Power network end-to-end queue scheduling and routing optimization method and system based on DQS

Abstract

The invention discloses a power network end-to-end queue scheduling and routing optimization method and system based on DQS, and relates to the field of power communication optimizing.The method comprises the steps that routing and delay requirements in a network are initialized and decomposed to each hop point; according to the decomposed delay demand and the real-time residual tolerable delay, the priority of the data packets is dynamically adjusted, and an accurate queue is allocated to each data packet; selecting an optimal path according to priority and delay requirements in combination with node and link state information; the routing and queue priorities are continuously optimized according to the network state to ensure that the QoS of the whole power network communication meets the actual demand and dynamically adapts to the change of the network environment; the method can flexibly adapt to changes of transmission paths, links and nodes in a power network, provides refined QoS guarantee for an intelligent power grid, and is especially suitable for scenes with strict requirements for low delay and high reliability, such as intelligent electric meters and power distribution automation.

Description

Technical Field

[0001] The present invention relates to the field of power communication optimization, and in particular to a method and system for end-to-end queue scheduling and routing optimization of a power network based on DQS. Background Art

[0002] With the rapid development of smart grid and distribution automation, the demand for power network communication is increasing, which puts higher requirements on the performance and reliability of communication technology. Especially in key application scenarios such as smart meters and distribution automation systems, low-latency and high-reliability communication has become a key factor in ensuring the stable operation of power systems. However, the existing quality of service (QoS) mechanism often shows obvious limitations when dealing with the complexity and dynamic changes of power networks.

[0003] Existing QoS mechanisms mainly rely on static resource allocation and preset queue scheduling strategies. These methods can better meet communication needs in fixed network environments, but they are obviously not adaptable in highly dynamic environments such as power networks. First, the transmission paths and link states in power networks are frequently adjusted over time, which makes it difficult for static queue scheduling and routing strategies to adapt to changes in network states in real time. Secondly, the end-to-end delay requirements of data packets in power networks are strict, and it is difficult for existing mechanisms to finely control the delay of each link, so that the end-to-end service quality requirements cannot be fully met; in addition, different types of data packets in power networks have different service quality requirements. For example, real-time control signals have extremely low tolerance for delays, while monitoring data are relatively loose. Existing mechanisms often adopt a unified scheduling strategy and cannot perform fine scheduling of different types of data packets, which makes it difficult to ensure the service quality of some key data packets. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is that the existing QoS mechanism is insufficiently adaptable in power network communication, cannot precisely control hop-by-hop link delay, and is difficult to meet complex communication requirements.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides a method for end-to-end queue scheduling and routing optimization in a power network based on DQS, comprising:

[0008] Initialize the routing and latency requirements in the network, broken down to each hop;

[0009] According to the decomposed delay requirements and the real-time remaining tolerable delay, the priority of the data packet is dynamically adjusted to assign each data packet to the correct queue;

[0010] Combine node and link status information to select the best path based on priority and delay requirements;

[0011] Continuously optimize routing and queue priorities according to network status to ensure that the QoS of the entire power network communication meets actual needs and dynamically adapts to changes in the network environment.

[0012] As a preferred solution of the end-to-end queue scheduling and routing optimization method for power networks based on DQS, the following is proposed:

[0013] The routing and delay requirements in the initialization network, broken down into each hop, include:

[0014] According to the data packet F in the power network 1 , f 2 , ..., f n}End-to-end delay requirement Decompose the delay requirements into hop-by-hop links through DQS and define the delay constraints for each hop.

[0015] The queue delay d at the DQS node q , that is, f n In Sw j The average time spent at the location is modeled using queuing theory, d q It is expressed as follows:

[0016]

[0017] Use Little's law to calculate the average waiting time of the queue and validate the arrival rate λ of the M / M / 1 / N system: Where N represents f n Position in the queue.

[0018] As a preferred solution of the end-to-end queue scheduling and routing optimization method for power networks based on DQS, the following is proposed:

[0019] The routing and delay requirements in the initialization network, broken down into each hop, also include:

[0020] The transmission delay d at the DQS node l Distinguishing between wired and wireless parts, the link capacity of the network C = {C w , C wl}, expressed as:

[0021]

[0022] d l The expression is as follows:

[0023]

[0024] As a preferred solution of the end-to-end queue scheduling and routing optimization method for power networks based on DQS, the following is proposed:

[0025] The dynamically adjusting the priority of the data packet according to the decomposed delay requirement and the real-time remaining tolerable delay, and assigning each data packet to an accurate queue includes:

[0026] Through the TPF algorithm, according to the remaining tolerable delay D of the data packet r Dynamically adjust its priority and assign the data packet to the deterministic guarantee queue Q 1 , adjustable guarantee queue Q 2 or best effort queue Q 3 ;

[0027] If D r Satisfy f n In future routing, q and d l When both take the maximum value, the original route hop count hop^ can still be satisfied, then the f n Assigned to the deterministic queue Q 1 Among them; expressed as:

[0028]

[0029] The queue length L is set according to the queue upper limit N of the switch, and the link capacity is the minimum value C. min , expressed as:

[0030]

[0031] As a preferred solution of the end-to-end queue scheduling and routing optimization method for power networks based on DQS, the following is proposed:

[0032] The allocation of each data packet to an accurate queue includes:

[0033] If f n D r Unsatisfied Deterministic Queue Q 1 hour:

[0034] First judgment: f n There is a new hop^, and the link status of the new route is good, f n Will be assigned to the adjustable queue Q 2 middle;

[0035] Second judgment: f n There is a new hop^, but the link state of the new route is congested, f n Will be assigned to the best effort queue Q 3 middle;

[0036] Third judgment: f n There is no new hop^ to choose from, f n Will be assigned to the best effort queue Q 3 middle;

[0037] The mathematical expression of the allocation process is:

[0038]

[0039] Among them, α and β are constants with values ​​of {0, 2}, and when their values ​​are 0, it means that the item is invalid.

[0040] As a preferred solution of the end-to-end queue scheduling and routing optimization method for power networks based on DQS, the following is proposed:

[0041] The combining of node and link status information and selecting the optimal path according to priority and delay requirements includes:

[0042] The GHRS algorithm is used to capture the network link status in real time through the graph neural network, including the node queue length L, link rate C, and select the optimal routing path. Ensure that data packets can be transmitted while meeting QoS requirements.

[0043] As a preferred solution of the end-to-end queue scheduling and routing optimization method for power networks based on DQS, the following is proposed:

[0044] The continuous optimization of routing and queue priority according to the network status includes:

[0045] Continuously adjust routing based on changes in link C and node status L and queue priority Q, ensuring that QoS in the power network meets actual communication requirements

[0046] In a second aspect, an embodiment of the present invention provides a DQS-based end-to-end queue scheduling and routing optimization system for a power network, including:

[0047] Initialization module, used to initialize the routing and delay requirements in the network, broken down to each hop;

[0048] Dynamic priority allocation module, used to dynamically adjust the priority of data packets according to the decomposed delay requirements and the real-time remaining tolerable delay, and allocate each data packet to the correct queue;

[0049] The optimal path selection module is used to select the optimal path according to the priority and delay requirements by combining the node and link status information;

[0050] The routing optimization execution module is used to continuously optimize routing and queue priorities according to the network status to ensure that the QoS of the entire power network communication meets actual needs and dynamically adapts to changes in the network environment.

[0051] In a third aspect, an embodiment of the present invention provides a computing device, including:

[0052] Memory and processor;

[0053] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the one or more programs are executed by the one or more processors, the one or more processors implement the DQS-based power network end-to-end queue scheduling and routing optimization method as described in any embodiment of the present invention.

[0054] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the DQS-based end-to-end queue scheduling and routing optimization method for a power network.

[0055] The beneficial effects of the present invention are as follows: the present invention effectively guarantees the transmission delay requirements by decomposing the end-to-end delay requirements hop by hop and dynamically adjusting the data packet priority at each hop, thereby ensuring the efficient transmission of key data such as real-time power control commands; combining node and link status information to select the optimal path, which not only improves the transmission efficiency, but also enhances the robustness and adaptability of the network; continuously monitors and optimizes routing and queue priorities to form a closed-loop feedback system, which can dynamically adapt to changes in the network environment and maximize the use of network resources; through precise priority adjustment and optimal path selection, network congestion and data packet loss are reduced, and the stability and reliability of the network are improved; the timely transmission of different types of data packets is guaranteed, especially for delay-sensitive applications, which significantly improves the user experience and service quality; for power networks, the efficient transmission of real-time control commands is guaranteed, and the power dispatching and grid operation efficiency are optimized; by improving network resource utilization and reducing data packet loss, the network operation and maintenance costs are reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use 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 ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0057] Figure 1 It is an overall flow chart of the DQS-based end-to-end queue scheduling and routing optimization method for a power network described in the first embodiment of the present invention. DETAILED DESCRIPTION

[0058] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0059] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0060] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0061] Example 1

[0062] Reference Figure 1 , which is the first embodiment of the present invention, and provides a DQS-based end-to-end queue scheduling and routing optimization method for a power network, comprising:

[0063] S1: Initialize the routing and delay requirements in the network, breaking them down into each hop;

[0064] S2: Dynamically adjust the priority of data packets based on the decomposed delay requirements and the real-time remaining tolerable delay, and assign each data packet to the correct queue;

[0065] S3: Combine node and link status information to select the optimal path based on priority and delay requirements;

[0066] S4: Continuously optimize routing and queue priorities according to network status to ensure that the QoS of the entire power network communication meets actual needs and dynamically adapts to changes in the network environment.

[0067] In the embodiment of the present application, the routing and delay requirements in the network are initialized in the above step S1, and the decomposition to each hop includes:

[0068] According to the data packet F in the power network 1 , f 2 , ..., f n}End-to-end delay requirement Decompose the delay requirements into hop-by-hop links through DQS and define the delay constraints for each hop.

[0069] The queue delay d at the DQS node q , that is, f n In Sw j The average time spent at the location is modeled using queuing theory, d q It is expressed as follows:

[0070]

[0071] Use Little's law to calculate the average waiting time of the queue and validate the arrival rate λ of the M / M / 1 / N system: Where N represents f n Position in the queue.

[0072] The transmission delay d at the DQS node l Distinguishing between wired and wireless parts, the link capacity of the network C = {C w , C wl}, expressed as:

[0073]

[0074] d l The expression is as follows:

[0075]

[0076] In the embodiment of the present application, in the above step S2, according to the decomposed delay requirement and the real-time remaining tolerable delay, the priority of the data packet is dynamically adjusted, and each data packet is assigned to an accurate queue, including:

[0077] Through the TPF algorithm, according to the remaining tolerable delay D of the data packet r Dynamically adjust its priority and assign the data packet to the deterministic guarantee queue Q 1 , adjustable guarantee queue Q 2or best effort queue Q 3 ;

[0078] Specifically, a differential queue service model is introduced to dynamically adjust the priority of packets based on the residual delay of the packets, giving priority to packets with smaller delays and strict requirements. n In terms of time consumed Define f n The remaining allowed delay in the internal network within the dashed box is D r =D QoS -D past Therefore, f n In Sw j Subsequent routing decisions need to satisfy

[0079] Defining functions To express f n The total delay of Expression n The mathematical expression of the entire differential queue service model is as follows:

[0080]

[0081] A three-channel queue forwarding module is introduced to allocate data packets to the deterministic guarantee queue, the adjustable guarantee queue and the best-effort queue according to the residual delay, and forward them according to the different priorities of the queues when congested.

[0082] The expression of the three-channel queue forwarding module is:

[0083]

[0084] If D r Satisfy f n In future routing, q and d l When both take the maximum value, the original route hop count hop^ can still be satisfied, then the f n Assigned to the deterministic queue Q 1 Among them; expressed as:

[0085]

[0086] The queue length L is set according to the queue upper limit N of the switch, and the link capacity is the minimum value C. min , expressed as:

[0087]

[0088] Assigning each packet to the correct queue involves:

[0089] If f n D r Unsatisfied Deterministic Queue Q 1 hour:

[0090] First judgment: f n There is a new hop^, and the link status of the new route is good, f n Will be assigned to the adjustable queue Q 2 middle;

[0091] Second judgment: f n There is a new hop^, but the link state of the new route is congested, f n Will be assigned to the best effort queue Q 3 middle;

[0092] Third judgment: f n There is no new hop^ to choose from, f n Will be assigned to the best effort queue Q 3 middle.

[0093] The mathematical expression of the allocation process is:

[0094]

[0095] Among them, α and β are constants with values ​​of {0, 2}, and when their values ​​are 0, it means that the item is invalid.

[0096] In the embodiment of the present application, in the above step S3, combining the node and link status information, selecting the optimal path according to the priority and delay requirements includes:

[0097] The GHRS algorithm is used to capture the network link status in real time through the graph neural network, including the node queue length L, link rate C, and select the optimal routing path. Ensure that data packets can be transmitted while meeting QoS requirements;

[0098] Extract eigenvalues ​​from the network graph G = (V, E, U), the eigenvalues ​​include:

[0099]

[0100] in, Indicates the QoS requirements, size, routing and queue length information of the data packet; Indicates the link transmission rate.

[0101] The GHRS algorithm is used to update the network status process in real time through the graph neural network, and the eigenvalues ​​are processed through the multi-layer perceptron of the graph neural network to generate the network status matrix The expression is The size of is r×r. The content of the record corresponds to The diagonal elements of Represents The eigenvalue of The remaining elements For X e The eigenvalue of For any f n Path In terms of The number of hops is the number of routes. and The mapping relationship between them is as follows:

[0102] Based on the updated network status matrix Generate routing decision matrix It is expressed as:

[0103]

[0104] yes A subset of The size of is hop×hop. Find a line that supports f i The optimal solution for dynamic QoS guarantee for The submatrix of and the matrix size is m×hop^. and Corresponding to In and Since the hop count hop^ is The number of The number of hop^ is, The number is hop^-1. γ and ε are and , and γ+ε=1.

[0105] It should be noted that the default and The impact on QoS is the same because is on the order of milliseconds and Any slight change in will affect the QoS results. The importance of the nodes has been balanced, so each weight value is taken as 1 / 2 to express the importance of queue delay and path delay equally.

[0106] Select the best path And output the final result R QoS , the first layer of GNN transforms the adjacency matrix A into As the input of the second layer, the final output To get the optimal solution The output Y of the GNN will be As the input of softmax, all f n Perform a three-classification task to count the number of DG, AG, and BEG. The expression of the output Y of GNN is as follows:

[0107]

[0108] Finally, the classification results are output according to the dynamic guarantee rate of QoS:

[0109]

[0110] In the embodiment of the present application, the continuous optimization of routing and queue priority according to the network status in the above step S4 includes:

[0111] Continuously adjust routing based on changes in link C and node status L and queue priority Q, ensuring that QoS in the power network meets actual communication requirements

[0112] The above is a schematic scheme of the DQS-based power network end-to-end queue scheduling and routing optimization method of this embodiment. It should be noted that the technical solution of the DQS-based power network end-to-end queue scheduling and routing optimization system and the above-mentioned DQS-based power network end-to-end queue scheduling and routing optimization method technical solution belong to the same concept, and the details of the technical solution of the DQS-based power network end-to-end queue scheduling and routing optimization system in this embodiment that are not described in detail can all be referred to the description of the technical solution of the DQS-based power network end-to-end queue scheduling and routing optimization method.

[0113] The DQS-based end-to-end queue scheduling and routing optimization system for a power network in this embodiment includes:

[0114] Initialization module, used to initialize the routing and delay requirements in the network, broken down to each hop;

[0115] Dynamic priority allocation module, used to dynamically adjust the priority of data packets according to the decomposed delay requirements and the real-time remaining tolerable delay, and allocate each data packet to the correct queue;

[0116] The optimal path selection module is used to select the optimal path according to the priority and delay requirements by combining the node and link status information;

[0117] The routing optimization execution module is used to continuously optimize routing and queue priorities according to the network status to ensure that the QoS of the entire power network communication meets actual needs and dynamically adapts to changes in the network environment.

[0118] This embodiment further provides a computing device, which is applicable to the case of a DQS-based power network end-to-end queue scheduling and routing optimization method, including:

[0119] Memory and processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the DQS-based end-to-end queue scheduling and routing optimization method for the power network as proposed in the above embodiment.

[0120] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the DQS-based end-to-end queue scheduling and routing optimization method for a power network as proposed in the above embodiment is implemented.

[0121] The storage medium proposed in this embodiment and the DQS-based end-to-end queue scheduling and routing optimization method for the power network proposed in the above embodiment belong to the same inventive concept. The technical details not described in detail in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0122] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for end-to-end queue scheduling and routing optimization in a power network based on DQS, characterized in that: include: Initialize the routing and latency requirements in the network, broken down to each hop; According to the decomposed delay requirements and the real-time remaining tolerable delay, the priority of the data packet is dynamically adjusted to assign each data packet to the correct queue; Combine node and link status information to select the best path based on priority and delay requirements; Continuously optimize routing and queue priorities according to network status to ensure that the QoS of the entire power network communication meets actual needs and dynamically adapts to changes in the network environment.

2. The DQS-based end-to-end queue scheduling and routing optimization method for a power network according to claim 1, characterized in that: The routing and delay requirements in the initialization network, broken down into each hop, include: According to the data packet F={f1,f2,...,f n }End-to-end delay requirement Decompose the delay requirements into hop-by-hop links through DQS and define the delay constraints for each hop. The queue delay at the DQS node is d q , that is, f n In Sw j The average time spent at the location is modeled using queuing theory, d q It is expressed as follows: Use Little's law to calculate the average waiting time of the queue and validate the arrival rate λ of the M / M / 1 / N system: Where N represents f n Position in the queue.

3. The DQS-based end-to-end queue scheduling and routing optimization method for a power network as claimed in claim 2, characterized in that: The routing and delay requirements in the initialization network, broken down into each hop, also include: The transmission delay d at the DQS node l Distinguishing between wired and wireless parts, the link capacity of the network C = {C w ,C wl }, expressed as: d l The expression is as follows:

4. The DQS-based end-to-end queue scheduling and routing optimization method for a power network as claimed in claim 3, characterized in that: The dynamically adjusting the priority of the data packet according to the decomposed delay requirement and the real-time remaining tolerable delay, and assigning each data packet to an accurate queue includes: Through the TPF algorithm, according to the remaining tolerable delay D of the data packet r Dynamically adjust its priority and assign data packets to the deterministic guarantee queue Q1, the adjustable guarantee queue Q2, or the best-effort queue Q3; If D r Satisfy f n In future routing, q and d l When both take the maximum value, the original route hop count can still be met ∧ , then the f n Assigned to the deterministic queue Q1; expressed as: The queue length L is set according to the queue upper limit N of the switch, and the link capacity is the minimum value C. min , expressed as:

5. The DQS-based end-to-end queue scheduling and routing optimization method for a power network as claimed in claim 4, characterized in that: The allocation of each data packet to an accurate queue includes: If f n D r When the deterministic queue Q1 is not satisfied: First judgment: f n There is a new hop ∧ , and the link status of the new route is good, f n Will be assigned to the adjustable queue Q2; Second judgment: f n There is a new hop ∧ , but the link state of the new route is congested, f n Will be assigned to the best effort cohort Q3; Third judgment: f n No new hop ∧ Available, f n Will be assigned to the best effort cohort Q3; The mathematical expression of the allocation process is: Among them, α and β are constants with values ​​of {0,2}. When their values ​​are 0, it means that the item is invalid.

6. The DQS-based end-to-end queue scheduling and routing optimization method for a power network according to claim 5, characterized in that: The combining of node and link status information and selecting the optimal path according to priority and delay requirements includes: The GHRS algorithm is used to capture the network link status in real time through the graph neural network, including the node queue length L, link rate C, and select the optimal routing path. Ensure that data packets can be transmitted while meeting QoS requirements.

7. The DQS-based end-to-end queue scheduling and routing optimization method for a power network according to claim 6, characterized in that: The continuous optimization of routing and queue priority according to the network status includes: Continuously adjust routing based on changes in link C and node status L and queue priority Q, ensuring that QoS in the power network meets actual communication requirements 8. A system using the DQS-based end-to-end queue scheduling and routing optimization method for a power network as claimed in any one of claims 1 to 7, characterized in that: include: Initialization module, used to initialize the routing and delay requirements in the network, broken down to each hop; Dynamic priority allocation module, used to dynamically adjust the priority of data packets according to the decomposed delay requirements and the real-time remaining tolerable delay, and allocate each data packet to the correct queue; The optimal path selection module is used to select the optimal path according to the priority and delay requirements by combining the node and link status information; The routing optimization execution module is used to continuously optimize routing and queue priorities according to the network status to ensure that the QoS of the entire power network communication meets actual needs and dynamically adapts to changes in the network environment.

9. A computing device comprising: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the DQS-based power network end-to-end queue scheduling and routing optimization method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the DQS-based end-to-end queue scheduling and routing optimization method for a power network as described in any one of claims 1 to 7.

Images