligent traffic network directed graph, improves the utilization rate of road resources, alleviates traffic congestion, and improves the overall operation efficiency of urban traffic.

[0004] To solve the above technical problems, the first aspect of the embodiment of the present application discloses a maximum traffic scheduling method for intelligent traffic scheduling, which comprises:

[0005] S1, constructing an intelligent traffic network directed graph; the intelligent traffic network directed graph comprises N network nodes and M directed edges, and N and M are positive integers;

[0006] S2, initializing the intelligent traffic network directed graph and the N network nodes to obtain initialized intelligent traffic network directed graph parameters and initialized network node parameters;

[0007] S3, processing the intelligent traffic network directed graph according to the initialized intelligent traffic network directed graph parameters and the initialized network node parameters to obtain a maximum traffic scheduling result.

[0008] As an optional implementation, in the first aspect of the embodiment of the present application, the network node comprises an input layer, a receiving layer, a state layer, a generation layer and a sending layer;

[0009] The input layer is used for receiving input traffic data and sending the input data to the receiving layer;

[0010] The receiving layer is configured to receive the traffic information output by the input layer;

[0011] The state layer is configured to set traffic activation state information;

[0012] The generating layer is configured to receive the traffic information output by the receiving layer according to the traffic activation state information, and send the traffic information to the sending layer;

[0013] The sending layer is configured to send the traffic information output by the sending layer to other network nodes.

[0014] As an optional implementation, in the first aspect of the embodiment of the present application, the constructing the directed graph of the intelligent transportation network comprises:

[0015] S11, obtaining node structure information of a target intelligent transportation network;

[0016] S12, processing the node structure information of the target intelligent transportation network to obtain a node cluster of the intelligent transportation network;

[0017] The node cluster of the intelligent transportation network comprises N network nodes;

[0018] S13, processing the node cluster of the intelligent transportation network to obtain a directed graph of the intelligent transportation network.

[0019] As an optional implementation, in the first aspect of the embodiment of the present application, the initializing the directed graph of the intelligent transportation network and the N network nodes to obtain initialized directed graph parameters of the intelligent transportation network and initialized network node parameters comprises:

[0020] S21, initializing a timer time parameter of the intelligent transportation network;

[0021] S22, initializing an iteration step length of the intelligent transportation network;

[0022] S23, initializing attribute information of the intelligent transportation network;

[0023] S24, initializing each network node to obtain initialized network node parameters; the initialized network node parameters comprise a number of predecessor nodes, a number of successor nodes and a number of target nodes;

[0024] S25, integrating the timer time parameter, the iteration step length and the attribute information to obtain initialized directed graph parameters of the intelligent transportation network.

[0025] As an optional implementation, in the first aspect of the present invention, the step of processing the directed graph of the intelligent transportation network according to the initialized directed graph parameters and initialized network node parameters to obtain the maximum traffic scheduling result includes:

[0026] S31, Update the state of the network nodes of the intelligent transportation network to obtain the state update information of the network nodes;

[0027] S32, Based on the state update information, the intelligent transportation network is processed to obtain the traffic flow constraint equation;

[0028] S33, Solve the traffic flow constraint equation to obtain the maximum flow scheduling result.

[0029] As an optional implementation, in the first aspect of the present invention, updating the state of the network nodes of the intelligent transportation network to obtain the state update information of the network nodes includes:

[0030] S311: For any network node, traverse all its predecessor nodes and query whether there is traffic arriving at the current node at the current time. If there is traffic, receive the traffic through the input layer and the receiving layer and record it in the network node state layer.

[0031] S312, when the state layer of network node k detects that the traffic sent at time t satisfies the activation state... At that time, the generation layer of network node k generates new traffic. and the flow The data is transmitted from network node k to the successor node next. i This allows us to obtain the status update information of network nodes.

[0032] As an optional implementation, in the first aspect of the present invention, solving the traffic flow constraint equation to obtain the maximum flow scheduling result includes:

[0033] S331, The traffic flow constraint equation is processed to obtain an optimized traffic flow constraint equation; the expression of the optimized traffic flow constraint equation is:

[0034] max f

[0035] st(e n -e1)f+Ax=0,

[0036] 0≤x≤u T

[0037] Where x = (x1, x2, ..., x m ) T ∈Rm×1 It represents the flow rate of each arc in the directed graph of the intelligent transportation network, subject to the flow rate limit u. T =(u1,u2,…,u m ) T ∈R m×1 Restrictions, Let x m+1 =f, A is the active state. The matrix formed, e n =(0,0,0,…,1) T e1 = (1, 0, 0, ..., 0) T ∈R m R m×1 Let m be the set of real numbers;

[0038] S332, Solve the optimized traffic flow constraint equation to obtain the maximum flow scheduling result.

[0039] A second aspect of this invention discloses a maximum flow scheduling device for intelligent traffic flow scheduling, the device comprising:

[0040] A network construction module is used to construct a directed graph of an intelligent transportation network; the directed graph of the intelligent transportation network includes N network nodes and M directed edges, where N and M are positive integers;

[0041] An initialization module is used to initialize the directed graph of the intelligent transportation network and N network nodes, and obtain the initialization parameters of the directed graph of the intelligent transportation network and the initialization parameters of the network nodes.

[0042] The traffic scheduling module is used to process the directed graph of the intelligent transportation network according to the initialization parameters of the directed graph and the initialization parameters of the network nodes to obtain the maximum traffic scheduling result.

[0043] As an optional implementation, in a second aspect of the present invention, the network node includes an input layer, a receiving layer, a state layer, a generating layer, and a transmitting layer;

[0044] The input layer is used to receive input traffic data and send the input data to the receiving layer;

[0045] The receiving layer is used to receive the traffic information output by the input layer;

[0046] The state layer is used to set traffic activation status information;

[0047] The generation layer is used to receive the traffic information output by the receiving layer according to the traffic activation status information, and send the traffic information to the sending layer;

[0048] The sending layer is used to send the traffic information output by the sending layer to other network nodes.

[0049] As an optional implementation, in the second aspect of the present invention, the construction of the directed graph of the intelligent transportation network includes:

[0050] S11, Obtain the node structure information of the target intelligent transportation network;

[0051] S12, Process the node structure information of the target intelligent transportation network to obtain the node cluster of the intelligent transportation network;

[0052] The node cluster of the intelligent transportation network includes N network nodes;

[0053] S13, process the node cluster of the intelligent transportation network to obtain a directed graph of the intelligent transportation network.

[0054] As an optional implementation, in the second aspect of the present invention, the initialization of the directed graph of the intelligent transportation network and N network nodes to obtain the initialized directed graph parameters and initialized network node parameters includes:

[0055] S21, Initialize the timer parameters of the intelligent transportation network;

[0056] S22, Initialize the iteration step size of the intelligent transportation network;

[0057] S23, Initialize the attribute information of the intelligent transportation network;

[0058] S24, initialize each network node to obtain initialized network node parameters; the initialized network node parameters include the number of predecessor nodes, the number of successor nodes and the number of target nodes.

[0059] S25, integrate the timer time parameters, the iteration step size and the attribute information to obtain the initial directed graph parameters of the intelligent transportation network.

[0060] As an optional implementation, in the second aspect of the present invention, the step of processing the directed graph of the intelligent transportation network according to the initialized directed graph parameters and initialized network node parameters to obtain the maximum traffic scheduling result includes:

[0061] S31, Update the state of the network nodes of the intelligent transportation network to obtain the state update information of the network nodes;

[0062] S32, Based on the state update information, the intelligent transportation network is processed to obtain the traffic flow constraint equation;

[0063] S33, Solve the traffic flow constraint equation to obtain the maximum flow scheduling result.

[0064] As an optional implementation, in the second aspect of the present invention, updating the state of the network nodes of the intelligent transportation network to obtain network node state update information includes:

[0065] S311: For any network node, traverse all its predecessor nodes and query whether there is traffic arriving at the current node at the current time. If there is traffic, receive the traffic through the input layer and the receiving layer and record it in the network node state layer.

[0066] S312, when the state layer of network node k detects that the traffic sent at time t satisfies the activation state... At that time, the generation layer of network node k generates new traffic. and the flow The data is transmitted from network node k to the successor node next. i This allows us to obtain the status update information of network nodes.

[0067] As an optional implementation, in the second aspect of the present invention, solving the traffic flow constraint equation to obtain the maximum flow scheduling result includes:

[0068] S331, The traffic flow constraint equation is processed to obtain an optimized traffic flow constraint equation; the expression of the optimized traffic flow constraint equation is:

[0069] max f

[0070] st(e n -e1)f+Ax=0,

[0071] 0≤x≤u T

[0072] Where x = (x1, x2, ..., x m ) T ∈R m×1 It represents the flow rate of each arc in the directed graph of the intelligent transportation network, subject to the flow rate limit u. T =(u1,u2,…,u m ) T ∈R m×1 Restrictions, Let x m+1 =f, A is the active state. The matrix formed, e n =(0,0,0,…,1) T e1 = (1, 0, 0, ..., 0) T ∈Rm R m×1 Let m be the set of real numbers;

[0073] S332, Solve the optimized traffic flow constraint equation to obtain the maximum flow scheduling result.

[0074] A third aspect of the present invention discloses another maximum flow scheduling device for intelligent traffic flow scheduling, the device comprising:

[0075] Memory containing executable program code;

[0076] A processor coupled to the memory;

[0077] The processor calls the executable program code stored in the memory to execute some or all of the steps in the maximum flow scheduling method for intelligent traffic flow scheduling disclosed in the first aspect of the present invention.

[0078] The fourth aspect of the present invention discloses a computer-storeable medium storing computer instructions, which, when invoked, are used to execute some or all of the steps in the maximum flow scheduling method for intelligent traffic flow scheduling disclosed in the first aspect of the present invention.

[0079] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0080] This invention discloses a maximum flow scheduling method for intelligent traffic flow management. This method constructs a directed graph of an intelligent transportation network; based on the initialized parameters of the directed graph and the initialized network node parameters, it processes the directed graph to obtain the maximum flow scheduling result. This method is adaptive to the intelligent transportation network environment while ensuring the global optimality and synchronization of flow scheduling. Attached Figure Description

[0081] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0082] Figure 1 This is a flowchart illustrating a maximum flow scheduling method for intelligent traffic flow scheduling disclosed in an embodiment of the present invention.

[0083] Figure 2 This is a schematic diagram of the structure of a maximum flow scheduling device for intelligent traffic flow scheduling disclosed in an embodiment of the present invention;

[0084] Figure 3 This is a schematic diagram of another maximum flow scheduling device for intelligent traffic flow scheduling disclosed in an embodiment of the present invention. Detailed Implementation

[0085] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0086] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0087] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0088] This invention discloses a maximum flow scheduling method and apparatus for intelligent traffic flow scheduling. The method includes: constructing a directed graph of an intelligent traffic network; the directed graph of the intelligent traffic network includes N network nodes and M directed edges, where N and M are positive integers; initializing the directed graph of the intelligent traffic network and the N network nodes to obtain initialized intelligent traffic network directed graph parameters and initialized network node parameters; processing the directed graph of the intelligent traffic network according to the initialized intelligent traffic network directed graph parameters and initialized network node parameters to obtain the maximum flow scheduling result. This invention's method can adapt to the intelligent traffic network environment while ensuring the global optimality and synchronization of flow scheduling. Detailed explanations follow.

[0089] Example 1

[0090] Please see Figure 1 , Figure 1This is a flowchart illustrating a maximum flow scheduling method for intelligent traffic flow scheduling disclosed in an embodiment of the present invention. Figure 1 The maximum flow scheduling method for intelligent traffic flow scheduling described herein is applied in the field of traffic flow scheduling technology, and the embodiments of this invention are not limited thereto. Figure 1 As shown, the maximum flow scheduling method for intelligent traffic flow scheduling may include the following operations:

[0091] S1, Construct a directed graph of the intelligent transportation network; the directed graph of the intelligent transportation network includes N network nodes and M directed edges, where N and M are positive integers;

[0092] S2, Initialize the directed graph of the intelligent transportation network and N network nodes to obtain the initial intelligent transportation network directed graph parameters and the initial network node parameters;

[0093] S3. Based on the initialized directed graph parameters of the intelligent transportation network and the initialized network node parameters, the directed graph of the intelligent transportation network is processed to obtain the maximum traffic scheduling result.

[0094] Optionally, the network node includes an input layer, a receiving layer, a state layer, a generating layer, and a transmitting layer;

[0095] The input layer is used to receive input traffic data and send the input data to the receiving layer;

[0096] The receiving layer is used to receive the traffic information output by the input layer;

[0097] The state layer is used to set traffic activation status information;

[0098] The generation layer is used to receive the traffic information output by the receiving layer according to the traffic activation status information, and send the traffic information to the sending layer;

[0099] The sending layer is used to send the traffic information output by the sending layer to other network nodes.

[0100] Optionally, the construction of the directed graph of the intelligent transportation network includes:

[0101] S11, Obtain the node structure information of the target intelligent transportation network;

[0102] S12, Process the node structure information of the target intelligent transportation network to obtain the node cluster of the intelligent transportation network;

[0103] The node cluster of the intelligent transportation network includes N network nodes;

[0104] S13, process the node cluster of the intelligent transportation network to obtain a directed graph of the intelligent transportation network, including:

[0105] (1) During the initialization phase, the network completes the establishment of its hierarchical structure, calculates its neighbor nodes based on the neighbor election radius, and stores them in a neighbor list s. i .cn; at the same time, it calculates its own average minimum reachable power value and broadcasts it to its neighboring nodes.

[0106] (2) Iteration begins with each surviving node s i First, calculate the cluster head parameter CH. prob Then check the neighbor list. i Does the .cn node contain a temporary cluster head node? If so, perform the following checks: If it is a temporary cluster head, set itself as its cluster head, and the iteration ends; if it is not a temporary cluster head, select the node with the smallest average minimum reachable power from the set of temporary cluster heads as its temporary cluster head, and the iteration ends; otherwise, check if node s is a temporary cluster head. i According to the random number T r Become a temporary cluster head (when random number T) r ≤CH prob When the iteration ends, proceed to the next iteration.

[0107] (3) Update the CH of the node at the end of each iteration. prob , let CH prob =CH prob *2.

[0108] The significance of updating: It allows the iteration to end within a fixed number of iterations; nodes with high remaining energy require fewer iterations and have a higher probability of being selected as cluster heads; the algorithm performs N iterations. iter The next iteration ensures that the cluster heads are evenly distributed throughout the entire coverage area.

[0109] (4) After the second phase of iterative election of candidate temporary cluster heads, clusters are established. If a node is a temporary cluster head: check its neighbor list. If there is no neighbor with an average minimum reachable power value smaller than its own, it declares itself as the final initial cluster head. If a node is a regular node: join the cluster head with the smallest average minimum reachable power value in the neighbor list.

[0110] (5) All initial cluster heads broadcast their position, number of members and remaining energy within a two-hop range. "Isolated clusters" with fewer than the threshold of members join the cluster head with the most remaining energy within a two-hop range and become a fused cluster head.

[0111] (6) After steps (1) to (5), at T cpDivide the network into several clusters over a time period, and select m cluster head nodes from N nodes, which can completely cover the entire network. Each node s i For each ∈S, 1≤i≤N, it can be controlled by a cluster head c. j c j ∈C, 1≤j≤m cover, S is the set of nodes, and C is the set of cluster heads.

[0112] Optionally, the initialization of the directed graph of the intelligent transportation network and N network nodes to obtain the initialized directed graph parameters and initialized network node parameters includes:

[0113] S21, Initialize the timer parameters of the intelligent transportation network;

[0114] S22, Initialize the iteration step size of the intelligent transportation network;

[0115] S23, Initialize the attribute information of the intelligent transportation network;

[0116] S24, initialize each network node to obtain initialized network node parameters; the initialized network node parameters include the number of predecessor nodes, the number of successor nodes and the number of target nodes.

[0117] S25, integrate the timer time parameters, the iteration step size and the attribute information to obtain the initial directed graph parameters of the intelligent transportation network.

[0118] Optionally, the step of processing the directed graph of the intelligent transportation network based on the initialized directed graph parameters and initialized network node parameters to obtain the maximum traffic scheduling result includes:

[0119] S31, Update the state of the network nodes of the intelligent transportation network to obtain the state update information of the network nodes;

[0120] S32, Based on the state update information, the intelligent transportation network is processed to obtain the traffic flow constraint equation;

[0121] S33, Solve the traffic flow constraint equation to obtain the maximum flow scheduling result.

[0122] Optionally, updating the state of the network nodes in the intelligent transportation network to obtain network node state update information includes:

[0123] S311: For any network node, traverse all its predecessor nodes and query whether there is traffic arriving at the current node at the current time. If there is traffic, receive the traffic through the input layer and the receiving layer and record it in the network node state layer.

[0124] S312, when the state layer of network node k detects that the traffic sent at time t satisfies the activation state... At that time, the generation layer of network node k generates new traffic. and the flow The data is transmitted from network node k to the successor node next. i This allows us to obtain the status update information of network nodes.

[0125] Optionally, solving the traffic flow constraint equation to obtain the maximum flow scheduling result includes:

[0126] S331, The traffic flow constraint equation is processed to obtain an optimized traffic flow constraint equation; the expression of the optimized traffic flow constraint equation is:

[0127] max f

[0128] st(e n -e1)f+Ax=0,

[0129] 0≤x≤u T

[0130] Where x = (x1, x2, ..., x m ) T ∈R m×1 It represents the flow rate of each arc in the directed graph of the intelligent transportation network, subject to the flow rate limit u. T =(u1,u2,…,u m ) T ∈R m×1 Restrictions, Let x m+1 =f, A is the active state. The matrix formed, e n =(0,0,0,…,1) T e1 = (1, 0, 0, ..., 0) T ∈R m R m×1 Let m be the set of real numbers;

[0131] S332, Solve the optimized traffic flow constraint equation to obtain the maximum flow scheduling result, including:

[0132] Let X = (x1, x2, ..., x m ,x m+1 ) T ∈R (m+1)×1 , Let q = (-1, 0, 0, ..., 1) T ∈R n×1If B = [A|q], then BX = (e n -e1)x m+1 +Ax, let c = (0,0,…,1) T ∈R (m+1)×1 So c T X = f, therefore:

[0133] maxc T X

[0134] stBX = 0,

[0135] 0≤X≤U T

[0136] The expression for the first traffic scheduling equation is:

[0137] L(X,y,h)=c T X+y T (BX)+h T (XU T )

[0138] S732, process the first flow scheduling equation to obtain the second flow scheduling equation;

[0139] The expression for the second flow scheduling equation is:

[0140] (-c T +B T y+h)X=0, -BX=0

[0141] -c T +B T y+h≥0,-(XU T )≥0

[0142] -h T (xU T If y ≥ 0, then X, h ≥ 0, and y is free.

[0143] S733, Solve the second flow scheduling equation to obtain the maximum flow scheduling result, including:

[0144] set up

[0145]

[0146] Equivalent to:

[0147]

[0148] When F(w) = 0, X in w represents the optimal flow on each edge.

[0149] Introducing projection in That is when In time *w*, *X* represents the optimal flow along each edge. This is because when *F(w)* = 0, At the same time, it is guaranteed that the first 2(m+1) terms in w are non-negative.

[0150] Introducing a dynamic model for solution

[0151]

[0152] Where 0 < λ ≤ 1,

[0153]

[0154] Convergence occurs when the error e(w,β) = 0 or approaches 0 infinitely. At this point, X in w represents the optimal flow along each edge, and the maximum flow is x in X. m+1 .

[0155] As can be seen, this invention discloses a maximum flow scheduling method for intelligent traffic flow management. This method constructs a directed graph of an intelligent transportation network; based on the initialized parameters of the directed graph and the initialized network node parameters, it processes the directed graph to obtain the maximum flow scheduling result. This invention's method can adapt to the intelligent transportation network environment while ensuring the global optimality and synchronization of flow scheduling.

[0156] Example 2

[0157] This embodiment presents a maximum flow scheduling method for intelligent traffic flow management. The travel time functions of each edge in the network are shown in Table 1. The specific implementation plan includes the following contents and steps:

[0158] Table 1. Travel time functions of each edge in the network.

[0159]

[0160] Step 1: Design the nodes, where each node consists of five parts: stream input layer, stream receiving layer, state layer, stream generation layer, and stream sending layer.

[0161] Step 2: Construct a directed graph of the intelligent transportation network and initialize various parameters. The specific steps are as follows:

[0162] Step 2.1: Initialize the nodes in the directed graph of the intelligent transportation network;

[0163] Step 2.2: Construct a directed graph model of the intelligent transportation network based on the topology of the directed graph of the intelligent transportation network. The model consists of four time-dependent nodes and four edges, and sets the starting node a and the target node d.

[0164] Step 3: Initialize all parameters. The specific steps are as follows:

[0165] Step 3.1: Initialize the timer T = 0 for the directed graph of the intelligent transportation network;

[0166] Step 3.2: Initialize the iteration step size Δt = 1 for the directed graph of the intelligent transportation network;

[0167] Step 3.3: Initialize the properties of the directed graph of the intelligent transportation network. and And initialize the predecessor node of each node. i and successor node next i target node next i ;

[0168] Step 4: Update the state of all nodes. The specific steps are as follows:

[0169] Step 4.1, when T=0, the starting node a moves to its successor node next. a Send traffic.

[0170] Step 4.2, for node b, calculate For node c, calculate For node d, calculate

[0171] Step 4.3: The target node d does not meet the condition, so let T + Δt = 1.

[0172] Step 4.4: For node b, calculate Node b sends traffic to its successor node c; for node c, calculate... Node c does not send traffic to its successor node c; for node d, the calculation...

[0173] Step 4.5: The target node d does not meet the condition, so let T + Δt = 2.

[0174] Step 4.6: For node b, calculate For node c, calculate Node c sends traffic to its successor node d; for node d, calculate...

[0175] Step 4.7: The target node d does not meet the condition, so let T + Δt = 3.

[0176] Step 4.8, for node b, calculate For node c, calculate Node c sends traffic to its successor node d; for node d, calculate... R d =pre d ;

[0177] Step 4.9, Determine R d =pre d If the conditions are met, generate the constraint u. 0

[0178] Step 5: Construct the traffic flow constraint equations. The specific steps are as follows:

[0179] Step 5.1: Matrix A is a node-arc matrix, where each row represents a node in the graph and each column represents an arc. The topological relationship is converted into a 4×4 node-arc matrix A as follows:

[0180]

[0181] Then, we construct the traffic flow constraint equation:

[0182] max f

[0183] stA T x = d,

[0184] 0≤x≤u T

[0185] Where x = (x ab ,x ac ,x bc ,x cd ) T ∈R 4×1 This represents the flow rate of each arc in the diagram, subject to the flow rate limit u. T =(u ab ,u ac ,u bc ,u cd ) T =(3,1,2,3) T ∈R 4×1 Restrictions.

[0186] Step 5.2: Problem transformation, constructing new traffic flow constraint equations.

[0187] Let e4 = (0,0,0,1) T e1 = (1,0,0,0) T ∈R 4 Then (e4-e1)f = -d. The equation is equivalent to:

[0188] max f

[0189] st(e4-e1)f+Ax=0,

[0190] 0≤x≤u 0

[0191] in, Let x5 = f, Therefore, the equation is equivalent to:

[0192] max f

[0193] st(e4-e1)x5+Ax=0,

[0194]

[0195] Let X = (x1, x2, x3, x4, x5) T ∈R 5×1 U 0 =(3,1,2,3,9) T ∈R 5×1

[0196] Let q = (-1, 0, 0, 1) T ∈R 4×1 Let B = [A|q],

[0197] So

[0198]

[0199] Then BX = (e4 - e1)x5 + Ax

[0200] Let c = (0,0,0,0,1) T ∈R 5×1 So c T X = f

[0201] Therefore, the equation is equivalent to

[0202]

[0203] stBX = 0,

[0204] 0≤X≤U 0

[0205] Step 5.3: Construct constraint equations:

[0206]

[0207] Therefore, the following constraints can be obtained:

[0208] (-c T +B T y+h)X=0, -BX=0

[0209] -cT +B T y+h≥0,-(XU 0 )≥0

[0210] -h T (XU 0 If y ≥ 0, then X, h ≥ 0, and y is free.

[0211] Step 5.4: Solve for the constraints.

[0212] set up

[0213]

[0214] Equivalent to:

[0215]

[0216]

[0217] When F(w) = 0, X in w represents the optimal flow on each edge.

[0218] Introducing projection in That is when In time *w*, *X* represents the optimal flow along each edge. This is because when *F(w)* = 0, At the same time, it is guaranteed that the first 2(m+1) terms in w are non-negative.

[0219]

[0220] Where 0 < λ ≤ 1,

[0221]

[0222] From the above formula, we can know

[0223]

[0224]

[0225] When the error e(w,β) approaches 0, the optimal solution can be obtained, resulting in X = (x ab ,x ac ,x bc ,x cd (x5) T =(2,1,2,3,3) T The flow of each side is shown by the first m terms, and the time-varying maximum flow scheduling to the target node d is finally obtained as 3.

[0226] As can be seen, this invention discloses a maximum flow scheduling method for intelligent traffic flow management. This method constructs a directed graph of an intelligent transportation network; based on the initialized parameters of the directed graph and the initialized network node parameters, it processes the directed graph to obtain the maximum flow scheduling result. This invention's method can adapt to the intelligent transportation network environment while ensuring the global optimality and synchronization of flow scheduling.

[0227] Example 3

[0228] Please see Figure 2 , Figure 2 This is a schematic diagram of a maximum flow scheduling device for intelligent traffic flow scheduling disclosed in an embodiment of the present invention. Figure 2 The described maximum flow scheduling device for intelligent traffic flow scheduling is applied in the field of flow scheduling technology, and the embodiments of the present invention are not limited thereto. Figure 2 As shown, the maximum flow scheduling device for intelligent traffic flow scheduling may include the following operations:

[0229] S301, Network Construction Module, used to construct a directed graph of an intelligent transportation network; the directed graph of the intelligent transportation network includes N network nodes and M directed edges, where N and M are positive integers;

[0230] S302, Initialization module, used to initialize the directed graph of the intelligent transportation network and N network nodes, and obtain the initialization parameters of the directed graph of the intelligent transportation network and the initialization parameters of the network nodes;

[0231] S303, Traffic scheduling module, is used to process the directed graph of the intelligent transportation network according to the initialized directed graph parameters and initialized network node parameters to obtain the maximum traffic scheduling result.

[0232] Example 4

[0233] Please see Figure 3 , Figure 3 This is a schematic diagram of a maximum flow scheduling device for intelligent traffic flow scheduling disclosed in an embodiment of the present invention. Figure 3 The described maximum flow scheduling device for intelligent traffic flow scheduling is applied in the field of flow scheduling technology, and the embodiments of the present invention are not limited thereto. Figure 3 As shown, the maximum flow scheduling device for intelligent traffic flow scheduling may include the following operations:

[0234] Memory 401 storing executable program code;

[0235] Processor 402 coupled to memory 401;

[0236] The processor 402 calls the executable program code stored in the memory 401 to execute the steps in the maximum flow scheduling method for intelligent traffic flow scheduling described in Embodiment 1 and Embodiment 2.

[0237] Example 5

[0238] This invention discloses a computer-readable storage medium storing a computer program for electronic data interchange, wherein the computer program enables a computer to perform the steps of the maximum flow scheduling method for intelligent traffic flow scheduling described in Embodiments 1 and 2.

[0239] The device embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0240] Through the detailed description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, including read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-Erasable Programmable Read-Only Memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0241] Finally, it should be noted that the maximum flow scheduling method and apparatus for intelligent traffic flow scheduling disclosed in the embodiments of the present invention are merely preferred embodiments of the present invention, and are only used to illustrate the technical solutions of the present invention, not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A maximum flow scheduling method for intelligent traffic flow scheduling, characterized in that, The method includes: S1, Construct a directed graph of the intelligent transportation network; the directed graph of the intelligent transportation network includes N network nodes and M directed edges, where N and M are positive integers; S2, initialize the directed graph of the intelligent transportation network and N network nodes to obtain the initialized directed graph parameters and initialized network node parameters, including: S21, Initialize the timer parameters of the intelligent transportation network; S22, Initialize the iteration step size of the intelligent transportation network; S23, Initialize the attribute information of the intelligent transportation network; S24, initialize each network node to obtain initialized network node parameters; the initialized network node parameters include the number of predecessor nodes, the number of successor nodes and the number of target nodes. S25, integrate the timer time parameters, the iteration step size and the attribute information to obtain the initialization intelligent transportation network directed graph parameters; S3, based on the initialized directed graph parameters of the intelligent transportation network and the initialized network node parameters, process the directed graph of the intelligent transportation network to obtain the maximum traffic scheduling result, including: S31, update the state of the network nodes of the intelligent transportation network to obtain the state update information of the network nodes, including: S311: For any network node, traverse all its predecessor nodes and query whether there is traffic arriving at the current node at the current time. If there is traffic, receive the traffic through the input layer and the receiving layer and record it in the network node state layer. S312, when the state layer of network node k detects that the traffic sent at time t satisfies the activation state... At that time, the generation layer of network node k generates new traffic. and the flow The data is transmitted from network node k to the successor node next. i This allows us to obtain the status update information of network nodes. S32, Based on the state update information, the intelligent transportation network is processed to obtain the traffic flow constraint equation; S33, Solve the traffic flow constraint equation to obtain the maximum flow scheduling result, including: S331, The traffic flow constraint equation is processed to obtain the optimized traffic flow constraint equation; The expression for the optimized traffic flow constraint equation is as follows: max f s.t.(e n -e1)f+Ax=0, 0≤x≤u T Where x = (x1, x2, ..., x m ) T ∈R m×1 It represents the flow rate of each arc in the directed graph of the intelligent transportation network, subject to the flow rate limit u. T =(u1,u2,…,u m ) T ∈R m×1 Restrictions, Let x m+1 =f, A is the active state. The matrix formed, e n =(0,0,0,…,1) T e1 = (1, 0, 0, ..., 0) T ∈R m R m×1 Let m be the set of real numbers; S332, Solve the optimized traffic flow constraint equation to obtain the maximum flow scheduling result.

2. The maximum flow scheduling method for intelligent traffic flow scheduling according to claim 1, characterized in that, The network node includes an input layer, a receiving layer, a state layer, a generating layer, and a sending layer; The input layer is used to receive input traffic data and send the input traffic data to the receiving layer; The receiving layer is used to receive the traffic information output by the input layer; The state layer is used to set traffic activation status information; The generation layer is used to receive the traffic information output by the receiving layer according to the traffic activation status information, and send the traffic information to the sending layer; The sending layer is used to send the traffic information output by the sending layer to other network nodes.

3. The maximum flow scheduling method for intelligent traffic flow scheduling according to claim 1, characterized in that, The construction of the directed graph of the intelligent transportation network includes: S11, Obtain the node structure information of the target intelligent transportation network; S12, Process the node structure information of the target intelligent transportation network to obtain the node cluster of the intelligent transportation network; The node cluster of the intelligent transportation network includes N network nodes; S13, process the node cluster of the intelligent transportation network to obtain a directed graph of the intelligent transportation network.

4. A maximum flow scheduling device for intelligent traffic flow scheduling, applied to the maximum flow scheduling method for intelligent traffic flow scheduling according to any one of claims 1 to 3, characterized in that, The device includes: A network construction module is used to construct a directed graph of an intelligent transportation network; the directed graph of the intelligent transportation network includes N network nodes and M directed edges, where N and M are positive integers; An initialization module is used to initialize the directed graph of the intelligent transportation network and N network nodes, and obtain the initialization parameters of the directed graph of the intelligent transportation network and the initialization parameters of the network nodes. The traffic scheduling module is used to process the directed graph of the intelligent transportation network according to the initialization parameters of the directed graph and the initialization parameters of the network nodes to obtain the maximum traffic scheduling result.

5. A maximum flow scheduling device for intelligent traffic flow scheduling, characterized in that, The device includes: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the maximum flow scheduling method for intelligent traffic flow scheduling as described in any one of claims 1-3.

6. A computer-storable medium, characterized in that, The computer storage medium stores computer instructions, which, when invoked, are used to execute the maximum flow scheduling method for intelligent traffic flow scheduling as described in any one of claims 1-3.

Images