Windowed scheduling method, system and equipment for communication traffic of power system

Abstract

The invention provides a windowed scheduling method, system and equipment for communication traffic of a power system. The method comprises the following steps: acquiring stream data of a plurality of service streams in a power communication network, and outputting each target queue in a port; based on the flow data of each service flow and each target queue, solving a target function corresponding to a preset windowed scheduling model according to a preset multi-dimensional constraint condition, and obtaining an optimal scheduling period, window length and window offset; wherein the windowed scheduling model is composed of a plurality of decision variables; the multi-dimensional constraint conditions comprise window mutual exclusion constraints among target queues of the same port and service guarantee constraints for guaranteeing the minimum service rate for low-priority queues; and generating and outputting a corresponding gating list based on the optimal scheduling period, the window length and the window offset corresponding to the power communication network. According to the invention, the reliability, the flexibility and the operation and maintenance performance of a novel power system communication network can be improved.

Description

Technical Field

[0001] This application relates to the intersection of power information communication and deterministic Ethernet (TSN / DetNet), and in particular to a windowed scheduling method, system and device for power system communication traffic. Background Technology

[0002] The new power system is driving the convergence and collaboration of power communication networks. With the integration of new energy sources, the growth of electric vehicles, and the rise of virtual power plants and smart distribution networks, the system is rapidly evolving towards distributed, flexible, intelligent, and digital architectures, leading to a surge in access scale and video demand. Communication networks must ensure low latency, low jitter, and high reliability for real-time services such as protection, monitoring, and dispatching, while also handling high-bandwidth / burst traffic from video surveillance and office applications, providing high-precision synchronization, redundancy, fault tolerance, and security isolation. Traditional dedicated communication equipment generally adopts a "black box" architecture, with integrated hardware and software and fixed functions, making it difficult to flexibly schedule and expand according to real-time changes in services. Furthermore, the closed interfaces of black box devices limit the programmability and verifiability of underlying scheduling strategies, resulting in inconsistencies in strategies, delayed optimization, and poor traceability in the actual operation and maintenance of cross-vendor and cross-domain networks. In recent years, open network devices have become an industry trend. Their core idea is the decoupling of hardware and software. The hardware adopts standardized design based on the Open Compute Project (OCP), while the software layer supports various network operating systems (NOS) through the Open Network Installation Environment (ONIE) and Switch Abstraction Interface (SAI), such as SONiC (Software for Open Networking in the Cloud) and DANOS (Dis-Aggregated Network Operating System). These devices possess programmability, verifiability, and interoperability, providing a foundation for flexible scheduling and intelligent management of power communication networks. Simultaneously, the development of Deterministic Networking (DetNet) and Time-Sensitive Networking (TSN) technologies has provided the power industry with highly deterministic transport mechanisms. The time gating mechanism (IEEE 802.1Qbv) introduced in TSN uses a gated list (GCL) to periodically schedule the queue transmission window, a core technology for ensuring deterministic latency and jitter.

[0003] Despite the progress made in TSN scheduling, existing technologies still have significant shortcomings in high-precision, strongly constrained, and multi-objective joint scheduling for new power system scenarios. Incomplete modeling and a lack of constraint linkage mechanisms make it difficult to support large-scale complex network scenarios. Ignoring guard bands and inter-frame interference models can lead to scheduling conflicts or severe fragmentation at period boundaries. The lack of guarantees and fairness control in BE (Best Efferent) services can easily cause low-priority flows to be completely starved when high-priority flows surge. Severe window fragmentation and low resource utilization reduce link utilization efficiency and scheduling stability. In multi-port, multi-queue scenarios, existing technologies are mostly statically configured or heuristically based, lacking period divisibility (…). The joint modeling of constraints such as constraints, Guard Band, phase alignment, minimum guarantee of BE service, and event-driven latency makes the reliability of actual deployment and scheduling results poor. Summary of the Invention

[0004] In view of this, embodiments of this application provide a windowed scheduling method, system, and device for power system communication traffic to eliminate or improve one or more defects existing in the prior art.

[0005] One aspect of this application provides a windowed scheduling method for power system communication traffic, the method comprising the following steps: Acquire the stream data of multiple service flows in the power communication network and the target queues in the output port of the power communication network; Based on the flow data of each of the aforementioned service flows and each of the aforementioned target queues, the objective function corresponding to the preset windowed scheduling model is solved according to preset multi-dimensional constraints to obtain the optimal scheduling period, window length, and window offset for the power communication network. The windowed scheduling model consists of multiple decision variables. The multi-dimensional constraints include: mutual exclusion constraints between target queues on the same port, and service guarantee constraints to ensure minimum service rate for low-priority queues. The objective function is used to jointly optimize bandwidth utilization and scheduling fragmentation. Based on the optimal scheduling period, window length, and window offset corresponding to the power communication network, a gating list for scheduling each service flow in the power communication network is generated and output.

[0006] In some embodiments of this application, the decision variables include: the scheduling period, window length, window offset, and period divisibility factor of each target queue in each output port.

[0007] In some embodiments of this application, the multi-dimensional constraint further includes a periodic divisibility constraint, which is used to set a positive integer divisibility factor for the scheduling period of each target queue, such that the scheduling period satisfies a divisibility relationship with a preset super-period.

[0008] In some embodiments of this application, the multi-dimensional constraints further include guardrail constraints, which are used to subtract a preset guardrail time from the nominal window length when calculating the effective service window length of each of the target queues.

[0009] In some embodiments of this application, the multi-dimensional constraints further include event-driven constraints, which are used to ensure that, for a service flow with a local expiration date, the cumulative service volume provided to the queue to which the service flow belongs before the time point corresponding to the local expiration date is equal to or greater than the cumulative data arrival volume of the service flow before that time point.

[0010] In some embodiments of this application, the objective function is represented as follows: in, Measuring the cost of window normalization Indicates the periodic divisor. This is the fragmentation penalty coefficient. This refers to the output port. Indicates the output port The target queue.

[0011] In some embodiments of this application, the step of solving the objective function corresponding to a preset windowed scheduling model based on the stream data of each of the service flows and each of the target queues, according to preset multi-dimensional constraints, to obtain the optimal scheduling period, window length, and window offset for the power communication network, includes: The flow data of each of the service flows and each of the target queues are input into the objective function corresponding to the preset windowed scheduling model. Based on the preset multi-dimensional constraints and the phased variable assignment strategy, the scheduling period, the window length and the window offset corresponding to the power communication network are solved sequentially.

[0012] Another aspect of this application provides a windowed dispatching system for power system communication traffic, the system comprising: The information acquisition module is used to acquire the stream data of multiple service flows in the power communication network and the target queues in the output port of the power communication network. The model solving module is used to solve the objective function corresponding to the preset windowed scheduling model based on the flow data of each of the service flows and each of the target queues, according to preset multi-dimensional constraints, to obtain the optimal scheduling period, window length, and window offset for the power communication network; wherein, the windowed scheduling model consists of multiple decision variables; the multi-dimensional constraints include: window mutual exclusion constraints between each of the target queues on the same port, and service guarantee constraints to ensure minimum service rate for low-priority queues; the objective function is used to jointly optimize bandwidth utilization and scheduling fragmentation. The output module is used to generate and output a gating list for scheduling each service flow in the power communication network based on the optimal scheduling period, window length and window offset corresponding to the power communication network.

[0013] A third aspect of this application provides an electronic device including a processor and a memory; the processor, when executing a running program stored in the memory, implements the windowed scheduling method for power system communication traffic.

[0014] A fourth aspect of this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the windowed scheduling method for power system communication traffic.

[0015] The fifth aspect of this application provides a computer program product, including a computer program that, when executed by a processor, implements the aforementioned windowed scheduling method for power system communication traffic.

[0016] This application discloses a windowed scheduling method for power system communication traffic. The method acquires flow data of multiple service flows in a power communication network and target queues at the output ports of the power communication network. Based on the flow data of each service flow and each target queue, it solves for a pre-defined objective function corresponding to a pre-defined windowed scheduling model according to pre-defined multi-dimensional constraints, thereby obtaining the optimal scheduling period, window length, and window offset for the power communication network. The windowed scheduling model consists of multiple decision variables. The multi-dimensional constraints include mutual exclusion constraints between target queues at the same port and service guarantee constraints ensuring minimum service rate for low-priority queues. The objective function is used to jointly optimize bandwidth utilization and scheduling fragmentation. Based on the optimal scheduling period, window length, and window offset for the power communication network, a gating list for scheduling each service flow in the power communication network is generated and output. This paper proposes a unified end-to-end deterministic bearing and windowed scheduling method for multi-service co-carrying scenarios in power communication networks. Addressing scheduling problems in multi-port, multi-queue networks, including period divisibility, guardrail time, phase alignment, minimum service guarantee (BE), and event-driven time limits, a multi-constraint joint modeling framework is constructed. With scheduling period, window length, window offset, and period divisibility factor as core decision-making parameters, a gridded window scheduling mechanism and deployable GCL optimization are designed. The objective function minimizes the normalized gating ratio and suppresses GCL fragmentation, improving the reliability, flexibility, and maintainability of new power system communication networks. The method is highly deployable, and the obtained solution naturally meets the requirements of super-period divisibility and unified port period, and can be directly applied. It converts to a GCL configuration executable by TSN devices without additional post-processing; it improves bandwidth utilization by optimizing the normalized duty cycle through the objective function, effectively reducing the proportion of idle time slices; with the help of an event-driven prefix constraint mechanism, it ensures that sufficient service volume can still be provided for power protection flow at critical millisecond moments, providing real-time guarantee; it enhances service fairness by using BE service lower bound constraints to ensure that low-priority traffic still receives minimum service guarantee when high-priority traffic occupies bandwidth, thus avoiding service "starvation"; and it improves the robustness of the scheduling scheme by introducing a guardrail mechanism and multi-dimensional constraints, enabling the scheduling to adapt to sudden link impacts and load changes, increasing the robustness and adaptability of the scheduling scheme.

[0017] Additional advantages, objectives, and features of this application will be set forth in part in the description which follows, and will in part become apparent to those skilled in the art upon review of the following description, or may be learned by practice of the application. The objectives and other advantages of this application can be realized and obtained by means of the structures specifically pointed out in the specification and drawings.

[0018] Those skilled in the art will understand that the purposes and advantages that can be achieved with this application are not limited to those specifically described above, and that the above and other purposes that this application can achieve will be more clearly understood from the following detailed description. Attached Figure Description

[0019] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, do not constitute a limitation thereof. The components in the drawings are not drawn to scale but are merely for illustrating the principles of this application. For ease of illustration and description of certain parts of this application, corresponding portions in the drawings may be enlarged, i.e., may appear larger relative to other components in an exemplary device actually manufactured according to this application. In the drawings: Figure 1 This is a schematic diagram of the first step in the windowed scheduling method for power system communication traffic according to an embodiment of this application.

[0020] Figure 2 This is a second flowchart illustrating a windowed scheduling method for power system communication traffic in one embodiment of this application.

[0021] Figure 3 This is a schematic diagram of a windowed scheduling system for power system communication traffic according to an embodiment of this application. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the embodiments and accompanying drawings. Here, the illustrative embodiments and their descriptions are used to explain this application, but are not intended to limit it.

[0023] It should also be noted that, in order to avoid obscuring this application with unnecessary details, only the structures and / or processing steps closely related to the solution according to this application are shown in the accompanying drawings, while other details that are not closely related to this application are omitted.

[0024] It should be emphasized that the term "including / comprises" as used herein refers to the presence of a feature, element, step, or component, but does not exclude the presence or addition of one or more other features, elements, steps, or components.

[0025] It should also be noted that, unless otherwise specified, the term "connection" in this article can refer not only to a direct connection, but also to an indirect connection involving an intermediary.

[0026] In the following description, embodiments of the present application will be illustrated with reference to the accompanying drawings. In the drawings, the same reference numerals represent the same or similar parts, or the same or similar steps.

[0027] It should be noted that existing technologies propose a Critical Time Triggered Flow (CTT) window scheduling method (CTT ILP) based on Integer Linear Programming (ILP), aiming to ensure deterministic time-limited transmission of critical services by statically generating window sequences through ILP. However, this method does not address constraints in power scenarios such as period divisibility, guardrail time, event-driven latency, or minimum BE guarantee. Another approach aims to improve the QoS performance of multi-hop TSN networks through path scheduling coordination. This method focuses on overall path and scheduling optimization but neglects fine-grained windowed scheduling of GCL, phase alignment, and event-driven mechanisms, failing to meet the fine-grained requirements of power scenarios. Yet another proposed online timeslot adjustment mechanism calculates the "latency compliance rate" by real-time collection of frame length statistics of critical flows at the sending and receiving ends and dynamically adjusts the GCL timeslot window size. Its innovation lies in introducing a closed-loop feedback mechanism to dynamically adjust the scheduling window to adapt to sudden critical flow expansion problems in environments such as automotive and industrial systems. However, this method does not perform unified modeling and global optimization of window period, length, and offset, making it difficult to meet the accuracy and convergence requirements of large-scale, high-real-time scheduling in power scenarios. Existing technologies also propose adding a scheduling plan verification module to TSN scheduling. This module can verify whether the gated list (GCL) configuration meets the specified terminal latency requirements after scheduling is generated (or before implementation). If scheduling errors are found, the correctness of the scheduling can be verified through simulation using methods such as digital twins, thereby preventing QoS violations or device inconsistencies caused by erroneous scheduling. While this approach enhances the reliability of scheduling and the feasibility of engineering execution, it does not address aspects such as window optimization, granularity adjustment, fragmentation control, and BE service assurance within the GCL. In general, existing solutions mostly focus on single or a few constraints, such as end-to-end time limit guarantees for critical time-triggered flows and joint optimization of critical flow paths and scheduling, lacking the ability to model multiple constraints in a unified manner for power scenarios. Furthermore, existing methods often remain at the level of abstract time slot allocation or window adjustment, without fully considering the actual configuration constraints of micro-clock scales, super-period divisibility structures, and gating lists in multi-port, multi-queue scenarios of TSN white-box devices. Most current online time slot adjustment and experience-based rule-driven scheduling methods lack explicit modeling and constraints on "normalized duty cycle" and "window fragmentation," which can easily lead to excessive window segmentation and an excessively high proportion of idle time slices. In addition, traditional solutions generally lack constraints on the minimum service rate of BE traffic, and when high-priority critical flows surge under fault or reconstruction scenarios, low-priority services are easily "starved" for a long time.Based on this, the inventors of this application first conceived of a unified method for end-to-end deterministic bearer and windowed scheduling. Addressing scheduling problems in multi-port, multi-queue networks, such as period divisibility, guardrail time, phase alignment, minimum service guarantee (BE), and event-driven time limits, a multi-constraint joint modeling framework is constructed. With scheduling period, window length, window offset, and period divisibility factor as core decisions, a gridded window scheduling mechanism and deployable GCL optimization are designed. The objective function minimizes the normalized gating ratio and suppresses GCL fragmentation, improving the reliability, flexibility, and maintainability of the new power system communication network. This application introduces a minimum service rate (BE) constraint into the windowed scheduling model, effectively ensuring fair resource allocation and service continuity. It also introduces period divisibility and guardrail constraints to improve GCL scheduling security and resource utilization. Furthermore, by adding a joint objective function of normalized duty cycle and fragmentation penalty term, the compactness and efficiency of scheduling are optimized.

[0028] The following examples will provide a detailed description.

[0029] This application provides a windowed scheduling method for power system communication traffic, see [link to relevant documentation]. Figure 1 The method includes the following steps: Step 100: Obtain the flow data of multiple service flows in the power communication network and the target queues in the output port of the power communication network; Step 200: Based on the flow data of each of the service flows and each of the target queues, solve the objective function corresponding to the preset windowed scheduling model according to the preset multi-dimensional constraints to obtain the optimal scheduling period, window length, and window offset for the power communication network; wherein, the windowed scheduling model consists of multiple decision variables; the multi-dimensional constraints include: window mutual exclusion constraints between each of the target queues on the same port, and service guarantee constraints to ensure minimum service rate for low-priority queues; the objective function is used to jointly optimize bandwidth utilization and scheduling fragmentation. It can be understood that the multi-dimensional constraints also include window validity constraints and same-port same-cycle constraints. The window validity constraint is used to ensure that for any queue, the sum of its window length and window offset is less than or equal to its scheduling cycle. The same-port same-cycle constraint is used to force all target queues on the same output port to adopt the same scheduling cycle. The window validity constraint can be expressed as: in, Represents the target queue At the output port The scheduling cycle on, Represents the target queue At the output port Window length on Represents the target queue At the output port Window offset on.

[0030] The same-port, same-period constraint can be expressed as: in, Represents the target queue At the output port The scheduling cycle on, Represents the target queue At the output port The scheduling cycle on, Indicates output port All queues gather.

[0031] Step 300: Based on the optimal scheduling period, window length, and window offset corresponding to the power communication network, generate and output a gating list for scheduling each service flow in the power communication network.

[0032] In one or more embodiments of this application, the microtick of the switch is used as the time scale. If the microtick of the switch where a certain port is located is... μ (ns), the hyperperiod of this port is H (ns), then the discretized superperiodic expression is as follows: in, This indicates a discretized superperiodic.

[0033] For each output port and each target queue used within that port. Define a windowed gated list (GCL) triplet variable as follows: in, Represents an integer greater than or equal to 1. Represents an integer greater than or equal to 0.

[0034] If queue The priority is π, and the configuration is... The service guarantee constraint for ensuring the minimum service rate of the low-priority queue is expressed by the following formula: in, Represents the target queue At the output port Effective window length on This represents the minimum service guarantee ratio specified by priority π.

[0035] For the same output port Two valid queues ( Introducing binary variables and order Therefore, windows on the same port need to be mutually exclusive, meaning that any two windows do not overlap on a periodic axis. The mutual exclusion constraint of windows between the target queues on the same port can be expressed as follows: in, Represents the target queue At the output port Window offset on Represents the target queue At the output port Window length on Indicates output port The guardrail time, Represents the target queue At the output port Window length on Represents the target queue At the output port Window offset on Represent a constant. equal .

[0036] As described above, this application constructs a multi-constraint joint modeling framework. The objective function minimizes the normalized gating ratio and suppresses GCL fragmentation, thereby improving the reliability, flexibility, and maintainability of the new power system communication network. It has strong deployability and can improve bandwidth utilization. By optimizing the normalized duty cycle through the objective function, the proportion of idle time slices is effectively reduced. Service fairness is enhanced, ensuring that low-priority traffic can still obtain minimum service guarantees when high-priority traffic occupies bandwidth, thus avoiding the phenomenon of service "starvation." The robustness of the scheduling scheme is improved. The introduction of multi-dimensional constraints enables the scheduling to adapt to sudden link impacts and load changes, increasing the robustness and adaptability of the scheduling scheme.

[0037] To further improve the reliability and fairness of the new power system communication network, in a windowed scheduling method for power system communication traffic provided in this application embodiment, the decision variables include: the scheduling period, window length, window offset, and period divisibility factor of each target queue in each output port.

[0038] In one or more embodiments of this application, for each output port target queue on Define the following decision variables: Indicates the scheduling period, satisfying ; The window length is specified to ensure it is not less than the maximum transmission duration per session, thus satisfying the requirements. , This indicates the minimum available window length. Indicates window offset, requiring ; Represents the periodic divisor. .

[0039] Each queue The maximum transmission time (ns) of a single frame is obtained from the set of streams it belongs to, as shown in the following formula: in, Represents each queue Maximum transmission time per frame This represents a business flow. Represents the target queue At the output port The collection of all business flows carried on it. This indicates the transmission time of a single frame in the service flow.

[0040] To further improve the reliability and fairness of the new power system communication network, in the windowed scheduling method for power system communication traffic provided in this application embodiment, the multi-dimensional constraint conditions also include a periodic divisibility constraint. The periodic divisibility constraint is used to set a positive integer divisibility factor for the scheduling period of each target queue, so that the scheduling period satisfies the divisibility relationship with the preset super-period.

[0041] In one or more embodiments of this application, the periodic division constraint can guarantee the divisibility relationship between the scheduling period and the supercycle, ensure that an integer number of windows occur within the supercycle, and generate a regular GCL periodic structure that facilitates end-to-end alignment. The periodic division constraint can be expressed as follows: To further improve the reliability, flexibility, and maintainability of the new power system communication network, in a windowed scheduling method for power system communication traffic provided in this application embodiment, the multi-dimensional constraints also include guardrail constraints. The guardrail constraints are used to deduct a preset guardrail time from the nominal window length when calculating the effective service window length of each target queue.

[0042] In one or more embodiments of this application, if the phases of all flows within the target queue are consistent, then the window start point needs to be aligned according to the service phase, which can be expressed as: in, The offset parameter represents the phase alignment. The scheduling cycle multiplication factor is a non-negative integer.

[0043] Define valid window With available services Considering the guardrail, the available service volume in a single period needs to cover the percentage bandwidth requirement. The guardrail constraint can be expressed as follows: in, Indicates the length of the available service window.

[0044] Guardrail constraints can be represented as: in, The physical duration of the guardrail is expressed in nanoseconds (ns).

[0045] Target queue The "percentage of bandwidth required" can be expressed as: If a certain priority Minimum BE service ratio specified Then for all The queue is now active.

[0046] To further improve the reliability, flexibility, and maintainability of new power system communication networks, in a windowed scheduling method for power system communication traffic provided in this application embodiment, the multi-dimensional constraints also include event-driven constraints. The event-driven constraints are used to ensure that, for a service flow with a local expiration date, the cumulative service volume provided to the queue to which the service flow belongs before the time point corresponding to the local expiration date is equal to or greater than the cumulative data arrival volume of the service flow before that time point.

[0047] In one or more embodiments of this application, for the same output port Sorting by queue index can reduce the space of equivalent solutions and improve search efficiency. The sorting is represented as follows: The total service volume over a supercycle can be expressed as: in, This represents the total service volume over a period of time.

[0048] Assume each business flow The transmission tick is , Then in Internal instance number Then the total arrivals in one supercycle can be expressed as: in, This indicates the business flow The time required for a data frame to complete transmission on a specific output port. This represents the discrete transmission time, corresponding to the transmission tick.

[0049] Define local expiration time for each flow (averaged per hop or default) ), can be expressed as follows: in, Indicates business flow Local time limit of local time limit Indicates business flow Total time budget from sending to receiving Indicates business flow The number of network devices that need to be traversed from the source node to the destination node.

[0050] In time set (Take each instance) On the ), the cumulative arrival volume The following formula represents: make And through linear inequalities and Integer linearization is performed, resulting in the cumulative service volume. It can be represented as: in, Indicates the offset from the start of the window Start to Time t The complete cycle experienced so far The quantity.

[0051] The event-driven constraint means that before the critical "local deadline" time point, the cumulative service should cover the cumulative arrivals, limiting jitter and tail latency. The event-driven constraint is expressed as follows: To further improve the reliability, flexibility, and maintainability of new power system communication networks, in a windowed scheduling method for power system communication traffic provided in this application embodiment, the objective function is expressed as follows: in, Measuring the cost of window normalization Indicates the periodic divisor. This is the fragmentation penalty coefficient. This refers to the output port. Indicates the output port The target queue.

[0052] In one or more embodiments of this application, a weighted linear objective function is designed with bandwidth utilization normalization and period fragmentation as optimization objectives. To avoid fractional functions, auxiliary variables and linearization parameters are used to linearize the window duty cycle, which can be expressed as follows: in, Represents auxiliary variables. This represents the linearization parameter, which can be 1000. A lower bandwidth normalization cost results in more compact scheduling and higher bandwidth utilization; fragmentation penalties can prevent excessive cycle splitting and improve scheduling deployability.

[0053] To further improve the reliability, flexibility, and maintainability of new power system communication networks, a windowed scheduling method for power system communication traffic is provided in an embodiment of this application, see [link to relevant documentation]. Figure 2 Step 200 specifically includes: Step 210: Input the flow data of each of the service flows and the target queues into the objective function corresponding to the preset windowed scheduling model, and solve the scheduling period, window length and window offset corresponding to the power communication network in sequence according to the preset multi-dimensional constraints and the phased variable assignment strategy.

[0054] In one or more embodiments of this application, the model is implemented using a constraint solver, employing a phased variable assignment approach: first, the scheduling period is allocated; then, the window length is allocated; and finally, the window offset is allocated. Combining random offsets and symmetry constraints improves search efficiency. Based on a restart and logging mechanism, Luby restarts are used to avoid local optima, and logs monitor the search process. Solutions are selected based on minimizing the objective function value, and a list of deployable gates is output. The constraint solver can be the constraint solver from Google OR-Tools.

[0055] This application also provides a windowed scheduling system for power system communication traffic, see [link to relevant documentation]. Figure 3 The system includes: The information acquisition module 10 is used to acquire the flow data of multiple service flows in the power communication network and the target queues in the output port of the power communication network. The model solving module 20 is used to solve the objective function corresponding to the preset windowed scheduling model based on the flow data of each of the service flows and each of the target queues, according to preset multi-dimensional constraints, to obtain the optimal scheduling period, window length, and window offset for the power communication network; wherein, the windowed scheduling model consists of multiple decision variables; the multi-dimensional constraints include: window mutual exclusion constraints between each of the target queues on the same port, and service guarantee constraints to ensure minimum service rate for low-priority queues; the objective function is used to jointly optimize bandwidth utilization and scheduling fragmentation. The output module 30 is used to generate and output a gating list for scheduling each service flow in the power communication network based on the optimal scheduling period, window length and window offset corresponding to the power communication network.

[0056] In a specific application example, the windowed scheduling method for power system communication traffic provided in this application models the gated list scheduling problem in the TSN standard as an integer-constrained optimization problem, and constructs a unified modeling framework by combining the multi-dimensional constraint characteristics of the power scenario. The method includes the following steps: Using the switch's microclock as the time scale, if the microclock of the switch where a certain port is located is... (ns), the timeout of this port is (ns), then discretization of the superperiodicity: For each output port and each queue used within that port. Define windowed GCL triplet variables to represent period (ticks), window length (ticks), and phase / offset (ticks), respectively: Enable the "super-periodic divisibility" constraint, and then introduce integers. satisfy: Each queue The maximum transmission time (ns) for a single frame is obtained from the set of streams to which it belongs, where The "minimum available window" is measured in ticks: The guard band is entered as ns and converted to tick for use: queue The "percentage of bandwidth required" (from all flows within it): If a certain priority Minimum BE service ratio specified Then for all The queue is now active.

[0057] For each output port The integer number of valid queues on Define the following decision variables: : Scheduling period (ticks), satisfying ; Window length (ticks) is guaranteed to be no less than the maximum transmission duration in a single session, satisfying the following conditions: ; Window offset (ticks), requirements ; Periodic divisibility factor ,make .

[0058] To ensure the deployability and determinism of the scheduling results, the model introduces the following constraints: Window validity constraints ensure that a window legally exists within a cycle; that is, the window must fall within a cycle to avoid "loopback". Same-port, same-cycle constraint: all queues on the same port share the same scheduling cycle, facilitating hardware programming and gating timing alignment. Periodic divisibility constraints ensure the divisibility between the scheduling period and the supercycle. An integer number of windows are generated, resulting in a regular GCL periodic structure that facilitates end-to-end alignment. If all flows in the queue have the same phase, let its tick value be [value]. Then the window start point needs to be aligned according to the business phase: Define valid window With available services Therefore, after considering the guardrail, the percentage of bandwidth demand that the available service volume in a single cycle needs to cover is: If queue The priority is And configuration This serves as a backup service window for low-priority / best-effort businesses: For the same port Two valid queues ( Introducing binary variables and order Then, windows at the same port must be mutually exclusive, meaning that any two windows must not overlap on a periodic axis: For the same port Sorting by queue index can reduce the space of equivalent solutions and improve search efficiency. The total service volume for one supercycle is: Assume each flow The transmission tick is , Then in Internal instance number Then the total arrivals in one supercycle are: The constraint is that the service capacity must cover at least the amount of data arriving within one supercycle: Define local expiration time for each flow (averaged per hop or default) ): In time set (Take each instance) On the above, define the arrival prefix requirement: make And through linear inequalities and After performing integer linearization, the prefix service quantity is: The constraints are as follows: before the critical "local deadline" time point, the cumulative service should cover the cumulative arrivals, limiting jitter and tail latency: With bandwidth utilization normalization and period fragmentation as optimization objectives, a weighted linear objective function is designed. To avoid fractional functions, auxiliary variables are used. and linearization parameters Linearize the "window duty cycle": The main objective is: in Measuring the cost of window normalization Indicates the periodic divisor. This represents the fragmentation penalty coefficient.

[0059] The objective function means that the smaller the bandwidth normalization cost, the more compact the scheduling and the higher the bandwidth utilization; the fragmentation penalty can avoid excessive cycle segmentation and improve the deployability of scheduling.

[0060] The model can be implemented using Google OR-Tools' constraint solver, employing strategies including: phased variable assignment, first assigning... redistribution Finally, the allocation Heuristic search, combined with random offsets and symmetry constraints, improves search efficiency; Restart and logging mechanisms, using Luby restart to avoid local optima, and logging to monitor the search process; Optimal solution selection, selecting the solution by minimizing the objective function value, and outputting a deployable GCL.

[0061] This application also provides an electronic device, which may include a processor, a memory, a receiver, and a transmitter. The processor is used to execute the windowed scheduling method for power system communication traffic mentioned in the above embodiments. The processor and memory can be connected via a bus or other means, taking a bus connection as an example. The receiver can be connected to the processor and memory via wired or wireless means.

[0062] The processor can be a central processing unit (CPU). The processor can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or combinations of the above types of chips.

[0063] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as the program instructions / modules corresponding to the windowed scheduling method for power system communication traffic in the embodiments of this application. The processor executes various functional applications and data processing by running the non-transitory software programs, instructions, and modules stored in the memory, thereby implementing the windowed scheduling method for power system communication traffic in the above method embodiments.

[0064] The memory may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created by the processor, etc. Furthermore, the memory may include high-speed random access memory and non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory may optionally include memory remotely located relative to the processor, which can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0065] The one or more modules are stored in the memory, and when executed by the processor, they perform the windowed scheduling method for power system communication traffic in the implementation embodiment.

[0066] In some embodiments of this application, the user equipment may include a processor, a memory, and a transceiver unit. The transceiver unit may include a receiver and a transmitter. The processor, memory, receiver, and transmitter may be connected via a bus system. The memory is used to store computer instructions, and the processor is used to execute the computer instructions stored in the memory to control the transceiver unit to send and receive signals.

[0067] As one implementation method, the functions of the receiver and transmitter in this application can be implemented by transceiver circuits or dedicated transceiver chips, and the processor can be implemented by dedicated processing chips, processing circuits or general-purpose chips.

[0068] As another implementation approach, the server provided in this application embodiment can be implemented using a general-purpose computer. That is, the program code implementing the processor, receiver, and transmitter functions is stored in memory, and the general-purpose processor implements the processor, receiver, and transmitter functions by executing the code in memory.

[0069] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the aforementioned windowed scheduling method for power system communication traffic. The computer-readable storage medium can be a tangible storage medium, such as random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, floppy disks, hard disks, removable storage disks, CD-ROMs, or any other form of storage medium known in the art.

[0070] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the aforementioned windowed scheduling method for power system communication traffic.

[0071] Those skilled in the art will understand that the exemplary components, systems, and methods described in conjunction with the embodiments disclosed herein can be implemented in hardware, software, or a combination of both. Whether implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application. When implemented in hardware, it can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. The programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave.

[0072] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0073] In this application, features described and / or illustrated for one embodiment may be used in the same or similar manner in one or more other embodiments, and / or combined with or in place of features of other embodiments.

[0074] The above description is merely a preferred embodiment of this application and is not intended to limit this application. For those skilled in the art, various modifications and variations can be made to the embodiments of this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for windowed scheduling of power system communication traffic, characterized by, The method includes: Acquire the stream data of multiple service flows in the power communication network and the target queues in the output port of the power communication network; Based on the flow data of each of the aforementioned service flows and each of the aforementioned target queues, the objective function corresponding to the preset windowed scheduling model is solved according to preset multi-dimensional constraints to obtain the optimal scheduling period, window length, and window offset for the power communication network. The windowed scheduling model consists of multiple decision variables. The multi-dimensional constraints include: mutual exclusion constraints between target queues on the same port, and service guarantee constraints to ensure minimum service rate for low-priority queues. The objective function is used to jointly optimize bandwidth utilization and scheduling fragmentation. Based on the optimal scheduling period, window length, and window offset corresponding to the power communication network, a gating list for scheduling each service flow in the power communication network is generated and output.

2. The method of claim 1, wherein, The decision variables include: the scheduling period, window length, window offset, and period divisibility factor of each target queue in each output port.

3. The method of claim 2, wherein, The multi-dimensional constraints also include a periodic divisibility constraint, which is used to set a positive integer divisibility factor for the scheduling period of each target queue, so that the scheduling period satisfies the divisibility relationship with the preset super-period.

4. The method of claim 3, wherein, The multi-dimensional constraints also include a guardrail constraint, which is used to subtract a preset guardrail time from the nominal window length when calculating the effective service window length of each target queue.

5. The method of claim 1, wherein, The multi-dimensional constraints also include event-driven constraints, which are used to ensure that, for a business flow with a local expiration date, the cumulative service volume provided to the queue to which the business flow belongs before the time point corresponding to the local expiration date is equal to or greater than the cumulative data arrival volume of the business flow before that time point.

6. The method of claim 3, wherein, The objective function is expressed as follows: in, Measuring the cost of window normalization Indicates the periodic divisor. This is the fragmentation penalty coefficient. This refers to the output port. Indicates the output port The target queue.

7. The method according to claim 1, characterized in that, The process involves solving a pre-defined objective function corresponding to a pre-defined windowed scheduling model based on the flow data of each of the service flows and each of the target queues, according to pre-defined multi-dimensional constraints, to obtain the optimal scheduling period, window length, and window offset for the power communication network, including: The flow data of each of the service flows and each of the target queues are input into the objective function corresponding to the preset windowed scheduling model. Based on the preset multi-dimensional constraints and the phased variable assignment strategy, the scheduling period, the window length and the window offset corresponding to the power communication network are solved sequentially.

8. A window-based dispatching system for power system communication traffic, characterized in that, The system includes: The information acquisition module is used to acquire the stream data of multiple service flows in the power communication network and the target queues in the output port of the power communication network. The model solving module is used to solve the objective function corresponding to the preset windowed scheduling model based on the flow data of each of the service flows and each of the target queues, according to preset multi-dimensional constraints, to obtain the optimal scheduling period, window length, and window offset for the power communication network; wherein, the windowed scheduling model consists of multiple decision variables; the multi-dimensional constraints include: window mutual exclusion constraints between each of the target queues on the same port, and service guarantee constraints to ensure minimum service rate for low-priority queues; the objective function is used to jointly optimize bandwidth utilization and scheduling fragmentation. The output module is used to generate and output a gating list for scheduling each service flow in the power communication network based on the optimal scheduling period, window length and window offset corresponding to the power communication network.

9. An electronic device, characterized in that, It includes a processor and a memory; when the processor executes the running program stored in the memory, it implements the windowed scheduling method for power system communication traffic as described in claims 1 to 7.

10. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by a processor, implements the windowed scheduling method for power system communication traffic as described in claims 1 to 7.

Images