Composite network flow flexible scheduling method and system based on service priority

Abstract

The invention belongs to the technical field of electric power Internet of Things communication, and discloses a flexible scheduling method and system for composite network traffic based on service priorities, and the method comprises the steps: distributing data packets of each node in a power grid scene to a high priority queue, a middle priority queue and a low priority queue according to service types; the data packets are automatically distributed to corresponding priority queues according to the service types of the data packets, and when the number of the data packets in the low or medium priority queue exceeds a backpressure threshold value, part of the data packets are moved to the high priority queue; when remaining time slots still exist after all the data packets of the high-priority queue are transmitted, the remaining time slots are distributed to the medium-priority queue and the low-priority queue according to a preset proportion; and according to the back pressure state of each queue, carrying out priority rollback or lifting adjustment on the queues which continuously exceed the threshold value. Through hierarchical management, a core service exclusively occupies a high-priority queue and preemptive transmission is realized, millisecond-level real-time response is ensured, meanwhile, residual bandwidth is dynamically allocated to low-priority data, and the problems of resource competition and delay caused by traditional static allocation are solved.

Description

Technical Field

[0001] This invention belongs to the field of power Internet of Things communication technology, and specifically relates to a method and system for flexible scheduling of composite network traffic based on service priority. Background Technology

[0002] With the continuous development of power systems and the sustained increase in electricity demand, new power systems have become the core development trend of the future power industry. As an important component of these new power systems, converter stations / substations play a crucial role, not only undertaking power conversion and dispatch tasks but also carrying out data collection and transmission for a large number of IoT sensing devices. Converter stations / substations integrate various sensing devices for real-time monitoring of the power grid's operating status and rely on network communication for data exchange. However, with the increase in monitoring equipment and data traffic, existing data dispatching mechanisms are gradually revealing limitations in complex network environments, mainly in the following aspects: First, network congestion is becoming increasingly prominent. The high concurrency, low latency, and high reliability data requirements of converter stations / substations conflict with the traditional static resource allocation model. Sudden data flows can easily lead to delays or loss of critical services. In particular, when a fault occurs, a large amount of alarm data floods in, and existing mechanisms are unable to respond in a timely manner, affecting the stable operation of the system.

[0003] Secondly, uneven resource allocation affects service quality. Fixed-bandwidth architectures lack flexibility and cannot be dynamically adjusted according to real-time demand, causing delays in critical data streams due to insufficient bandwidth, while low-priority data consumes excessive resources. For example, resource contention between status monitoring data and scheduling instructions may delay the transmission of emergency instructions.

[0004] Finally, the business priority management mechanism is inadequate. The existing solution fails to finely differentiate the urgency of data, with high-priority services (fault alarms, scheduling instructions) sharing limited resources with low-priority data (status reports), reducing emergency response capabilities. The failure to prioritize the transmission of important instructions may affect the timeliness of fault handling.

[0005] Furthermore, there is a lack of dynamic resource allocation and priority scheduling mechanisms adapted to network communication. The existing mechanisms have not developed resource allocation strategies that adjust in real time for network communication scenarios, nor have they formed dynamic scheduling rules linked to business priorities. This results in an inability to quickly adapt to fluctuations in network load, further exacerbating resource waste and disruptions to critical business transmissions.

[0006] Existing scheduling mechanisms typically rely on cloud computing platforms for centralized data sharing or add edge computing devices in the cloud for preprocessing, but they have significant shortcomings: static bandwidth strategies struggle to cope with congestion caused by high-concurrency traffic, especially leading to delays in critical data during sudden failures; fixed allocation rules cannot adapt to real-time demand changes, with low-priority data crowding out bandwidth for high-priority tasks; and lax service hierarchy management results in critical data such as fault alarms not receiving transmission guarantees, increasing system risk. Traditional static scheduling mechanisms are ill-suited to handle the massive heterogeneous traffic from converter stations / substations and their complex requirements. Summary of the Invention

[0007] The purpose of this invention is to provide a flexible scheduling method and system for composite network traffic based on service priority, so as to solve the problem that existing technologies are unable to cope with congestion caused by high concurrent traffic, resulting in delays in critical data and difficulty in ensuring transmission.

[0008] To achieve the above objectives, the present invention adopts the following technical solution: In a first aspect, the present invention provides a flexible scheduling method for composite network traffic based on service priorities, comprising: In the power grid scenario, data packets for each node are allocated to three priority queues: high, medium, and low, based on their service type. When a data packet arrives at a node, it is automatically assigned to the corresponding priority queue based on its service type. When the number of data packets in a low or medium priority queue exceeds the back pressure threshold, some data packets are moved to a high priority queue. If there are still remaining time slots after all data packets of the high-priority queue have been transmitted within each scheduling cycle, the remaining time slots will be allocated to the medium and low-priority queues according to a preset ratio. At the end of each scheduling cycle, based on the back pressure status of each queue, priority rollback or promotion is adjusted for queues that continuously exceed the threshold.

[0009] Furthermore, the allocation of data packets in the power grid scenario to high, medium, and low priority queues according to service type includes: The queues of each node in the power grid multi-electro-interconnected sensing device are initialized. Priority queues are set up and capacity and back pressure thresholds are determined based on the real-time requirements of different power grid services. Three priority queues are set up within each node: Priority 1 queue... Priority 2 queue and priority 3 queue Each queue has a preset initial capacity. and back pressure threshold ,in, Less than ; Used to store real-time data packets. Used to store remote, non-real-time data packets. Used to store local non-real-time data packets.

[0010] Furthermore, when a data packet arrives at the node, it is automatically assigned to the corresponding priority queue based on its service type. When the number of data packets in the low or medium priority queue exceeds the back pressure threshold, some data packets are moved to the high priority queue, including: During the initialization phase, the PCTSA (Composite Network Traffic Scheduling Algorithm) based on service priority awareness is used to assign time slot weights to each queue and set priority scheduling policies. When the queue capacity reaches a threshold... At this time, the priority promotion mechanism is activated, moving the data packet from the low-priority queue. , Move to .

[0011] Furthermore, when a data packet arrives, it is assigned to the corresponding priority queue based on its type; if the number of data packets exceeds its backpressure threshold... Activate the priority boosting mechanism to move some data packets from this queue to... Queue; calculate the number of packets removed using the following formula. :

[0012] in, This indicates the remaining capacity in the current queue. express The current number of data packets in the queue; The queue is processed as follows: .

[0013] Furthermore, when there are still remaining time slots after all data packets of the high-priority queue have been transmitted within each scheduling cycle, the remaining time slots are allocated to the medium and low-priority queues according to a preset ratio, including: Time slots are allocated based on priority queue status, prioritizing real-time data transmission, and distributing any remaining time slots proportionally to lower priority queues. First, the priority 1 queue Data packets in the specified location will be sent with priority, if in If there are remaining time slots during the transmission process of the queue, these remaining time slots will be allocated proportionally. and queue: when All data packets in the queue have been transmitted, and there is still remaining transmission time. The remaining time will be allocated proportionally. and Data packets in the queue; during the scheduling period, The data packets in the queue have exhausted their transmission time slots. and The queue of data packets will no longer be transmitted during this period.

[0014] Furthermore, at the end of each scheduling cycle, based on the backpressure status of each queue, priority rollback or promotion adjustment is performed on queues that continuously exceed the threshold, including: At the end of each scheduling cycle, the system checks the queue status and performs priority adjustments on queues that exceed the backpressure threshold. or If the number of packets in a queue exceeds the backpressure threshold, the system will move some packets from these queues to another queue. In queues, priority promotion operations follow these rules: The number of packets removed each time ensures The queue will not overflow; The priority promotion operation stops when the number of remaining packets in the queue falls below the backpressure threshold after the packets are removed. Queue adjustments are achieved using the following formula:

[0015]

[0016] in, and They represent and The remaining capacity of the queue, express The capacity already occupied in the queue.

[0017] Furthermore, after all data packets have been scheduled and transmitted, the queue status is checked, and scheduling is terminated when all queues are empty and there are no new data packets. , , The queues are all empty and there are no new data packets to process, so the scheduling terminates and the current scheduling process is complete.

[0018] Secondly, the present invention provides a flexible scheduling system for composite network traffic based on service priorities, comprising: The queue partitioning module is used to allocate data packets of each node in the power grid scenario to three priority queues: high, medium, and low, according to the service type. The priority enhancement module is used to automatically allocate data packets to the corresponding priority queue according to their service type when they arrive at the node. When the number of data packets in the low or medium priority queue exceeds the back pressure threshold, some data packets will be moved to the high priority queue. The priority allocation module is used to allocate the remaining time slots to the medium and low priority queues according to a preset ratio when there are still remaining time slots after all data packets of the high priority queue have been transmitted in each scheduling cycle. The output adjustment module is used to adjust the priority of queues that continuously exceed the threshold at the end of each scheduling cycle, based on the back pressure status of each queue.

[0019] Furthermore, the allocation of data packets in the power grid scenario to high, medium, and low priority queues according to service type includes: The queues of each node in the power grid multi-electro-interconnected sensing device are initialized. Priority queues are set up and capacity and back pressure thresholds are determined based on the real-time requirements of different power grid services. Three priority queues are set up within each node: Priority 1 queue... Priority 2 queue and priority 3 queue Each queue has a preset initial capacity. and back pressure threshold ,in, Less than ; Used to store real-time data packets. Used to store remote, non-real-time data packets. Used to store local non-real-time data packets.

[0020] Furthermore, when a data packet arrives at the node, it is automatically assigned to the corresponding priority queue based on its service type. When the number of data packets in the low or medium priority queue exceeds the back pressure threshold, some data packets are moved to the high priority queue, including: During the initialization phase, the PCTSA (Composite Network Traffic Scheduling Algorithm) based on service priority awareness is used to assign time slot weights to each queue and set priority scheduling policies. When the queue capacity reaches a threshold... At this time, the priority promotion mechanism is activated, moving the data packet from the low-priority queue. , Move to .

[0021] Furthermore, when a data packet arrives, it is assigned to the corresponding priority queue based on its type; if the number of data packets exceeds its backpressure threshold... Activate the priority boosting mechanism to move some data packets from this queue to... Queue; calculate the number of packets removed using the following formula. :

[0022] in, This indicates the remaining capacity in the current queue. express The current number of data packets in the queue; The queue is processed as follows: .

[0023] Furthermore, when there are still remaining time slots after all data packets of the high-priority queue have been transmitted within each scheduling cycle, the remaining time slots are allocated to the medium and low-priority queues according to a preset ratio, including: Time slots are allocated based on priority queue status, prioritizing real-time data transmission, and distributing any remaining time slots proportionally to lower priority queues. First, the priority 1 queue Data packets in the specified location will be sent with priority, if in If there are remaining time slots during the transmission process of the queue, these remaining time slots will be allocated proportionally. and queue: when All data packets in the queue have been transmitted, and there is still remaining transmission time. The remaining time will be allocated proportionally. and Data packets in the queue; during the scheduling period, The data packets in the queue have exhausted their transmission time slots. and The queue of data packets will no longer be transmitted during this period.

[0024] Furthermore, at the end of each scheduling cycle, based on the backpressure status of each queue, priority rollback or promotion adjustment is performed on queues that continuously exceed the threshold, including: At the end of each scheduling cycle, the system checks the queue status and performs priority adjustments on queues that exceed the backpressure threshold. or If the number of packets in a queue exceeds the backpressure threshold, the system will move some packets from these queues to another queue. In queues, priority promotion operations follow these rules: The number of packets removed each time ensures The queue will not overflow; The priority promotion operation stops when the number of remaining packets in the queue falls below the backpressure threshold after the packets are removed. Queue adjustments are achieved using the following formula:

[0025]

[0026] in, and They represent and The remaining capacity of the queue, express The capacity already occupied in the queue.

[0027] Furthermore, after all data packets have been scheduled and transmitted, the queue status is checked, and scheduling is terminated when all queues are empty and there are no new data packets. , , The queues are all empty and there are no new data packets to process, so the scheduling terminates and the current scheduling process is complete.

[0028] Thirdly, the present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the flexible scheduling method for composite network traffic based on service priority.

[0029] Fourthly, the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the flexible scheduling method for composite network traffic based on service priorities.

[0030] Compared with the prior art, the present invention has the following technical effects: This invention employs priority queue scheduling, which allocates data packets in the power grid scenario to three priority queues—high, medium, and low—according to their service type. Real-time service data packets are given priority to enter the high-priority queue, non-real-time remote data packets are entered into the medium-priority queue, and non-real-time local data packets are entered into the low-priority queue. Dynamic resource allocation is achieved through the time-slice allocation mechanism of the PCTSA algorithm. In each scheduling cycle, high-priority queue data packets are transmitted first. After their time slices are used up, the remaining time slices are allocated to medium and low-priority queues proportionally. Priority promotion and rollback mechanisms are set up. When the backlog of low-priority queue data packets exceeds the threshold, they are automatically promoted to high-priority queues. At the same time, the rollback mechanism avoids excessive congestion in high-priority queues. Flexible queue management is adopted within the node, and queue capacity and backpressure threshold are dynamically adjusted. When the number of data packets in a certain queue exceeds the threshold, some data packets are transferred or the priority is adjusted to optimize the flow of data packets between queues.

[0031] By rationally allocating bandwidth resources while ensuring the real-time performance of high-priority services, avoiding network congestion, improving data transmission flexibility and efficiency, reducing low-priority data packet latency, enhancing system response speed and reliability, and strengthening the power IoT network traffic scheduling capabilities, this architecture optimizes the allocation of broadband and narrowband network resources based on the power grid's load dynamic adjustment scheduling strategy, ensuring efficient transmission of service traffic. Nodes within the power grid collaborate through data exchange and routing modules to guarantee efficient data transmission and priority scheduling within the power dispatching system. This architecture can meet the data sensing, transmission, and scheduling needs of diverse IoT devices in the power system, improving real-time performance and efficiency. Attached Figure Description

[0032] Figure 1 This is a network architecture for sharing and scheduling multi-dimensional IoT sensing data in the power grid.

[0033] Figure 2 A logical block diagram of the flexible scheduling mechanism for the final flow of the power grid composite network.

[0034] Figure 3 The average queue waiting time for messages under different service flow arrival rates.

[0035] Figure 4 The average packet wait time under different traffic allocations.

[0036] Figure 5 This is a flowchart. Detailed Implementation

[0037] The present invention will be further described below with reference to the accompanying drawings: Example 1, please refer to Figure 5 This invention provides a flexible scheduling method for composite network traffic based on service priorities, comprising: In the power grid scenario, data packets for each node are allocated to three priority queues: high, medium, and low, based on their service type. When a data packet arrives at a node, it is automatically assigned to the corresponding priority queue based on its service type. When the number of data packets in a low or medium priority queue exceeds the back pressure threshold, some data packets are moved to a high priority queue. If there are still remaining time slots after all data packets of the high-priority queue have been transmitted within each scheduling cycle, the remaining time slots will be allocated to the medium and low-priority queues according to a preset ratio. At the end of each scheduling cycle, based on the back pressure status of each queue, priority rollback or promotion is adjusted for queues that continuously exceed the threshold.

[0038] This solution introduces a three-layer priority queue scheduling mechanism, prioritizing the processing of real-time data (such as emergency alarms and equipment status monitoring) for core services like power dispatch instructions and fault alarms. Real-time data is automatically allocated to the highest priority queue, meeting the power grid's millisecond-level response requirements for critical services and ensuring low-latency transmission in high-traffic scenarios. In high-concurrency IoT data environments within the power grid, this design effectively avoids real-time data loss caused by network congestion, significantly improving security and reliability.

[0039] When data packets in a low-priority queue reach the backpressure threshold, priority is increased using the PCTSA algorithm. This mechanism is adapted to scenarios of sudden power grid failures causing a surge in data, avoiding the backlog and loss of low-priority data, ensuring complete data transmission during system overload, and enhancing the power grid's service adaptability in broadband and narrowband hybrid networks.

[0040] By employing priority queuing and precise time slot allocation, combined with the characteristics of the power grid's composite network, high-priority services such as remote control commands are transmitted first, while ensuring conflict-free transmission of low-priority data such as equipment status monitoring. This mechanism reduces resource waste and latency accumulation caused by concurrent multi-service operations in the power grid, thereby improving system throughput and response speed.

[0041] This solution addresses the complex electromagnetic environment of the power grid and the fault characteristics of high-frequency equipment. Through a dynamic resource scheduling strategy, it prioritizes critical services during periods of surge in network load or partial outages, thereby mitigating network congestion and data loss in real time and ensuring the stable operation of the power grid under extreme operating conditions.

[0042] Example 2: The present invention provides a flexible scheduling method for composite network traffic based on service priority, comprising: This invention relates to the field of power Internet of Things (IoT) communication technology, and proposes a flexible scheduling method for composite network traffic based on service priority. It achieves efficient scheduling and management of data traffic from multiple power IoT sensing devices through a Priority-Aware Composite Network Traffic Scheduling Algorithm (PCTSA). The specific implementation scheme is as follows: Priority queue scheduling is adopted to allocate data packets in the power grid scenario to three priority queues: high, medium and low priority, according to the service type. Real-time service data packets enter the high priority queue first, non-real-time remote data packets enter the medium priority queue, and non-real-time local data packets enter the low priority queue. Dynamic resource allocation is achieved through the time-slice allocation mechanism of the PCTSA algorithm. In each scheduling cycle, high-priority queue data packets are transmitted first. After their time slices are used up, the remaining time slices are allocated to medium and low-priority queues proportionally. Priority promotion and rollback mechanisms are set up. When the backlog of low-priority queue data packets exceeds the threshold, they are automatically promoted to high-priority queues. At the same time, the rollback mechanism avoids excessive congestion in high-priority queues. Flexible queue management is adopted within the node, and queue capacity and backpressure threshold are dynamically adjusted. When the number of data packets in a certain queue exceeds the threshold, some data packets are transferred or the priority is adjusted to optimize the flow of data packets between queues.

[0043] The network architecture of the power grid multi-electro-IoT sensing device designed in this patent is as follows: Figure 1 As shown. This architecture includes multiple IoT sensing nodes, each with three priority queues ( , , These are used to store real-time business data, remote non-real-time data, and local non-real-time data, respectively. Using the PCTSA scheduling algorithm, each node in the power grid dynamically schedules data packets based on data priority and queue status, ensuring that real-time data is processed first in the priority queue, while fairly allocating remaining bandwidth to low-priority data, thus guaranteeing the stable operation of the power dispatching system. The power grid network management platform is responsible for centralized monitoring and management of the status of each node, dynamically adjusting the scheduling strategy based on the power grid load, optimizing the allocation of broadband and narrowband network resources, and ensuring efficient transmission of business traffic. Nodes within the power grid collaborate through data exchange and routing modules to ensure efficient data transmission and priority scheduling within the power dispatching system. This architecture enables the data sensing, transmission, and scheduling needs of various IoT devices in the power system, improving the system's real-time performance and efficiency.

[0044] Specifically, it includes: Step 1: Initialize queues and scheduling parameters In step one, the queues of each node in the power grid's multi-electro-interconnected sensing device are first initialized. Based on the real-time requirements of different power grid services, three priority queues are set up, and their capacities and backpressure thresholds are determined. Simultaneously, the system assigns time slot weights to each queue and sets a priority scheduling strategy to ensure that real-time data is transmitted preferentially.

[0045] Based on the real-time requirements of different power grid services, priority queues are set up and capacity and back pressure thresholds are determined. Three priority queues are set up within each node: Priority 1 queue (… Priority 2 queue ( ) and priority 3 queue ( Each queue has a preset initial capacity. and back pressure threshold ,in, Less than . Specifically, Used to store real-time data packets. Used to store remote, non-real-time data packets. It is used to store local non-real-time data packets.

[0046] During the initialization phase, time slot weights are assigned to each queue, and a priority scheduling strategy is set to ensure that real-time data transmission has a high priority. For example, suppose... The maximum capacity is 10. and Each queue has a maximum capacity of 20. When the queue capacity reaches the threshold... When this happens, the system will activate the priority promotion mechanism, moving data packets from the low-priority queue ( , Move to .

[0047] Step 2: Packet Allocation and Priority Boosting Mechanism In step two, the system allocates queues according to data packet type and activates a priority boosting mechanism when the queue capacity exceeds the back pressure threshold to dynamically adjust the data packet distribution.

[0048] When a data packet arrives, the system allocates it to the corresponding priority queue based on its type (real-time or non-real-time). For example, real-time service data packets will be allocated to... Remote non-real-time data packets are assigned to Local non-real-time data packets then enter queue.

[0049] If the number of packets in a queue exceeds its backpressure threshold ( The system will activate a priority boosting mechanism, moving some data packets from this queue to... Queues. For example, suppose... The number of packets in the queue exceeds 13 ( The system will then redirect some data packets from... Move to Calculate the number of packets removed using the following formula. :

[0050] in, This indicates the remaining capacity in the current queue. express The current number of packets in the queue. Similarly, The queue is processed as follows:

[0051] By dynamically adjusting the distribution of data packets in the queue, it is ensured that real-time data packets are transmitted with priority.

[0052] Step 3: Time Slot Allocation and Data Transmission In step three, the system allocates time slots based on the priority queue status, prioritizing real-time data transmission and allocating any remaining time slots proportionally to lower priority queues.

[0053] In actual data transmission, the system allocates time slots based on the status of the power grid priority queue. First, the priority 1 queue ( Data packets in the specified range will be sent with priority to ensure the transmission of real-time data. If in If there are remaining time slots during the transmission process of the queue, these remaining time slots will be allocated proportionally. and queue.

[0054] Specifically, if All data packets in the queue have been transmitted, and there is still remaining transmission time. The system will allocate the remaining time proportionally. and The data packets in the queue are ensured to receive appropriate transmission opportunities, even for low-priority packets. If, within a given scheduling cycle, The data packets in the queue have exhausted their transmission time slots. and Data packets in the queue will not be transmitted during this period. This is done to ensure that the priority of real-time data is fully guaranteed.

[0055] In addition, the system periodically evaluates the queue status and checks whether priority adjustments are needed to ensure that the latency of real-time data transmission is not affected by low-priority packets.

[0056] Step 4: Queue Backpressure and Priority Adjustment In step four, the system checks the queue status at the end of each scheduling cycle and performs priority adjustment on queues that exceed the back pressure threshold to ensure that real-time data transmission is not blocked.

[0057] At the end of each scheduling cycle, the system checks the status of each priority queue, especially checking for queue backpressure. If or If the number of packets in a queue exceeds the backpressure threshold, the system will move some packets from these queues to another queue. A queue is used to ensure that the transmission of real-time data is not blocked. This priority promotion operation follows these rules: The number of packets removed each time must be ensured The queue will not overflow.

[0058] The priority promotion operation will only stop when the number of remaining packets in the queue is below the backpressure threshold after the removed packets.

[0059] The specific queue adjustments are implemented using the following formula:

[0060]

[0061] in, and They represent and The remaining capacity of the queue, express The system dynamically adjusts the queue's state to ensure that high-priority data is transmitted promptly.

[0062] Step 5: Termination Condition and Algorithm End In step five, after the system has completed the scheduling and transmission of all data packets, it checks the queue status. When all queues are empty and there are no new data packets, the scheduling algorithm is terminated.

[0063] After all data packets have been scheduled and transmitted, the system checks the status of each queue to ensure that critical power grid business data has been successfully transmitted. If , , When all queues are empty and no new data packets need to be processed, the scheduling algorithm will terminate, completing this scheduling process.

[0064] Figure 2 The core processes of this patent's implementation scheme are demonstrated, including network initialization, node registration, data sharing requests, traffic scheduling, and data transmission. The entire process is coordinated by proxy nodes, uses federated learning for data simplification, and employs a consensus mechanism to ensure data consistency. Furthermore, it utilizes the widely used and practical AES (Advanced Encryption Standard) encryption technology to guarantee the security of data transmission.

[0065] Figure 3 The average latency of packets within a node was simulated under different service arrival rates in a power grid scenario. Service arrival rates ranged from 14.4 to 33.6 kbps. Simulation results are as follows: Figure 3As shown, the average waiting time of all three scheduling algorithms increases with the increase in traffic arrival rate. This is because the utilization rate of the ready queue within a node also increases with the increase in service arrival rate. Therefore, the number of packets in the queue increases, indicating that individual packets need to wait additional time to complete service. Since the PCTSA scheduling algorithm not only allocates packets to different ready queues according to service priority, but also dynamically adjusts their position in the ready queue according to the number of backlogged packets, low-priority packets with multiple backlogs can obtain service earlier. Therefore, compared with the First Come First Service (FCFS) and Dynamic Multilevel Priority (DMP) algorithms, the PCTSA algorithm has the smoothest growth trend and the smallest average waiting time. Under the simulation condition of a transmission rate of 33.6 kbps, the average waiting time of packets within a node under the PAS algorithm scheduling is only 67% of that of the DMP algorithm.

[0066] Figure 4 The queuing times of three scheduling algorithms in a power grid scenario were simulated under different traffic flow ratios. The traffic flow ratio gradually increased from 1:1:1 to 1:1:2 to simulate a burst scenario of low-priority traffic. The simulation results are as follows: Figure 5 As shown, compared with DMP and FCFS methods, the PCTSA algorithm can still guarantee a low queue waiting time under the condition of non-real-time service bursts, and can take into account the latency requirements of both real-time and non-real-time packets. It solves the starvation problem of low-priority service packets not receiving service for a long time.

[0067] Example 3: This invention uses an ±800kV UHV digital converter station as a typical application scenario, deploying a flexible scheduling scheme for composite network traffic based on service priorities. This scheme is used for the scheduling and transmission of massive amounts of data collected by various IoT sensing devices within the station, especially for the efficient interaction of multiple types of data such as voltage and current monitoring data and remote control commands. During implementation, each node of the converter station is equipped with a scheduling system that supports dynamic resource allocation. Based on the real-time requirements of the services, the system divides the data flow into three categories: real-time services, remote non-real-time services, and local non-real-time services. These are stored in priority queues 1, 2, and 3, respectively, and differentiated capacity and back pressure thresholds are set for each queue. Corresponding time slot weights are also assigned to ensure that real-time data transmission has the highest priority.

[0068] When a converter station generates data transmission requests, the system first intelligently allocates data packets based on their type. For example, real-time service data such as fault alarms is directly stored in priority queue 1, while remote, non-real-time data such as equipment status inspections is stored in priority queue 2. If the data volume in priority queue 2 or 3 exceeds the backpressure threshold, the system immediately activates a priority boosting mechanism, transferring some data to priority queue 1 to accelerate transmission. During the data transmission phase, the system prioritizes sending data packets to priority queue 1. If there are still packets remaining after transmission, they are proportionally allocated to lower priority queues. At the end of each scheduling cycle, the system comprehensively checks the queue status, dynamically adjusting priorities and resource allocation until all queues are empty and no new data is pending processing. Ultimately, this achieves millisecond-level response for critical services and complete transmission of all data, significantly improving the data scheduling efficiency of the converter station and the stability of network operation.

[0069] This invention addresses the characteristics of high-concurrency IoT data in power grids by designing a three-layer priority queue (real-time services, remote non-real-time, and local non-real-time). Through refined hierarchical management, core services (such as fault alarms and scheduling instructions) are exclusively assigned to high-priority queues and transmitted preemptively, ensuring millisecond-level real-time response. At the same time, the remaining bandwidth is dynamically allocated to low-priority data, solving the resource contention and latency problems caused by traditional static allocation.

[0070] Adapted to scenarios involving sudden power grid failures and data surges at converter stations / substations, this mechanism automatically elevates backlogged data to the highest priority queue for transmission when the backlog of low-priority queue data exceeds the back pressure threshold. This avoids data loss due to localized network overload, ensuring the integrity and timeliness of all business data under extreme operating conditions.

[0071] By considering the complex electromagnetic environment of the power grid, the system dynamically adjusts the capacity of each priority queue and triggers data migration by monitoring queue backpressure thresholds (such as queue occupancy trigger values) in real time. When a low-priority queue approaches overflow, it automatically expands its capacity or transfers data packets to an idle queue to prevent congestion from spreading to a single queue and enhances the system's robustness against sudden traffic surges.

[0072] Designed specifically for the hybrid broadband and narrowband network architecture of the power grid, it dynamically divides transmission time slots based on the PCTSA algorithm: core time slots are prioritized for high-priority real-time services, and the remaining time slots are allocated proportionally to medium and low-priority queues. Through dynamic optimization of time slot weights, it achieves highly reliable transmission of critical instructions in narrowband channels and balanced load balancing of large-volume data in broadband channels.

[0073] To address the multi-scale equipment access requirements of the power grid, a real-time network load perception and elastic resource allocation model is established. During high loads or partial outages, low-priority service bandwidth is automatically reduced while prioritizing core control links; during steady-state operation, redundant resources are dynamically released, supporting seamless switching between multiple modes from routine monitoring to emergency response, thereby improving resource utilization and system resilience.

[0074] In another embodiment of the present invention, a flexible scheduling system for composite network traffic based on service priority is provided, which can be used to implement the above-mentioned flexible scheduling method for composite network traffic based on service priority. Specifically, the system includes: The queue partitioning module is used to allocate data packets of each node in the power grid scenario to three priority queues: high, medium, and low, according to the service type. The priority enhancement module is used to automatically allocate data packets to the corresponding priority queue according to their service type when they arrive at the node. When the number of data packets in the low or medium priority queue exceeds the back pressure threshold, some data packets will be moved to the high priority queue. The priority allocation module is used to allocate the remaining time slots to the medium and low priority queues according to a preset ratio when there are still remaining time slots after all data packets of the high priority queue have been transmitted in each scheduling cycle. The output adjustment module is used to adjust the priority of queues that continuously exceed the threshold at the end of each scheduling cycle, based on the back pressure status of each queue.

[0075] The module division in this embodiment of the invention is illustrative and represents only one logical functional division. In actual implementation, other division methods may be used. Furthermore, the functional modules in the various embodiments of the invention can be integrated into a single processor, exist as separate physical entities, or be integrated into a single module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0076] In another embodiment of the present invention, a computer device is provided, comprising a processor and a memory. The memory stores a computer program, which includes program instructions. The processor executes the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or 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, etc. It is the computing and control core of the terminal, suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions from the computer storage medium to achieve a corresponding method flow or function. The processor described in this embodiment of the present invention can be used for the operation of a flexible scheduling method for composite network traffic based on service priorities.

[0077] In another embodiment of the present invention, a storage medium is provided, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device used to store programs and data. It is understood that the computer-readable storage medium here can include both the built-in storage medium in the computer device and extended storage media supported by the computer device. The computer-readable storage medium provides storage space that stores the terminal's operating system. Furthermore, the storage space also stores one or more instructions suitable for loading and execution by a processor. These instructions can be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here can be high-speed RAM or non-volatile memory, such as at least one disk storage device. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the flexible scheduling method for composite network traffic based on service priorities in the above embodiments.

[0078] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0079] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0080] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0081] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0082] 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 it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A flexible scheduling method for composite network traffic based on service priority, characterized in that, include: In the power grid scenario, data packets for each node are allocated to three priority queues: high, medium, and low, based on their service type. When a data packet arrives at a node, it is automatically assigned to the corresponding priority queue based on its service type. When the number of data packets in a low or medium priority queue exceeds the back pressure threshold, some data packets are moved to a high priority queue. If there are still remaining time slots after all data packets of the high-priority queue have been transmitted within each scheduling cycle, the remaining time slots will be allocated to the medium and low-priority queues according to a preset ratio. At the end of each scheduling cycle, based on the back pressure status of each queue, priority rollback or promotion is adjusted for queues that continuously exceed the threshold.

2. The flexible scheduling method for composite network traffic based on service priority according to claim 1, characterized in that, The method of allocating data packets in the power grid scenario to high, medium, and low priority queues according to service type includes: The queues of each node in the power grid multi-electro-interconnected sensing device are initialized. Priority queues are set up and capacity and back pressure thresholds are determined based on the real-time requirements of different power grid services. Three priority queues are set up within each node: Priority 1 queue... Priority 2 queue and priority 3 queue Each queue has a preset initial capacity. and back pressure threshold ,in, Less than ; Used to store real-time data packets. Used to store remote, non-real-time data packets. Used to store local non-real-time data packets.

3. The flexible scheduling method for composite network traffic based on service priority according to claim 1, characterized in that, When a data packet arrives at a node, it is automatically assigned to the corresponding priority queue based on its service type. When the number of data packets in a low or medium priority queue exceeds the back pressure threshold, some data packets are moved to a high priority queue, including: During the initialization phase, the PCTSA (Composite Network Traffic Scheduling Algorithm) based on service priority awareness is used to assign time slot weights to each queue and set priority scheduling policies. When the queue capacity reaches a threshold... At this time, the priority promotion mechanism is activated, moving the data packet from the low-priority queue. , Move to .

4. The flexible scheduling method for composite network traffic based on service priority according to claim 3, characterized in that, When a data packet arrives, it is assigned to the corresponding priority queue according to its type; if the number of data packets exceeds its backpressure threshold... Activate the priority boosting mechanism to move some data packets from this queue to... queue; Calculate the number of packets removed using the following formula. : in, This indicates the remaining capacity in the current queue. express The current number of data packets in the queue; The queue is processed as follows: 。 5. The flexible scheduling method for composite network traffic based on service priority according to claim 1, characterized in that, When there are still remaining time slots after all data packets of the high-priority queue have been transmitted within each scheduling cycle, the remaining time slots are allocated to the medium and low-priority queues according to a preset ratio, including: Time slots are allocated based on priority queue status, prioritizing real-time data transmission, and distributing any remaining time slots proportionally to lower priority queues. First, the priority 1 queue Data packets in the specified location will be sent with priority, if in If there are remaining time slots during the transmission process of the queue, these remaining time slots will be allocated proportionally. and queue: when All data packets in the queue have been transmitted, and there is still remaining transmission time. The remaining time will be allocated proportionally. and Data packets in the queue; during the scheduling period, The data packets in the queue have exhausted their transmission time slots. and The queue of data packets will no longer be transmitted during this period.

6. The flexible scheduling method for composite network traffic based on service priority according to claim 1, characterized in that, At the end of each scheduling cycle, based on the back pressure status of each queue, priority rollback or promotion adjustments are made for queues that continuously exceed the threshold, including: At the end of each scheduling cycle, the system checks the queue status and performs priority adjustments on queues that exceed the backpressure threshold. or If the number of packets in a queue exceeds the backpressure threshold, the system will move some packets from these queues to another queue. In queues, priority promotion operations follow these rules: The number of packets removed each time ensures The queue will not overflow; The priority promotion operation stops when the number of remaining packets in the queue falls below the backpressure threshold after the packets are removed. Queue adjustments are achieved using the following formula: in, and They represent and The remaining capacity of the queue, express The capacity already occupied in the queue.

7. The flexible scheduling method for composite network traffic based on service priority according to claim 6, characterized in that, After all data packets have been scheduled and transmitted, check the queue status. Terminate scheduling when all queues are empty and there are no new data packets. , , The queues are all empty and there are no new data packets to process, so the scheduling process is terminated, completing this scheduling process.

8. A flexible network traffic scheduling system based on service priority, characterized in that, include: The queue partitioning module is used to allocate data packets of each node in the power grid scenario to three priority queues: high, medium, and low, according to the service type. The priority enhancement module is used to automatically allocate data packets to the corresponding priority queue according to their service type when they arrive at the node. When the number of data packets in the low or medium priority queue exceeds the back pressure threshold, some data packets will be moved to the high priority queue. The priority allocation module is used to allocate the remaining time slots to the medium and low priority queues according to a preset ratio when there are still remaining time slots after all data packets of the high priority queue have been transmitted in each scheduling cycle. The output adjustment module is used to adjust the priority of queues that continuously exceed the threshold at the end of each scheduling cycle, based on the back pressure status of each queue.

9. The flexible scheduling system for composite network traffic based on service priority according to claim 8, characterized in that, The method of allocating data packets in the power grid scenario to high, medium, and low priority queues according to service type includes: The queues of each node in the power grid multi-electro-interconnected sensing device are initialized. Priority queues are set up and capacity and back pressure thresholds are determined based on the real-time requirements of different power grid services. Three priority queues are set up within each node: Priority 1 queue... Priority 2 queue and priority 3 queue Each queue has a preset initial capacity. and back pressure threshold ,in, Less than ; Used to store real-time data packets. Used to store remote, non-real-time data packets. Used to store local non-real-time data packets.

10. The flexible scheduling system for composite network traffic based on service priority according to claim 8, characterized in that, When a data packet arrives at a node, it is automatically assigned to the corresponding priority queue based on its service type. When the number of data packets in a low or medium priority queue exceeds the back pressure threshold, some data packets are moved to a high priority queue, including: During the initialization phase, the PCTSA (Composite Network Traffic Scheduling Algorithm) based on service priority awareness is used to assign time slot weights to each queue and set priority scheduling policies. When the queue capacity reaches a threshold... At this time, the priority promotion mechanism is activated, moving the data packet from the low-priority queue. , Move to .

11. The flexible scheduling system for composite network traffic based on service priority according to claim 10, characterized in that, When a data packet arrives, it is assigned to the corresponding priority queue according to its type; if the number of data packets exceeds its backpressure threshold... Activate the priority boosting mechanism to move some data packets from this queue to... queue; Calculate the number of packets removed using the following formula. : in, This indicates the remaining capacity in the current queue. express The current number of data packets in the queue; The queue is processed as follows: 。 12. The flexible scheduling system for composite network traffic based on service priority according to claim 8, characterized in that, When there are still remaining time slots after all data packets of the high-priority queue have been transmitted within each scheduling cycle, the remaining time slots are allocated to the medium and low-priority queues according to a preset ratio, including: Time slots are allocated based on priority queue status, prioritizing real-time data transmission, and distributing any remaining time slots proportionally to lower priority queues. First, the priority 1 queue Data packets in the specified location will be sent with priority, if in If there are remaining time slots during the transmission process of the queue, these remaining time slots will be allocated proportionally. and queue: when All data packets in the queue have been transmitted, and there is still remaining transmission time. The remaining time will be allocated proportionally. and Data packets in the queue; during the scheduling period, The data packets in the queue have exhausted their transmission time slots. and The queue of data packets will no longer be transmitted during this period.

13. The flexible scheduling system for composite network traffic based on service priority according to claim 8, characterized in that, At the end of each scheduling cycle, based on the back pressure status of each queue, priority rollback or promotion adjustments are made for queues that continuously exceed the threshold, including: At the end of each scheduling cycle, the system checks the queue status and performs priority adjustments on queues that exceed the backpressure threshold. or If the number of packets in a queue exceeds the backpressure threshold, the system will move some packets from these queues to another queue. In queues, priority promotion operations follow these rules: The number of packets removed each time ensures The queue will not overflow; The priority promotion operation stops when the number of remaining packets in the queue falls below the backpressure threshold after the packets are removed. Queue adjustments are achieved using the following formula: in, and They represent and The remaining capacity of the queue, express The capacity already occupied in the queue.

14. The flexible scheduling system for composite network traffic based on service priority according to claim 13, characterized in that, After all data packets have been scheduled and transmitted, check the queue status. Terminate scheduling when all queues are empty and there are no new data packets. , , The queues are all empty and there are no new data packets to process, so the scheduling process is terminated, completing this scheduling process.

15. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the flexible scheduling method for composite network traffic based on service priority as described in any one of claims 1 to 7.

16. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the flexible scheduling method for composite network traffic based on service priority as described in any one of claims 1 to 7.

Images