A method and system for intelligent dynamic planning of emergency communication networks

Abstract

This invention discloses an intelligent dynamic planning method and system for emergency communication networks, relating to the field of network communication technology. The invention first constructs an emergency communication network, then collects basic link data, constructs a calculation model for load update values ​​and load identification values ​​based on the basic data, and calculates load statistics. Based on the load update values, load statistics, and load identification values, link evaluation results are calculated, and corresponding dynamic planning is performed. The system is used to implement the above method. This invention monitors link status in real time and constructs a highly real-time evaluation mechanism based on load update values, load statistics, and load identification values, comprehensively and in real-time reflecting the actual load situation of the network.

Description

Technical Field

[0001] This invention relates to the field of network communication technology, and in particular to an intelligent dynamic planning method and system for emergency communication networks. Background Technology

[0002] Natural disasters are characterized by their suddenness in time, urgency in disaster relief, randomness in location, and unpredictability in their development. Therefore, it is necessary to build a flexible, efficient, and agile emergency communication system to ensure the smooth progress of subsequent comprehensive rescue work.

[0003] Currently, while existing emergency communication networks employ intelligent dynamic programming methods to improve network robustness and response speed to some extent, some technical shortcomings still exist in practical applications. Existing intelligent dynamic programming methods typically adjust network configuration through the analysis of historical and real-time data, but their main drawbacks are:

[0004] While existing methods can make some dynamic adjustments based on network conditions, the lack of a highly real-time evaluation mechanism leads to a lag in the adjustment process, making it unable to respond promptly to sudden network traffic surges or failures. Existing dynamic programming methods often rely on relatively coarse indicators when evaluating network conditions, failing to comprehensively and accurately reflect the true network load, thus affecting the accuracy of dynamic programming. The inability to accurately predict and evaluate network load results in inefficient resource allocation, particularly in emergency communication scenarios, where resource waste is significant. Summary of the Invention

[0005] In view of this, the present invention proposes an intelligent dynamic planning method and system for emergency communication networks. The present invention comprehensively and in real-time reflects the actual load situation of the network by monitoring link status in real time and constructing a highly real-time evaluation mechanism based on load update values, load statistics, and load identification values.

[0006] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0007] An intelligent dynamic planning method for emergency communication networks includes the following steps:

[0008] Step 1: Construct an emergency communication network;

[0009] Step 2: Use network devices to monitor the link status of the emergency communication network in real time and collect basic link data, including throughput, packet loss rate and latency.

[0010] Step 3: Construct a training sample set. Each training sample in the training sample set includes a current time-based basic data X(t) and a historical basic data Y(t). Here, X(t) is a 3x1 column vector, including the throughput, packet loss rate, and latency of the corresponding link at time t; Y(t) is a 3x1 column vector, including the average throughput, packet loss rate, and latency of the corresponding link during the duration Time before time t.

[0011] Step 4: Construct a calculation model for load update value and load identification value using deep learning. The input to the calculation model is the basic data X(t) of the link at time t and the corresponding historical basic data Y(t). The output of the calculation model is the load update value and load identification value of the link at time t.

[0012] Step 5: Sum the three elements in the historical basic data Y(t) and record it as the load statistics of the link at time t. Combine the load update value and load identification value of the link at time t to calculate the evaluation result L of the link at time t. t ;

[0013] Step 6, evaluate the link at time t, L t The network is compared with the preset network normal state threshold T and network warning state threshold F, where T is less than F; based on the comparison result, corresponding dynamic planning is performed to complete the intelligent dynamic planning of the emergency communication network.

[0014] Furthermore, the specific method for constructing the calculation model of the load update value and the load identification value using deep learning in step 4 is as follows:

[0015] Step 401: For input samples X(t) and Y(t), calculate the corresponding load update values.

[0016]

[0017] Among them, B m The maximum throughput of the link is given by TR(), where TR() represents the trace of the computation matrix, W is the first updated weight matrix (a 3x3 matrix), V is the second updated weight matrix (a 3x3 matrix), and the superscript T indicates transpose.

[0018] Step 402: For the input sample X(t), calculate the corresponding load identification value.

[0019]

[0020] Where q is the first recognition weight vector, and q is a 3x1 column vector; denoted as the nonlinear transformation function; p is the second recognition weight vector, p is a 3x1 column vector; b is the adjustment term, b is a constant;

[0021] Step 403: Calculate the corresponding loss value.

[0022]

[0023] in, This represents the true value of the link load update at time t. The value is the sum of the three elements in the column vector X(t)-X(t-1); This represents the true value of the load identification value of the link at time t. The value is the link status value at time t, which is manually marked based on the link's normal, overloaded, or underloaded states.

[0024] Step 404, based on the loss value Backpropagation using gradient descent is performed to update the first updated weight matrix, the second updated weight matrix, the first identification weight vector, and the second identification weight vector until the loss value is reached. Converge; save the parameters of the first updated weight matrix, the second updated weight matrix, the first identification weight vector, and the second identification weight vector; complete the construction of the calculation model for the load update value and the load identification value.

[0025] Furthermore, in step 5, the evaluation result L of the link at time t is calculated. t The specific methods are as follows:

[0026]

[0027] in, Let μ1, μ2, and μ3 be the load statistics of the link at time t, and let μ1, μ2, and μ3 be the adjustment coefficients of the load update value, load statistics value, and load identification value, respectively. μ1, μ2, and μ3 are all positive numbers, and μ1 + μ2 + μ3 = 1.

[0028] Furthermore, the specific method for performing the corresponding dynamic programming based on the comparison results in step 6 is as follows:

[0029] If L t If T < T, then it is the normal state, and the corresponding dynamic programming is:

[0030] Resource optimization: Maintain the current resource allocation and continue to monitor the link status of the emergency communication network;

[0031] Precautions: Maintain existing precautions and continue to regularly check the link status of the emergency communication network;

[0032] If T≤L tIf F, then it is a warning state, and the corresponding dynamic programming is as follows:

[0033] Resource adjustment: Dynamically adjust bandwidth allocation, optimize traffic distribution, and avoid overload;

[0034] Add redundancy: Add redundant connections to critical nodes to improve the robustness of the emergency communication network;

[0035] Prevention measures: Strengthen monitoring, and promptly detect and handle potential fault points;

[0036] If F ≤ L t , then it is an abnormal state, and the corresponding dynamic programming is as follows:

[0037] Emergency adjustment: Immediately adjust the network configuration, such as adding temporary base stations, adjusting frequency allocation, and optimizing route selection;

[0038] Resource reallocation: Reasonably allocate bandwidth and other resources to avoid overload of certain nodes;

[0039] Fault recovery: Quickly locate the fault point and take measures to restore the emergency communication network service;

[0040] Emergency response: Set different quality of service (QoS) standards according to the emergency level and service type to ensure priority for critical communications.

[0041] An intelligent dynamic programming system for an emergency communication network is used to execute an intelligent dynamic programming method for an emergency communication network described in any one of the above, and specifically includes a construction module, a collection module, an evaluation module, and a dynamic programming module;

[0042] The construction module is used to construct an emergency communication network;

[0043] The collection module is connected to the construction module and is used to use network devices to monitor the link status of the emergency communication network in real time and collect the basic data of the links;

[0044] The evaluation module is connected to the collection module. The evaluation module specifically includes a training layer and an application layer. The training layer is used to construct a calculation model for load update values and load identification values based on the basic data of the collected links, and the application layer is used to calculate the evaluation result L of the link according to the basic data of the collected links and the calculation model of the load update values and load identification values t ;

[0045] The dynamic programming module is connected to the evaluation module and is used to perform corresponding dynamic programming according to the evaluation result L of the link t for the corresponding dynamic programming.

[0046] Due to the adoption of the above technical solution, the beneficial effects of the present invention compared with the prior art are as follows:

[0047] 1. This invention uses a data-driven approach to obtain evaluation results, ensuring that the network can respond quickly to sudden traffic or failures, thereby improving the overall robustness and flexibility of the network.

[0048] 2. By calculating load statistics, this invention can comprehensively evaluate the utilization of network resources, rationally allocate bandwidth and other resources, and avoid resource waste. Especially in emergency communication scenarios, it can maximize resource utilization efficiency and ensure the completion of critical communication tasks.

[0049] 3. This invention, through the calculation of load identification values, can promptly identify potential network fault points and take preventative measures to avoid service quality degradation. In the event of a fault, the system can quickly locate and restore service, reducing downtime and ensuring communication continuity.

[0050] 4. This invention, through the calculation of load update values, can promptly monitor changes in network status, balance the load distribution within the network, and ensure that the load on each link remains within a reasonable range. This effectively avoids situations where some links are overloaded while other links are idle, thereby improving the overall service quality of the network. Attached Figure Description

[0051] Figure 1 This is an overall flowchart of an intelligent dynamic planning method for emergency communication networks in an embodiment of the present invention.

[0052] Figure 2 This is a schematic diagram of the structure of an intelligent dynamic planning system for an emergency communication network according to an embodiment of the present invention. Detailed Implementation

[0053] The invention will be further described below with reference to the accompanying drawings and specific embodiments.

[0054] An intelligent dynamic programming method for emergency communication networks, such as Figure 1 As shown, it includes the following steps:

[0055] Step 1: Construct an emergency communication network;

[0056] Specifically, it aggregates and integrates data such as network resources, operating status, and alarm information from all subsystems of the entire network. Based on a real 3D geographic information system, it realistically presents the status of communication equipment, communication quality, communication status, and alarm information in the entire network, providing comprehensive, efficient, and reliable operation and maintenance support for network maintenance personnel.

[0057] Step 2: Use network devices to monitor the link status of the emergency communication network in real time and collect basic link data, including throughput, packet loss rate and latency.

[0058] Step 3: Construct a training sample set. Each training sample in the training sample set includes a current time-based basic data X(t) and a historical basic data Y(t). Here, X(t) is a 3x1 column vector, including the throughput, packet loss rate, and latency of the corresponding link at time t; Y(t) is a 3x1 column vector, including the average throughput, packet loss rate, and latency of the corresponding link during the duration Time before time t.

[0059] Step 4: Construct a calculation model for load update value and load identification value using deep learning. The input to the calculation model is the basic data X(t) of the link at time t and the corresponding historical basic data Y(t). The output of the calculation model is the load update value and load identification value of the link at time t.

[0060] Step 5: Sum the three elements in the historical basic data Y(t) and record it as the load statistics of the link at time t. Combine the load update value and load identification value of the link at time t to calculate the evaluation result L of the link at time t. t ;

[0061] Specifically, the assessment results refer to the load status of the link, comprehensively reflecting the link's real-time load, long-term load trends, and the existence of potential problems. The assessment results of the busy / idle status will be used to guide the next dynamic planning measures.

[0062] This step, by assessing the busy / idle status of the links, provides a crucial decision-making basis for subsequent dynamic planning. Real-time monitoring and assessment enable the system to detect changes in the busy / idle status of the links in a timely manner, which is especially important for emergency communication networks, because sudden traffic surges or failures in the network may occur at any time. Through real-time assessment, preventive measures can be taken in advance before the links become overloaded, thus avoiding a decline in service quality.

[0063] Step 6, evaluate the link at time t, L t The network is compared with the preset network normal state threshold T and network warning state threshold F, where T is less than F; based on the comparison result, corresponding dynamic planning is performed to complete the intelligent dynamic planning of the emergency communication network.

[0064] Furthermore, the specific method for constructing the calculation model of the load update value and the load identification value using deep learning in step 4 is as follows:

[0065] Step 401: For input samples X(t) and Y(t), calculate the corresponding load update values.

[0066] Among them, B mThe maximum throughput of the link is given by TR(), where TR() represents the trace of the computation matrix, W is the first updated weight matrix (a 3x3 matrix), V is the second updated weight matrix (a 3x3 matrix), and the superscript T indicates transpose.

[0067] Step 402: For the input sample X(t), calculate the corresponding load identification value.

[0068]

[0069] Where q is the first recognition weight vector, and q is a 3x1 column vector; denoted as the nonlinear transformation function; p is the second recognition weight vector, p is a 3x1 column vector; b is the adjustment term, b is a constant;

[0070] Specifically, nonlinear transformation functions include ReLU, Sigmoid, etc. This embodiment uses the Sigmoid function. In this embodiment, b = 0.5;

[0071] Load identification values ​​are used to distinguish different network states, helping to identify whether the current network is in a normal state or has potential problems, providing a basis for dynamic planning, and helping the system to perform resource scheduling and optimization based on the current network state;

[0072] Step 403: Calculate the corresponding loss value.

[0073]

[0074] in, This represents the true value of the link load update at time t. The value is the sum of the three elements in the column vector X(t)-X(t-1); This represents the true value of the load identification value of the link at time t. The value is the link status value at time t, which is manually marked based on the link's normal, overloaded, or underloaded states.

[0075] Step 404, based on the loss value Backpropagation using gradient descent is performed to update the first updated weight matrix, the second updated weight matrix, the first identification weight vector, and the second identification weight vector until the loss value is reached. Converge; save the parameters of the first updated weight matrix, the second updated weight matrix, the first identification weight vector, and the second identification weight vector; complete the construction of the calculation model for the load update value and the load identification value.

[0076] Furthermore, in step 5, the evaluation result L of the link at time t is calculated. tThe specific methods are as follows:

[0077]

[0078] in, Let μ1, μ2, and μ3 be the load statistics of the link at time t, and μ1, μ2, and μ3 be the adjustment coefficients of the load update value, load statistics value, and load identification value, respectively. μ1, μ2, and μ3 are all positive numbers, and μ1 + μ2 + μ3 = 1.

[0079] In this embodiment, μ1 = 0.5, μ2 = 0.3, and μ3 = 0.2.

[0080] Furthermore, the specific method for performing the corresponding dynamic programming based on the comparison results in step 6 is as follows:

[0081] If L t If T < T, then it is the normal state, and the corresponding dynamic programming is:

[0082] Resource optimization: Maintain the current resource allocation and continue to monitor the link status of the emergency communication network;

[0083] Precautions: Maintain existing precautions and continue to regularly check the link status of the emergency communication network;

[0084] If T≤L t If <F, it indicates a warning state, and the corresponding dynamic programming approach is:

[0085] Resource adjustment: Dynamically adjust bandwidth allocation, optimize traffic distribution, and avoid overload;

[0086] Increase redundancy: Add redundant connections to critical nodes to improve the robustness of the emergency communication network;

[0087] Preventive measures: Strengthen monitoring and promptly identify and address potential failure points;

[0088] If F≤L t If the condition is abnormal, the corresponding dynamic programming approach is:

[0089] Emergency Adjustments: Immediately adjust network configurations, such as adding temporary base stations, adjusting frequency allocations, and optimizing route selection;

[0090] Resource reallocation: Allocate bandwidth and other resources reasonably to avoid overloading certain nodes;

[0091] Fault recovery: Quickly locate the fault point and take measures to restore emergency communication network services;

[0092] Emergency Response: Set different Quality of Service (QoS) standards based on the urgency level and service type to ensure critical communications are prioritized.

[0093] Specifically,

[0094] 1. Add temporary base stations: When the assessment results show that the network load is high or there is local overload, temporary base stations can be added to alleviate the pressure and improve coverage and service quality.

[0095] 2. Adjust frequency allocation: Based on the evaluation results, dynamically adjust the frequency allocation to ensure the rational use of spectrum resources, avoid co-channel interference, and improve communication quality.

[0096] 3. Optimize route selection: Based on load statistics and identification values, optimize route selection to avoid overloaded links, distribute traffic reasonably, and improve overall network efficiency.

[0097] 4. Add redundant connections: For critical nodes, add redundant connections to improve the robustness and fault tolerance of the network and ensure that the network can still maintain connectivity in the event of partial link failure.

[0098] 5. Set QoS standards: Based on the evaluation results, set different Quality of Service (QoS) standards according to the urgency and service type of different services to ensure priority transmission of critical information.

[0099] An intelligent dynamic planning system for emergency communication networks is provided for executing any of the aforementioned intelligent dynamic planning methods for emergency communication networks, such as... Figure 2 As shown, it specifically includes a construction module, a collection module, an evaluation module, and a dynamic programming module;

[0100] The building module is used to construct an emergency communication network;

[0101] The collection module is connected to the construction module and is used to monitor the link status of the emergency communication network in real time using network devices and collect basic link data.

[0102] The evaluation module is connected to the collection module. The evaluation module specifically includes a training layer and an application layer. The training layer is used to construct a calculation model for the load update value and load identification value based on the basic data of the collected links. The application layer is used to calculate the evaluation result L of the link based on the basic data of the collected links and the calculation model for the load update value and load identification value. t ;

[0103] The dynamic programming module is connected to the evaluation module and is used to evaluate the link based on the evaluation result L. t Perform the corresponding dynamic programming.

[0104] In summary, this invention comprehensively and in real-time reflects the actual load situation of the network by monitoring the link status in real time and constructing a highly real-time evaluation mechanism based on load update values, load statistics values, and load identification values.

[0105] This embodiment provides an electronic device for an emergency communication network intelligent dynamic planning system, which includes one or more processors and a memory.

[0106] A processor can be a central processing unit (CPU) or other form of processing unit with data processing and / or instruction execution capabilities, and can control other components in an electronic device to perform desired functions.

[0107] The memory may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor may execute the program instructions to implement the intelligent dynamic planning method for emergency communication networks described above in any embodiment of this application, and / or other desired functions. Various contents such as initial extrinsic parameters and thresholds may also be stored in the computer-readable storage medium.

[0108] In one example, the electronic device may also include input and output devices, which are interconnected via a bus system and / or other forms of connection (not shown). The input device may include, for example, a keyboard, a mouse, etc. The output device may output various information to the outside, including warning messages, braking force, etc. The output device may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0109] In addition, depending on the specific application, electronic devices may include any other suitable components.

[0110] In addition to the methods and devices described above, embodiments of this application may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the steps of an intelligent dynamic planning method for emergency communication networks provided in any embodiment of this application.

[0111] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this application. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0112] Furthermore, embodiments of this application may also be computer-readable storage media storing computer program instructions thereon, which, when executed by a processor, cause the processor to perform the steps of an intelligent dynamic planning method for emergency communication networks provided in any embodiment of this application.

[0113] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may, for example, include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0114] It should be noted that the terminology used in this invention is for describing specific embodiments only and is not intended to limit the scope of this application. As shown in this specification, unless the context clearly indicates otherwise, words such as "a," "an," "an," and / or "the" do not specifically refer to the singular and may include the plural. The terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, or apparatus that includes said element.

[0115] It should also be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention. Unless otherwise expressly specified and limited, the terms "installed," "connected," "linked," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components. For those skilled in the art, the specific meaning of the above terms in the present invention can be understood according to the specific circumstances.

[0116] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; 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 or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the technical solutions of the embodiments of the present invention.

Claims

1. A method for intelligent dynamic planning of emergency communication networks, characterized in that, Includes the following steps: Step 1: Construct an emergency communication network; Step 2: Use network devices to monitor the link status of the emergency communication network in real time and collect basic link data, including throughput, packet loss rate and latency. Step 3: Construct a training sample set. Each training sample in the training sample set includes basic data for the current time step. And a historical baseline data ;in, It is a 3x1 column vector, including the throughput, packet loss rate and latency of the link at time t; It is a 3x1 column vector, which includes the average values ​​of throughput, packet loss rate and latency of the corresponding link during the duration Time before time t. Step 4: Construct a computational model for the load update value and load identification value using deep learning; the input to the computational model is the basic data of the link at time t. and the corresponding historical basic data The output of the calculation model is the load update value and load identification value of the link at time t; specifically: Step 401, for the input sample and Calculate the corresponding load update value : ； in, The maximum throughput of the link is given by TR(), where TR() represents the trace of the computation matrix, W is the first updated weight matrix (a 3x3 matrix), and V is the second updated weight matrix (a 3x3 matrix). The superscript T indicates transpose. Step 402, for the input sample Calculate the corresponding load identification value : ； Where q is the first recognition weight vector, and q is a 3x1 column vector; denoted as the nonlinear transformation function; p is the second recognition weight vector, p is a 3x1 column vector; b is the adjustment term, b is a constant; Step 403: Calculate the corresponding loss value. : ； in, This represents the true value of the link load update at time t. The value is The sum of the three elements in the column vector; This represents the true value of the load identification value of the link at time t. The value is the link status value at time t, which is manually marked based on the link's normal, overloaded, or underloaded states. Step 404, based on the loss value Backpropagation is performed using gradient descent to update the first updated weight matrix, the second updated weight matrix, the first identification weight vector, and the second identification weight vector until the loss value is reached. Convergence; save the parameters of the first updated weight matrix, the second updated weight matrix, the first identification weight vector, and the second identification weight vector; complete the construction of the calculation model for the load update value and the load identification value; Step 5, transfer historical basic data The sum of the three elements is denoted as the load statistics of the link at time t. Combining the load update value and load identification value of the link at time t, the evaluation result of the link at time t is calculated. ; Step 6: Evaluate the link at time t. The network is compared with the preset network normal state threshold T and network warning state threshold F, where T is less than F; based on the comparison result, corresponding dynamic planning is performed to complete the intelligent dynamic planning of the emergency communication network.

2. The intelligent dynamic planning method for emergency communication networks according to claim 1, characterized in that, Step 5 calculates the evaluation result of the link at time t. The specific methods are as follows: ； in, The load statistics of the link at time t. , , These represent the adjustment coefficients for the load update value, load statistics value, and load identification value, respectively. , , All are positive numbers, and .

3. The intelligent dynamic planning method for emergency communication networks according to claim 2, characterized in that, The specific method for performing dynamic programming based on the comparison results in step 6 is as follows: If <T, it is in the normal state, and the corresponding dynamic programming is as follows: Resource optimization: Maintain the current resource allocation and continue to monitor the link status of the emergency communication network; Precautions: Maintain existing precautions and continue to regularly check the link status of the emergency communication network; If T ≤ <F, it is a warning state, and the corresponding dynamic programming is as follows: Resource adjustment: Dynamically adjust bandwidth allocation, optimize traffic distribution, and avoid overload; Increase redundancy: Add redundant connections to critical nodes to improve the robustness of the emergency communication network; Preventive measures: Strengthen monitoring and promptly identify and address potential failure points; If F≤ If the condition is abnormal, the corresponding dynamic programming approach is: Emergency Adjustments: Immediately adjust network configurations, such as adding temporary base stations, adjusting frequency allocations, and optimizing route selection; Resource reallocation: Allocate bandwidth and other resources reasonably to avoid overloading certain nodes; Fault recovery: Quickly locate the fault point and take measures to restore emergency communication network services; Emergency Response: Set different Quality of Service (QoS) standards based on the urgency level and service type to ensure critical communications are prioritized.

4. An intelligent dynamic planning system for emergency communication networks, characterized in that, The method for executing the intelligent dynamic planning method for emergency communication networks according to any one of claims 1-3 includes a construction module, a collection module, an evaluation module, and a dynamic planning module. The building module is used to construct an emergency communication network; The collection module is connected to the construction module and is used to monitor the link status of the emergency communication network in real time using network devices and collect basic link data. The evaluation module is connected to the collection module. The evaluation module specifically includes a training layer and an application layer. The training layer is used to construct a calculation model for load update values ​​and load identification values ​​based on the basic data collected from the link. The application layer is used to calculate the evaluation results of the link based on the basic data collected from the link and the calculation model for load update values ​​and load identification values. ; The dynamic programming module is connected to the evaluation module and is used to evaluate the link based on the evaluation results. Perform the corresponding dynamic programming.

Images