Cooperative scheduling method

Abstract

The invention discloses a cooperative scheduling method, which comprises the following steps of: 1) deploying a central node controller in a target network, and deploying a cooperative scheduler on each node in the target network; 2) the central node controller sends a monitoring request to each node regularly; the cooperative scheduler reports the state information of the node where the cooperative scheduler is located and the link load condition to a central node controller; 3) the central node controller constructs a global resource view according to the state information and the link load data, and pushes the global resource view to each node; (4) a cooperative scheduler on the source node calculates a plurality of candidate paths according to the target IP address of the data flow and the global routing link table and the network topology structure of the target network, and sends the candidate paths to a central node controller; and 5) the central node controller calculates a comprehensive scoring result of each candidate path, selects an optimal path and sends the optimal path to the source node for data transmission. According to the invention, the efficiency and reliability of network communication are greatly improved.

Description

Technical Field

[0001] The present invention belongs to the cross-technical field of combining network communication technology with information security, and relates to a collaborative scheduling method. Background Art

[0002] With the rapid development of cloud computing, big data and Internet of Things technologies, the architecture and performance requirements of data center networks (DCNs) are increasing. In a highly connected DCN, servers often communicate one-to-one and many-to-many. How to efficiently utilize multiple paths between servers becomes the key to improving network performance. The transmission method based on the shortest path has problems such as low multi-path utilization efficiency, unbalanced network load, and data communication congestion, which leads to decreased data scheduling performance. Therefore, a method is needed that can analyze node status and link load in real time and dynamically select the optimal transmission path based on this.

[0003] Collaborative scheduling currently faces multiple challenges that are closely related to the network model. First, the sudden increase in data has put forward higher requirements on the storage and computing capabilities of the system, requiring the scheduling system to have efficient data processing and distribution capabilities to avoid data backlogs and processing delays. Secondly, the dynamic nature of network bandwidth increases the complexity of scheduling, requiring the scheduling algorithm to be able to adapt to bandwidth changes in real time, optimize resource allocation, and ensure the smooth execution of key tasks. At the same time, the randomization of network congestion has exacerbated the uncertainty of network conditions, requiring collaborative scheduling algorithms to have intelligent prediction and adaptive adjustment capabilities to effectively deal with network congestion and improve the overall performance and stability of the system. In addition, the diversification of network goals requires scheduling strategies to be more flexible and changeable to meet the various needs of different users and achieve optimal configuration and maximum utilization of resources. Summary of the invention

[0004] In view of the problems existing in the prior art, the purpose of the present invention is to provide an efficient collaborative scheduling method. The present invention is committed to developing a more intelligent and adaptive scheduling algorithm based on node status and link load conditions, improving the system's ability to cope with data, bandwidth and congestion, while focusing on optimizing resource management and task allocation strategies to ensure efficient and stable collaborative scheduling in various network environments.

[0005] To achieve the purpose, the technical solution adopted by the present invention is:

[0006] (1) System initialization: The present invention is based on a mesh structure to achieve control forwarding separation and global centralized control. The system includes a central node controller and a data source / destination node. The central node controller is responsible for collecting network resource information, including node status and link load, and calculating the optimal transmission path based on this information.

[0007] (2) Global resource view construction: The central node controller regularly collects network node status information and link load conditions. Node status information includes CPU usage, memory occupancy, and port status. Link load conditions include bandwidth utilization, latency, and packet loss rate. This information is used to evaluate the processing capacity and health of nodes and the transmission capacity and reliability of links, providing a basis for path selection.

[0008] (3) Optimal path calculation: The central node controller calculates the optimal path between a pair of nodes based on the node status and link load information obtained in real time and the preset routing algorithm.

[0009] (4) Data transmission and monitoring: The central node controller sends the calculated optimal path to the source node, and the source node forwards it to the next hop node according to the optimal path. At the same time, the central node controller continuously monitors the network status and dynamically adjusts the transmission path as needed to adapt to network changes.

[0010] The key points or inventive points of the present invention are mainly reflected in the following aspects:

[0011] (1) Real-time dynamic monitoring and analysis

[0012] The present invention introduces a real-time dynamic monitoring mechanism that can continuously and in real time collect node status and link load information in the network. This real-time feature enables the system to quickly respond to changes in network status, thereby making more accurate path selection decisions.

[0013] (2) Optimal path calculation based on multiple factors

[0014] When selecting the optimal transmission path, the present invention not only considers traditional single factors such as path length and bandwidth utilization, but also comprehensively considers multiple factors such as link available bandwidth, path delay, link load balancing degree, node processing capacity, etc. This multi-objective optimization algorithm makes the calculated optimal path more comprehensive and reasonable, and can better meet the diverse needs of network transmission.

[0015] (3) Intelligent dynamic adjustment capability

[0016] The present invention has intelligent dynamic adjustment capabilities, and can quickly recalculate and send new optimal path information to devices along the way when the network status changes (such as link failure, node congestion, etc.). This dynamic adjustment mechanism enables the network to maintain an efficient and stable operating state, reducing service interruptions and data loss caused by network failures and performance issues.

[0017] The technical solution of the present invention is:

[0018] A collaborative scheduling method, the steps of which include:

[0019] 1) deploying a central node controller in the target network and deploying a collaborative scheduler on each node in the target network;

[0020] 2) The central node controller periodically sends a monitoring request to each node in the target network; each time the collaborative scheduler receives the monitoring request, it reports the status information and link load status of the node to the central node controller;

[0021] 3) The central node controller constructs a global resource view based on the status information and link load data of each node, and pushes it to each node;

[0022] 4) The collaborative scheduler on the source node in the target network obtains the global routing link table and network topology of the target network from the global resource view; then, according to the destination IP address of the data flow and the global routing link table and network topology of the target network, multiple candidate paths are calculated and sent to the central node controller;

[0023] 5) The central node controller calculates the comprehensive scoring result of each candidate path, selects the optimal path according to the comprehensive scoring result of each candidate path, and sends it to the source node for data transmission.

[0024] Furthermore, the central node controller calculates a comprehensive scoring result of each candidate path based on delay time, bandwidth capacity, reliability, security and cost-effectiveness.

[0025] Furthermore, the central node controller is based on the evaluation function Calculate the i-th candidate path P i The comprehensive score result Score(P i ), where D max ,D min are the maximum and minimum delay times among the candidate paths, respectively, and w D is the weight of the delay time; B max ,B min are the maximum and minimum bandwidth capacities of the multiple candidate paths, respectively, and w B is the weight of bandwidth capacity; R max ,R min are the maximum and minimum reliability values ​​of the multiple candidate paths, respectively, and w R is the reliability weight; S max is the maximum value of security among the multiple candidate paths, w S is the weight of security; C max ,C minare the maximum and minimum cost-effectiveness of the multiple candidate paths, respectively, and w C The weight of cost-effectiveness.

[0026] Furthermore, the status information includes but is not limited to CPU usage, memory occupancy, and port status.

[0027] Furthermore, the link load data of the node is obtained using the Simple Network Management Protocol (SNMP).

[0028] Furthermore, the link load data includes bandwidth utilization, delay time and packet loss rate.

[0029] Furthermore, the central node controller monitors the amount of data received and sent by each node, the frequency of sending and receiving, the data transmission delay time, the bandwidth rate, the response time, and the number of data transmission intermediate times, and constructs and updates an abnormal curve in real time based on the monitoring data, and then identifies bottlenecks or potential problems in the target network based on the abnormal curve.

[0030] Furthermore, the central node controller dynamically evaluates the validity of the current optimal path based on the monitored changes in the network status, and recalculates and selects a new optimal path if the current optimal path is invalid.

[0031] Furthermore, the method for calculating multiple candidate paths is: first, obtain multiple indicator factors from the global resource view and determine the importance value of each indicator factor, generate multiple alternative paths from the source node to the destination node according to the global routing link table and network topology of the target network; then assign weights to each alternative path according to the importance value of each indicator factor to generate an alternative path weighted graph; then use the algorithm in graph theory to search and evaluate the advantages and disadvantages of each alternative path in the alternative path weighted graph, and generate multiple candidate paths according to the evaluation results.

[0032] Furthermore, the indicator factors include link status, bandwidth usage, and historical transmission records; the algorithm in the graph theory is Dijkstra algorithm, A* algorithm, Bellman-Ford algorithm or its variants.

[0033] The advantages of the present invention are as follows:

[0034] (1) This method can intelligently distribute network traffic, preventing some links or nodes from being overloaded due to excessive traffic while other links or nodes are relatively idle. By balancing the network load, the overall throughput and stability of the network can be effectively improved.

[0035] (2) When a node is in poor condition (such as failure, maintenance, or performance degradation), the path selection algorithm based on node status and link load can quickly replan the transmission path to bypass the problematic node or link, ensuring the continuity and reliability of data transmission.

[0036] The present invention calculates the optimal transmission path from the source to the destination according to the status of each node and the load of each link, thereby realizing efficient and accurate transmission of massive data, greatly improving the efficiency and reliability of network communication. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0038] The present invention is further described in detail below in conjunction with the accompanying drawings. The examples given are only used to explain the present invention but not to limit the scope of the present invention.

[0039] (1) System initialization

[0040] First, a central node controller is deployed at the core or logical center of the network as the management and decision-making center of the entire network. The controller is responsible for global resource monitoring, data analysis, path calculation and optimization, and unified scheduling and distribution of path information. The central node controller must have high availability, high reliability, and strong data processing capabilities to cope with complex and changing data flows and requests in large-scale network environments.

[0041] Secondly, this method adopts distributed deployment, deploying a collaborative scheduler on each node in the network. Each node is located in a different physical space position. These nodes constitute important nodes on the data transmission path, which directly affects the efficiency and reliability of data transmission. The collaborative scheduler works closely with the central node controller to receive and execute the path information and scheduling instructions issued by the controller. At the same time, they are also responsible for collecting the status information and link load data of local nodes, and reporting them to the central node controller in real time for global analysis and optimization. By deploying a collaborative scheduler on the node, the status information and link load of the transmission node can be actively reported in real time. The central node controller updates the global routing link in real time according to the information reported by the transmission node, and sends the collaborative scheduler of each node in time, so that each transmission node always maintains the latest global routing link table, which can realize fine-grained control and dynamic adjustment of the data transmission path, and further improve the flexibility and efficiency of data transmission.

[0042] Finally, during system deployment, reasonable network planning and policy configuration are used to ensure that there is at least one reachable path between any two nodes. This requires that the connectivity and redundancy of the network be fully considered during network design to avoid network interruptions caused by single point failures or link congestion. With the global vision and intelligent algorithms of the central node controller, the network topology can be dynamically evaluated and optimized, potential path problems can be discovered and resolved in a timely manner, and the continuity and stability of data transmission can be ensured.

[0043] (2) Construction of global resource view

[0044] First, we set a precise monitoring period (such as every second or every minute). Through this periodic monitoring mechanism, the central node controller regularly sends detailed monitoring requests to each node in the network. These requests are intended to collect key status information, including but not limited to CPU usage, memory usage, and port status, so as to fully understand the operating status of each node.

[0045] Secondly, in order to accurately capture the real-time performance of the link, we use real-time data flow monitoring and SNMP (Simple Network Management Protocol) and other technologies to instantly obtain the link load status. Specific indicators include bandwidth utilization, delay time, and packet loss rate. These indicators play an irreplaceable role in evaluating the transmission efficiency and reliability of the link.

[0046] Finally, the central node controller integrates the node information and link load data collected above to build a comprehensive and accurate global resource view, and pushes it to all nodes, so that in a complex network environment, each node manager can clearly understand the scheduling of the node in the global resource scheduling. This view not only provides a solid foundation for subsequent path calculation, but also enables network administrators to intuitively understand the resource allocation and operation status of the entire network, providing strong support for network optimization and decision-making.

[0047] (3) Optimal path calculation

[0048] First, the collaborative scheduler of the source node obtains the global routing link table and network topology from the global resource view, and calls the intelligent routing algorithm according to the destination IP address of the data stream. The pseudo code is shown below. The best link is obtained in combination with the global routing link table. The algorithm comprehensively considers multiple factors such as the link length of the network topology, the number of routing points, the link health status, the bandwidth utilization rate, and the historical transmission time efficiency, and calculates multiple candidate paths.

[0049] Among them, the intelligent routing algorithm collects necessary indicator data from the global resource view and network topology, including link status, bandwidth usage, historical transmission records, etc., cleans, integrates and preprocesses the collected indicator data for algorithm use, and generates multiple alternative paths from the source node to the destination node according to the importance of each indicator factor and the global routing link table and network topology of the target network; then, a weighted graph of alternative paths is generated by assigning weights to each alternative path according to the importance value of each indicator factor; then, the algorithms in graph theory (such as Dijkstra algorithm, A* algorithm, Bellman-Ford algorithm or its variants) are used to search for the best path in the weighted graph of alternative paths. These algorithms can evaluate the pros and cons of the path according to the weight (i.e., the result after comprehensive consideration of multiple factors) and generate multiple candidate paths.

[0050] The weighted graph of candidate paths determines the index factors (such as link status, bandwidth usage, and historical transmission records) and assigns an importance value to each of them (a weight between 0 and 1, indicating the importance ratio of the factor in the overall evaluation). For each candidate path, the comprehensive weight of the path is calculated based on the importance value of each index factor and the specific value of the path in each index, and is achieved through weighted summation: Where n is the number of indicator factors involved in the path. In view of the different numbers of indicator factors involved in different alternative paths, default values ​​(such as 0 or a neutral value) are assigned to the indicator factors not involved to ensure that all paths can be compared under the same framework. The weighted graph of alternative paths uses the calculated weight of each alternative path to assign corresponding weights or labels to each node (source node, intermediate node, destination node) and edge (path segment) in the graph.

[0051] Secondly, in order to select the path that best suits the current transmission needs from a large number of candidate paths, each candidate path is quantitatively scored through a multi-dimensional evaluation function, including but not limited to the path's delay time, bandwidth capacity, reliability (such as link failure rate), security (such as encryption support), and cost-effectiveness. The evaluation function can objectively reflect the advantages and disadvantages of each path.

[0052] The evaluation function defines the indicators and corresponding weights of each dimension, delay time (D): unit: milliseconds (ms), weight w D ; Bandwidth capacity (B): unit Mbps, weight w B ; Reliability (R): can be expressed using the inverse of the link failure rate (i.e. MTBF, mean time between failures) or the negative logarithm of the failure rate, etc., with a weight of w R ; Security (S): A score based on factors such as encryption support and security protocols (e.g., 0-10 points), with a weight of w S; Cost-effectiveness (C): Considering deployment and maintenance costs, it can be quantified by the ratio of cost to performance, with a weight of w C . Let the score of path Pi in each dimension be D i ,B i ,R i ,S i ,C i , then the path P i The total score is:

[0053]

[0054] Among them, D max ,D min ,B max ,B min ,R max ,R min ,S max C max ,C min They are the maximum and minimum values ​​of the corresponding dimensions in all candidate paths, respectively, and are used for normalization so that the scores of all dimensions are between 0 and 1 (cost-effectiveness is a reverse indicator, so subtraction and inversion are used).

[0055] Then, based on the comprehensive scoring results of the evaluation function, the central node controller will sort and filter, and finally select the optimal path. This optimal path can not only provide the best data transmission performance under current conditions, but also adapt to future changes in network status to a certain extent, ensuring the continuity and stability of data transmission. Through such a process, the central node controller can intelligently manage network traffic, optimize data transmission efficiency, and improve overall network performance.

[0056] (4) Data transmission and monitoring

[0057] First, the source node transmits data according to the optimal path calculated by the central node controller to ensure that the data can reach the destination node along the most efficient and reliable path.

[0058] Secondly, the central node controller continuously and actively monitors the status of the entire network, including link load, bandwidth utilization, latency changes, and any potential security threats. By collecting and analyzing this data in real time, such as the overload of the amount of data received and sent by the node, too high a frequency of sending and receiving, severe data transmission delays, bandwidth rates 50% lower than normal networks, response timeouts, data transmission mid-segment, etc., combined with the historical values ​​of each node, the central node controller can quickly identify any bottlenecks or potential problems in the network for abnormal curves of these indicators.

[0059] Finally, based on the monitored changes in network status, the central node controller will dynamically evaluate the effectiveness of the current optimal path. Once it is found that the current path is no longer the best choice (for example, due to link failure, bandwidth congestion, or cost increase), the controller will immediately trigger the path adjustment mechanism. It will re-call the routing algorithm, combine the latest network status information, recalculate and select a new optimal path.

[0060] The intelligent network optimal transmission path selection system and method based on node status and link load proposed in the present invention realizes reasonable, efficient and balanced allocation of network resources by real-time monitoring of network status and dynamically selecting the optimal path, improves the efficiency, reliability and stability of data transmission, and has significant technical innovation and broad application prospects.

[0061] In a 10Mbps network bandwidth environment, by simulating a network scenario with 50 transmission nodes, we conducted a comparative experiment on this algorithm (the intelligent network optimal transmission path algorithm based on node status and link load) and the traditional scheduling algorithm based on the shortest path. The comparison results are as follows:

[0062] Table 1 Comparison results

[0063] Shortest Path Scheduling Algorithm Intelligent scheduling algorithm Throughput 6Mbps 8Mbps Transmission delay 1.2s 0.8s Bandwidth Utilization 60％ 80％

[0064] In summary, this patent can dynamically select the optimal transmission path by comprehensively considering the current state of the node and the link load, effectively avoiding the congestion of high-load links, thereby significantly improving the overall throughput of the network. In contrast, the traditional shortest path algorithm only selects routes based on the path length, without considering the actual load situation, resulting in some links becoming bottlenecks during high-load periods, limiting the further improvement of throughput. The experimental results show that under the same network conditions, the throughput of this algorithm is about 33% higher than that of the traditional algorithm. In addition, since this patent can intelligently avoid congested links and select a more unobstructed path for data transmission, it significantly reduces the transmission delay of data. When facing network congestion, the traditional shortest path algorithm may choose a path that seems to be the shortest but is actually severely delayed due to excessive load, resulting in increased transmission delay. Experimental data show that this algorithm performs well in reducing transmission delay, and the average delay is reduced by about 25% compared with the traditional algorithm. Finally, by intelligently allocating network resources, this patent can ensure that network resources are used more evenly and efficiently. It dynamically adjusts the transmission strategy according to the real-time status of nodes and links to avoid excessive concentration and waste of resources. In contrast, the traditional shortest path algorithm may cause some links to be resource-constrained due to not considering global resource allocation, while other links are relatively idle, resulting in uneven bandwidth utilization. Experimental results show that this algorithm improves bandwidth utilization by about 20% compared with traditional algorithms, achieving a better configuration of network resources.

[0065] Although the specific embodiments of the present invention are disclosed for the purpose of illustration, the purpose is to help understand the content of the present invention and implement it accordingly, those skilled in the art will understand that various substitutions, changes and modifications are possible without departing from the spirit and scope of the present invention and the appended claims. Therefore, the present invention should not be limited to the content disclosed in the best embodiment, and the scope of the present invention is subject to the scope defined in the claims.

Claims

1. A collaborative scheduling method, comprising the steps of: 1) deploying a central node controller in the target network and deploying a collaborative scheduler on each node in the target network; 2) The central node controller periodically sends a monitoring request to each node in the target network; each time the collaborative scheduler receives the monitoring request, it reports the status information and link load status of the node to the central node controller; 3) The central node controller constructs a global resource view based on the status information and link load data of each node, And push it to each of the nodes; 4) The collaborative scheduler on the source node in the target network obtains the global routing link table and network topology of the target network from the global resource view; then, according to the destination IP address of the data flow and the global routing link table and network topology of the target network, multiple candidate paths are calculated and sent to the central node controller; 5) The central node controller calculates the comprehensive scoring result of each candidate path, selects the optimal path according to the comprehensive scoring result of each candidate path, and sends it to the source node for data transmission.

2. The method according to claim 1, characterized in that The central node controller calculates a comprehensive scoring result of each candidate path based on delay time, bandwidth capacity, reliability, security and cost-effectiveness.

3. The method according to claim 2, characterized in that The central node controller is based on the evaluation function Calculate the i-th candidate path P i The comprehensive score result Score(P i ), where D max ,D min are the maximum and minimum delay times among the candidate paths, respectively, and w D is the weight of the delay time; B max ,B min are the maximum and minimum bandwidth capacities of the multiple candidate paths, respectively, and w B is the weight of bandwidth capacity; R max ,R min are the maximum and minimum reliability values ​​of the multiple candidate paths, respectively, and w R is the reliability weight; S max is the maximum value of security among the multiple candidate paths, w S is the weight of security; C max ,C min are the maximum and minimum cost-effectiveness of the multiple candidate paths, respectively, and w C The weight of cost-effectiveness.

4. The method according to claim 1, 2 or 3, characterized in that: The status information includes but is not limited to CPU usage, memory occupancy, and port status.

5. The method according to claim 1, 2 or 3, characterized in that: The link load data of the node is obtained by using the Simple Network Management Protocol (SNMP).

6. The method according to claim 1, 2 or 3, characterized in that: The link load data includes bandwidth utilization, delay time and packet loss rate.

7. The method according to claim 1, 2 or 3, characterized in that: The central node controller monitors the amount of data received and sent by each node, the frequency of sending and receiving, the data transmission delay time, the bandwidth rate, the response time, and the number of data transmission intermediate times, and constructs and updates an abnormal curve in real time based on the monitoring data, and then identifies bottlenecks or potential problems in the target network based on the abnormal curve.

8. The method according to claim 1, characterized in that The central node controller dynamically evaluates the validity of the current optimal path based on the monitored network status changes, and recalculates and selects a new optimal path if the current optimal path is invalid.

9. The method according to claim 1, characterized in that: The method for calculating the plurality of candidate paths is as follows: first, obtaining a plurality of index factors from the global resource view and determining the importance value of each index factor, generating a plurality of alternative paths from the source node to the destination node according to the global routing link table and the network topology structure of the target network; then, assigning a weight to each alternative path according to the importance value of each index factor to generate an alternative path weighted graph; then, using an algorithm in graph theory to search and evaluate the pros and cons of each alternative path in the alternative path weighted graph, and generating a plurality of candidate paths according to the evaluation results.

10. The method according to claim 9, characterized in that The index factors include link status, bandwidth usage, and historical transmission records; the algorithm in the graph theory is Dijkstra algorithm, A* algorithm, Bellman-Ford algorithm or its variants.

Images