Switch service quality optimization method and device based on intelligent prediction and adaptive scheduling, equipment and storage medium

Abstract

The invention discloses a switch service quality optimization method and device based on intelligent prediction and adaptive scheduling, equipment and a storage medium, and relates to the technical field of network communication, and the method comprises the steps: selecting a multi-dimensional feature model based on real-time network flow data; obtaining a flow demand prediction result based on the multi-dimensional feature model; adjusting a service priority based on the traffic demand prediction result and a real-time network load; and setting a differential service code point value based on the adjusted service priority, and realizing the differential service of the network flow. According to the invention, modeling is carried out on the traffic through multiple dimensions, deep analysis and prediction of traffic behaviors are realized by using the model, the priority and resource allocation are intelligently adjusted according to the real-time change of the network load and the traffic prediction result, and a finer and more intelligent traffic scheduling decision is provided.

Description

Technical Field

[0001] The present application relates to the field of network communication technology, and in particular to a method, apparatus, device, and storage medium for optimizing switch service quality based on intelligent prediction and adaptive scheduling. Background Art

[0002] QoS (Quality of Service) technology is a core mechanism for ensuring the quality of critical service transmission in network communications and is widely used in enterprise networks, service provider networks, and home networks. Current switch QoS technologies typically rely on simple priority-based scheduling algorithms. While these methods can ensure the timely transmission of high-priority traffic to a certain extent, they lack the ability to dynamically adapt to network load fluctuations. Existing priority scheduling cannot intelligently predict changes in network load, resulting in uneven resource allocation. This can lead to severe starvation of low-priority traffic, especially during peak network loads. Existing methods also employ static modeling of traffic behavior, relying solely on static priorities and simple traffic classification. They fail to consider dynamic changes in traffic characteristics and network behavior, resulting in poor adaptability to actual network environments.

[0003] Therefore, how to adaptively and dynamically adjust priorities and resource allocation is an urgent problem that needs to be solved.

[0004] The above content is only used to assist in understanding the technical solution of this application and does not constitute an admission that the above content is prior art. Summary of the Invention

[0005] The main purpose of this application is to provide a switch service quality optimization method, device, equipment and storage medium based on intelligent prediction and adaptive scheduling, aiming to solve the technical problem of how to adaptively and dynamically adjust priority and resource allocation.

[0006] To achieve the above objectives, the present application proposes a switch service quality optimization method based on intelligent prediction and adaptive scheduling, the method comprising:

[0007] Select a multi-dimensional feature model based on real-time network traffic data;

[0008] Based on the multi-dimensional feature model, a flow demand prediction result is obtained;

[0009] Adjusting service priorities based on the traffic demand forecast result and real-time network load;

[0010] A differentiated services code point value is set based on the adjusted service priority to implement differentiated services for network traffic.

[0011] In one embodiment, before selecting the multi-dimensional feature model based on the real-time network traffic data, the method further includes:

[0012] Determine traffic demand based on historical network traffic data;

[0013] Based on the traffic demand, historical network traffic characteristics in multiple dimensions are obtained;

[0014] Based on the multiple-dimensional historical network traffic features, a multi-dimensional feature model is established, wherein different types of historical network traffic data correspond to different multi-dimensional feature models.

[0015] In one embodiment, adjusting the service priority based on the traffic demand prediction result and the real-time network load includes:

[0016] Determining the business importance, business urgency, development cost coefficient, and destructiveness constant corresponding to the network traffic data based on the traffic demand forecast result and the real-time network load;

[0017] Calculate business priority based on the business importance, business urgency, development cost coefficient and destructiveness constant;

[0018] When the service priority exceeds a preset priority threshold, determining the service priority of the network traffic data as a target priority;

[0019] When the proportion of the target priority business exceeds a preset threshold, the business priority of the network data traffic is increased.

[0020] In one embodiment, setting a Differentiated Services Code Point value based on the adjusted service priority to implement real-time traffic scheduling includes:

[0021] When the adjusted service priority is higher than the first preset priority, setting the differentiated services code point value to the first preset value;

[0022] When the adjusted service priority is less than the first preset priority and greater than the second preset priority, setting the differentiated services code point value to the second preset value;

[0023] When the adjusted service priority is less than the second preset priority, the differentiated services code point value is set to a third preset value.

[0024] In one embodiment, after setting a Differentiated Services Code Point value based on the service priority to implement differentiated services for network traffic, the method further includes:

[0025] Based on the real-time network traffic data and the traffic demand forecast result, visualizing key indicators of the real-time network traffic data and the traffic demand forecast result;

[0026] sorting and filtering the real-time network traffic data based on the key indicators;

[0027] Obtain discarded traffic in the real-time network traffic data, and visualize detailed information of the discarded traffic.

[0028] In one embodiment, after visualizing the key indicators of the real-time network traffic data and the traffic demand forecast result based on the real-time network traffic data and the traffic demand forecast result, the method further includes:

[0029] Based on the real-time network traffic data, obtaining a complete life cycle of the real-time network traffic data;

[0030] Based on the complete life cycle, adjusting the service quality parameters to obtain the real-time network traffic data simulation traffic demand prediction result;

[0031] When it is detected that the simulation traffic demand prediction result is abnormal or the service quality parameters conflict, a diagnostic report is generated.

[0032] In one embodiment, the method further comprises:

[0033] Get the set minimum bandwidth threshold;

[0034] When the real-time network load is higher than a preset high load threshold and the bandwidth of the network traffic data is lower than the minimum bandwidth threshold, the bandwidth of the network traffic data is set to the minimum bandwidth threshold.

[0035] In addition, to achieve the above-mentioned purpose, the present application also proposes a switch service quality optimization device based on intelligent prediction and adaptive scheduling, the switch service quality optimization device based on intelligent prediction and adaptive scheduling comprising:

[0036] A selection module is used to select a multi-dimensional feature model based on real-time network traffic data;

[0037] A prediction module, configured to obtain a flow demand prediction result based on the multi-dimensional feature model;

[0038] An adjustment module, configured to adjust service priorities based on the traffic demand prediction result and the real-time network load;

[0039] The setting module is used to set a differentiated services code point value based on the adjusted service priority to achieve differentiated services for network traffic.

[0040] In addition, to achieve the above-mentioned purpose, the present application also proposes a switch service quality optimization device based on intelligent prediction and adaptive scheduling, the device comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, the computer program being configured to implement the steps of the switch service quality optimization method based on intelligent prediction and adaptive scheduling as described above.

[0041] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the switch service quality optimization method based on intelligent prediction and adaptive scheduling as described above are implemented.

[0042] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the switch service quality optimization method based on intelligent prediction and adaptive scheduling as described above.

[0043] This application selects a multi-dimensional feature model based on real-time network traffic data; obtains traffic demand forecasts based on the multi-dimensional feature model; adjusts service priorities based on the traffic demand forecasts and real-time network load; and sets differential service code point values ​​based on the adjusted service priorities to achieve differentiated services for network traffic. This application models traffic across multiple dimensions, utilizing the model to conduct in-depth analysis and prediction of traffic behavior. Based on real-time changes in network load and traffic forecasts, it intelligently adjusts priorities and resource allocation, providing more refined and intelligent traffic scheduling decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0045] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0046] Figure 1 A flowchart of the first embodiment of the switch service quality optimization method based on intelligent prediction and adaptive scheduling provided by this application;

[0047] Figure 2 A flowchart of the second embodiment of the switch service quality optimization method based on intelligent prediction and adaptive scheduling provided by this application;

[0048] Figure 3 This is a schematic diagram of the module structure of a switch service quality optimization device based on intelligent prediction and adaptive scheduling according to an embodiment of the present application;

[0049] Figure 4 Schematic diagram of the device structure of the hardware operating environment involved in the switch service quality optimization method based on intelligent prediction and adaptive scheduling in the embodiment of the present application.

[0050] The purpose, features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0051] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0052] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0053] The main solution of the embodiment of the present application is: based on real-time network traffic data, a multi-dimensional feature model is selected; based on the multi-dimensional feature model, a traffic demand prediction result is obtained; based on the traffic demand prediction result and the real-time network load, the service priority is adjusted; based on the adjusted service priority, a differential service code point value is set to achieve differentiated services for network traffic.

[0054] Because the existing scheduling method based on static priority fails to take into account the dynamic changes of the network environment, the scheduling decision-making lacks intelligence; during the peak network load period, the scheduling priority of the traffic cannot be dynamically adjusted according to the real-time load, resulting in starvation of low-priority traffic or degradation of service quality; it also fails to reasonably consider the actual needs of different types of traffic, resulting in waste of resources or uneven distribution.

[0055] This application provides a solution that selects a multidimensional feature model based on real-time network traffic data; generates traffic demand forecasts based on these multidimensional feature models; adjusts service priorities based on these traffic demand forecasts and real-time network load; and sets Differentiated Service Code Point (DSCP) values ​​based on the adjusted service priorities to provide differentiated services for network traffic. This application models traffic across multiple dimensions, utilizing the model to conduct in-depth analysis and prediction of traffic behavior. Based on real-time changes in network load and traffic forecasts, it intelligently adjusts priorities and resource allocation, providing more refined and intelligent traffic scheduling decisions.

[0056] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, mobile phone, etc., or an electronic device or computer capable of performing the above functions. The following describes this embodiment and the following embodiments using a computer as an example.

[0057] Based on this, the embodiment of the present application provides a switch service quality optimization method based on intelligent prediction and adaptive scheduling, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the switch service quality optimization method based on intelligent prediction and adaptive scheduling of the present application.

[0058] In this embodiment, the switch service quality optimization method based on intelligent prediction and adaptive scheduling includes steps S10 to S40:

[0059] Step S10: selecting a multi-dimensional feature model based on real-time network traffic data;

[0060] It should be noted that real-time network traffic data can be a collection of digital information transmitted through the network and its related performance indicators, reflecting the network's status, performance, and health, such as bandwidth usage, latency, packet loss rate, and other performance indicators. A multidimensional feature model can select multidimensional features of historical network traffic data (such as bandwidth, latency, packet loss rate, etc.) as input to a deep learning model. The trained model can be used to predict the changing trends of real-time network traffic data over a certain period of time.

[0061] It is understandable that according to the needs of different real-time network traffic data, appropriate multi-dimensional feature models are selected to predict real-time network traffic data, different prediction results are obtained, and different scheduling strategies are adopted according to the prediction results to improve the degree of refinement of scheduling.

[0062] In a feasible implementation, before step S10, it may also include: determining traffic demand based on historical network traffic data; obtaining historical network traffic characteristics in multiple dimensions based on the traffic demand; and establishing a multi-dimensional feature model based on the historical network traffic characteristics in multiple dimensions, wherein different types of historical network traffic data correspond to different multi-dimensional feature models.

[0063] It should be noted that historical network traffic data can be a collection of the amount of digital information transmitted through the network and its related performance indicators over a period of time in the past, and can include real-time traffic, data streams and other types. Traffic demand can be the demand for different types of network traffic data. For example, real-time traffic (such as video streams and voice streams) prioritizes latency requirements, while data streams focus on bandwidth guarantees. Historical network traffic characteristics can be historical bandwidth requirements, latency tolerance, traffic type, network load and other information.

[0064] In this embodiment, according to the requirements of different types of network traffic data, a multi-dimensional feature model is established for each type of network traffic data, which can make traffic scheduling decisions more refined and improve the utilization rate of network resources.

[0065] The above is only a feasible implementation of step S10 provided in this embodiment, and this embodiment does not specifically limit the specific implementation of step S10.

[0066] Step S20: obtaining a traffic demand prediction result based on the multi-dimensional feature model;

[0067] It should be noted that the traffic demand prediction result may be a trend of traffic changes within a certain period of time in the future, such as changes in bandwidth demand.

[0068] It is understandable that since it is necessary to realize dynamic prediction of network traffic data, step S20 is performed, which can avoid the problem that the existing method is based only on static priority and simple traffic classification, fails to consider the dynamic changes of traffic characteristics and network behavior, and thus leads to poor adaptability to the actual network environment, thereby enhancing the adaptability of the switch QoS technology.

[0069] Step S30, adjusting service priorities based on the traffic demand prediction result and real-time network load;

[0070] It should be noted that real-time network load refers to the amount of data being transmitted on a network link, device, or system at the current moment, as well as its utilization of network resources. It reflects the network's immediate stress level and is a key indicator for network performance monitoring and dynamic scheduling. Service prioritization can be used to ensure that critical applications (such as video conferencing and real-time gaming) receive sufficient bandwidth and low latency even during network congestion, while non-critical traffic (such as file downloads and email) can be restricted or delayed. Different QoS technologies employ different prioritization methods.

[0071] It is understandable that since it is necessary to ensure balanced resource allocation during peak network load, step S30 is performed to adjust the priority of network traffic data in real time to avoid severe starvation of low-priority traffic, thereby realizing intelligent adjustment of traffic priority and bandwidth allocation.

[0072] In a feasible implementation, step S30 may include: determining the business importance, business urgency, development cost coefficient and destructive constant corresponding to the network traffic data based on the traffic demand forecast result and the real-time network load; calculating the business priority based on the business importance, business urgency, development cost coefficient and destructive constant; when the business priority exceeds a preset priority threshold, determining the business priority of the network traffic data as the target priority; when the proportion of the target priority business exceeds a preset threshold, increasing the business priority of the network data traffic.

[0073] It should be noted that business importance, business urgency, development cost coefficient, destructive constant, preset priority threshold, target priority and preset threshold can be arbitrary constants. Business importance can mean the degree of impact of a certain network business or application on the core functions, user experience or revenue of an organization. Business urgency can mean the sensitivity of traffic to delay, that is, whether real-time or near real-time transmission is required. The development cost coefficient can mean the technical and resource overhead required to implement or maintain a certain QoS policy, including hardware support, configuration complexity and operation and maintenance costs. The destructive constant can mean the potential impact of QoS policy changes on existing network services. The target priority can be a unified division of network traffic data when the business priority exceeds a certain constant. For example, when the business priority exceeds 8, the business corresponding to the network traffic data is identified as the target priority. When the proportion of target priority business exceeds the preset threshold (such as 60%), the priority of the network traffic data is increased.

[0074] In this embodiment, by adjusting the priority of network traffic data and adopting an adaptive mechanism, the service priority corresponding to the network traffic data can be comprehensively assessed to ensure the rationality of resource allocation.

[0075] The above is only a feasible implementation of step S30 provided in this embodiment, and this embodiment does not specifically limit the specific implementation of step S30.

[0076] Step S40: Setting a Differentiated Services Code Point (DSCP) value based on the adjusted service priority to implement differentiated services for network traffic.

[0077] It should be noted that the Differentiated Services Code Point (DSCP) value is a 6-bit field in the ToS (Type of Service) field of the IP packet header, which is used to mark the priority and service level of traffic (a total of 64 possible values). It is the core marking mechanism of the DiffServ (Differentiated Services) model in modern QoS (Quality of Service).

[0078] It is understandable that, since it is necessary to implement differentiated services for network traffic, step S40 is performed to timely convey the priority of the network traffic amount and the service type.

[0079] In a feasible implementation, step S40 may include: when the adjusted service priority is higher than the first preset priority, setting the differentiated services code point value to a first preset value; when the adjusted service priority is lower than the first preset priority and higher than the second preset priority, setting the differentiated services code point value to a second preset value; when the adjusted service priority is lower than the second preset priority, setting the differentiated services code point value to a third preset value.

[0080] It should be noted that the first preset priority and the second preset priority can be arbitrary constants, the first preset value is a high priority DSCP (Differentiated Services Code Point) value, the second preset value is a medium priority DSCP value, and the third preset value can be a low priority DSCP value.

[0081] In this embodiment, by mapping priorities to DSCP values ​​and properly configuring DSCP, network performance for key services (such as voice and video) can be significantly optimized while preventing non-key traffic (such as file downloads) from occupying excessive resources.

[0082] The above is only a feasible implementation of step S40 provided in this embodiment, and this embodiment does not specifically limit the specific implementation of step S40.

[0083] This embodiment provides a switch service quality optimization method based on intelligent prediction and adaptive scheduling. Based on real-time network traffic data, a multi-dimensional feature model is selected; traffic demand prediction results are obtained based on the multi-dimensional feature model; service priorities are adjusted based on the traffic demand prediction results and real-time network load; and differential service code point values ​​are set based on the adjusted service priorities to achieve differentiated services for network traffic. This application models traffic through multiple dimensions, utilizing the model to perform in-depth analysis and prediction of traffic behavior. Based on real-time changes in network load and traffic prediction results, priorities and resource allocation are intelligently adjusted, providing more refined and intelligent traffic scheduling decisions.

[0084] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above embodiment 1 can be referred to the above introduction and will not be described in detail later. Figure 2 After step S40, the switch service quality optimization method based on intelligent prediction and adaptive scheduling further includes steps S41 to S43:

[0085] Step S41, based on the real-time network traffic data and the traffic demand forecast result, visualizing the key indicators of the real-time network traffic data and the traffic demand forecast result;

[0086] It should be noted that the key indicators of network traffic data can be traffic type (such as video stream, voice stream, data stream), source / destination IP address, current bandwidth allocation, priority level, status (passed / discarded), latency, packet loss rate, etc., which are used to reflect the status, performance and health of the network.

[0087] It is understandable that displaying the processing status of network traffic in real time can provide an intuitive user interface to facilitate monitoring of network operation status.

[0088] In a feasible implementation, step S41 may include: obtaining the complete life cycle of the real-time network traffic data based on the real-time network traffic data; adjusting the service quality parameters based on the complete life cycle to obtain the simulated traffic demand prediction result of the real-time network traffic data; generating a diagnostic report when an abnormality is detected in the simulated traffic demand prediction result or when the service quality parameters conflict.

[0089] It should be noted that the complete life cycle may include the switch nodes that the path passes through, the processing timestamps of each node, the priority change history and the final processing results (passed / discarded). The service quality parameters may include bandwidth allocation ratio, priority threshold, etc. The simulated traffic demand prediction results may include simulated traffic distribution changes, predicted discard rate changes and bandwidth utilization changes. The diagnostic report may include traffic snapshots, log fragments and recommended solutions.

[0090] In this implementation, the complete path of traffic from ingress to egress is tracked, and parameters such as bandwidth allocation and priority thresholds are adjusted based on key indicators of real-time network traffic data at each path node. Network behavior under different strategies is simulated, and anomalies or parameter conflicts in the simulation results are detected. This allows the precise location of the specific device, time, and strategy where packet loss occurs. By optimizing strategies through simulation prediction, resource waste or conflicts caused by static QoS configuration can be avoided.

[0091] The above is only a feasible implementation of step S41 provided in this embodiment, and this embodiment does not specifically limit the specific implementation of step S41.

[0092] Step S42: sorting and filtering the real-time network traffic data based on the key indicators;

[0093] It is understandable that by sorting and filtering real-time network traffic data based on key indicators, the query speed of abnormal network traffic data can be improved.

[0094] Step S43: Obtain discarded traffic in the real-time network traffic data, and visualize detailed information of the discarded traffic.

[0095] It should be noted that the discarded traffic in real-time network traffic data may be data packets that cannot be forwarded normally due to network equipment or system resource limitations. The detailed information of the discarded traffic may include the reasons for the discard (such as QoS policy restrictions, security rule triggering), discard time distribution histogram, discarded traffic type statistical pie chart, etc.

[0096] It can be understood that visualizing detailed information about discarded traffic is helpful in improving the efficiency of discarded traffic analysis.

[0097] In a feasible implementation, step S43 may include: obtaining a set minimum bandwidth threshold; when the real-time network load is higher than the preset high load threshold and the bandwidth of the network traffic data is lower than the minimum bandwidth threshold, setting the bandwidth of the network traffic data to the minimum bandwidth threshold.

[0098] It should be noted that the minimum bandwidth threshold and the preset high load threshold can be arbitrary constants.

[0099] It is understandable that the minimum bandwidth guarantee mechanism can ensure that low-priority traffic can still obtain a certain bandwidth under high load.

[0100] This embodiment provides a switch service quality optimization method based on intelligent prediction and adaptive scheduling. Based on the real-time network traffic data and the traffic demand prediction result, the key indicators of the real-time network traffic data and the traffic demand prediction result are visualized; based on the key indicators, the real-time network traffic data is sorted and screened; the discarded traffic in the real-time network traffic data is obtained, and the detailed information of the discarded traffic is visualized. This embodiment optimizes the switch service quality through intelligent prediction and adaptive scheduling, visualizes the key indicators and prediction results of network traffic in real time, sorts and screens the traffic data, accurately obtains and visualizes the discarded traffic information, effectively improves the efficiency of network resource utilization, enhances the service quality of the switch, ensures stable network operation, and meets the efficient communication needs in complex network environments.

[0101] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the switch service quality optimization method based on intelligent prediction and adaptive scheduling of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0102] This application also provides a switch service quality optimization device based on intelligent prediction and adaptive scheduling, please refer to Figure 3The switch service quality optimization device based on intelligent prediction and adaptive scheduling includes:

[0103] A selection module 10 is used to select a multi-dimensional feature model based on real-time network traffic data;

[0104] A prediction module 20, configured to obtain a flow demand prediction result based on the multi-dimensional feature model;

[0105] An adjustment module 30, configured to adjust service priorities based on the traffic demand prediction result and the real-time network load;

[0106] The setting module 40 is configured to set the adjusted Differentiated Services Code Point value based on the service priority to implement differentiated services for network traffic.

[0107] The switch service quality optimization device based on intelligent prediction and adaptive scheduling provided in this application utilizes the switch service quality optimization method based on intelligent prediction and adaptive scheduling described in the aforementioned embodiments, and can address the technical issues of switch service quality optimization based on intelligent prediction and adaptive scheduling. Compared to the prior art, the beneficial effects of the switch service quality optimization device based on intelligent prediction and adaptive scheduling provided in this application are the same as those of the switch service quality optimization method based on intelligent prediction and adaptive scheduling provided in the aforementioned embodiments. Other technical features of the switch service quality optimization device based on intelligent prediction and adaptive scheduling are the same as those disclosed in the aforementioned embodiments and are not further elaborated here.

[0108] The selection module 10 is also used to determine traffic demand based on historical network traffic data; obtain historical network traffic characteristics in multiple dimensions based on the traffic demand; and establish a multi-dimensional feature model based on the historical network traffic characteristics in multiple dimensions, wherein different types of historical network traffic data correspond to different multi-dimensional feature models.

[0109] The prediction module 20 is also used to determine the business importance, business urgency, development cost coefficient and destructive constant corresponding to the network traffic data based on the traffic demand prediction results and real-time network load; calculate the business priority based on the business importance, business urgency, development cost coefficient and destructive constant; when the business priority exceeds a preset priority threshold, determine the business priority of the network traffic data as the target priority; when the proportion of the target priority business exceeds a preset threshold, increase the business priority of the network data traffic.

[0110] The setting module 40 is further configured to set the Differentiated Services Code Point value to a first preset value when the adjusted service priority is higher than a first preset priority; set the Differentiated Services Code Point value to a second preset value when the adjusted service priority is lower than the first preset priority and higher than a second preset priority; and set the Differentiated Services Code Point value to a third preset value when the adjusted service priority is lower than the second preset priority.

[0111] The setting module 40 is also used to visualize the key indicators of the real-time network traffic data and the traffic demand forecast results based on the real-time network traffic data and the traffic demand forecast results; sort and filter the real-time network traffic data based on the key indicators; obtain the discarded traffic in the real-time network traffic data, and visualize the detailed information of the discarded traffic.

[0112] The setting module 40 is also used to obtain the complete life cycle of the real-time network traffic data based on the real-time network traffic data; adjust the service quality parameters based on the complete life cycle to obtain the simulated traffic demand prediction result of the real-time network traffic data; and generate a diagnostic report when an abnormality in the simulated traffic demand prediction result is detected or when a conflict of the service quality parameters is detected.

[0113] The setting module 40 is further configured to obtain a set minimum bandwidth threshold; when the real-time network load is higher than a preset high load threshold and the bandwidth of the network traffic data is lower than the minimum bandwidth threshold, the bandwidth of the network traffic data is set to the minimum bandwidth threshold.

[0114] The present application provides a switch service quality optimization device based on intelligent prediction and adaptive scheduling. The switch service quality optimization device based on intelligent prediction and adaptive scheduling includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the switch service quality optimization method based on intelligent prediction and adaptive scheduling in the above-mentioned embodiment 1.

[0115] Reference below Figure 4, which shows a schematic diagram of the structure of a switch service quality optimization device based on intelligent prediction and adaptive scheduling suitable for implementing the embodiments of the present application. The switch service quality optimization device based on intelligent prediction and adaptive scheduling in the embodiments of the present application can include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), in-vehicle terminals (such as in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 4 The switch service quality optimization device based on intelligent prediction and adaptive scheduling shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0116] like Figure 4 As shown, the switch service quality optimization device based on intelligent prediction and adaptive scheduling may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes based on a program stored in a ROM (Read Only Memory) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. Various programs and data required for the operation of the switch service quality optimization device based on intelligent prediction and adaptive scheduling are also stored in RAM 1004. Processing device 1001, ROM 1002, and RAM 1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, hard disk, etc.; and communication devices 1009. The communication devices 1009 can allow the switch quality of service optimization device based on intelligent prediction and adaptive scheduling to communicate wirelessly or wired with other devices to exchange data. Although the diagram shows a switch quality of service optimization device based on intelligent prediction and adaptive scheduling with various systems, it should be understood that implementation or presence of all the illustrated systems is not required. More or fewer systems may alternatively be implemented or present.

[0117] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0118] The switch service quality optimization device based on intelligent prediction and adaptive scheduling provided in this application utilizes the switch service quality optimization method based on intelligent prediction and adaptive scheduling described in the aforementioned embodiment, and can solve the technical problems of switch service quality optimization based on intelligent prediction and adaptive scheduling. Compared with the prior art, the beneficial effects of the switch service quality optimization device based on intelligent prediction and adaptive scheduling provided in this application are the same as the beneficial effects of the switch service quality optimization method based on intelligent prediction and adaptive scheduling provided in the aforementioned embodiment. Other technical features of the switch service quality optimization device based on intelligent prediction and adaptive scheduling are the same as those disclosed in the method of the aforementioned embodiment, and are not further described here.

[0119] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0120] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0121] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, a computer program) stored thereon, the computer-readable program instructions being used to execute the switch service quality optimization method based on intelligent prediction and adaptive scheduling in the above-mentioned embodiment.

[0122] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0123] The computer-readable storage medium may be included in the switch service quality optimization device based on intelligent prediction and adaptive scheduling; or it may exist independently without being assembled into the switch service quality optimization device based on intelligent prediction and adaptive scheduling.

[0124] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by a switch quality of service optimization device based on intelligent prediction and adaptive scheduling, the switch quality of service optimization device based on intelligent prediction and adaptive scheduling: selects a multidimensional feature model based on real-time network traffic data; obtains a traffic demand prediction result based on the multidimensional feature model; adjusts service priorities based on the traffic demand prediction result and real-time network load; and sets a differentiated service code point value based on the adjusted service priority to implement differentiated services for network traffic.

[0125] Computer program code for performing the operations of the present application may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0126] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0127] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0128] The computer-readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the aforementioned method for optimizing switch quality of service based on intelligent prediction and adaptive scheduling. This computer-readable storage medium is capable of resolving the technical issues of optimizing switch quality of service based on intelligent prediction and adaptive scheduling. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the method for optimizing switch quality of service based on intelligent prediction and adaptive scheduling provided in the aforementioned embodiments, and are not further elaborated here.

[0129] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the switch service quality optimization method based on intelligent prediction and adaptive scheduling as described above.

[0130] The computer program product provided in this application can solve the technical problem of optimizing switch quality of service based on intelligent prediction and adaptive scheduling. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the switch quality of service optimization method based on intelligent prediction and adaptive scheduling provided in the above-mentioned embodiment, and will not be elaborated here.

[0131] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A switch service quality optimization method based on intelligent prediction and adaptive scheduling, characterized in that: The method includes: Select a multi-dimensional feature model based on real-time network traffic data; Based on the multi-dimensional feature model, a flow demand prediction result is obtained; Adjusting service priorities based on the traffic demand forecast result and real-time network load; A differentiated services code point value is set based on the adjusted service priority to implement differentiated services for network traffic.

2. The method according to claim 1, wherein Before selecting the multi-dimensional feature model based on the real-time network traffic data, the method further includes: Determine traffic demand based on historical network traffic data; Based on the traffic demand, historical network traffic characteristics in multiple dimensions are obtained; Based on the multiple-dimensional historical network traffic features, a multi-dimensional feature model is established, wherein different types of historical network traffic data correspond to different multi-dimensional feature models.

3. The method according to claim 1, wherein The adjusting the service priority based on the traffic demand prediction result and the real-time network load includes: Determining the business importance, business urgency, development cost coefficient, and destructiveness constant corresponding to the network traffic data based on the traffic demand forecast result and the real-time network load; Calculate business priority based on the business importance, business urgency, development cost coefficient and destructiveness constant; When the service priority exceeds a preset priority threshold, determining the service priority of the network traffic data as a target priority; When the proportion of the target priority business exceeds a preset threshold, the business priority of the network data traffic is increased.

4. The method according to claim 1, wherein The step of setting a differentiated services code point value based on the adjusted service priority to implement real-time traffic scheduling includes: When the adjusted service priority is higher than the first preset priority, setting the differentiated services code point value to the first preset value; When the adjusted service priority is less than the first preset priority and greater than the second preset priority, setting the differentiated services code point value to the second preset value; When the adjusted service priority is less than the second preset priority, the differentiated services code point value is set to a third preset value.

5. The method according to claim 1, wherein After setting the differentiated services code point value based on the service priority to implement differentiated services for network traffic, the method further includes: Based on the real-time network traffic data and the traffic demand forecast result, visualizing key indicators of the real-time network traffic data and the traffic demand forecast result; sorting and filtering the real-time network traffic data based on the key indicators; Obtain discarded traffic in the real-time network traffic data, and visualize detailed information of the discarded traffic.

6. The method according to claim 5, wherein After visualizing the key indicators of the real-time network traffic data and the traffic demand forecast result based on the real-time network traffic data and the traffic demand forecast result, the method further includes: Based on the real-time network traffic data, obtaining a complete life cycle of the real-time network traffic data; Based on the complete life cycle, adjusting the service quality parameters to obtain the real-time network traffic data simulation traffic demand prediction result; When it is detected that the simulation traffic demand prediction result is abnormal or the service quality parameters conflict, a diagnostic report is generated.

7. The method according to any one of claims 1 to 6, characterized in that The method further comprises: Get the set minimum bandwidth threshold; When the real-time network load is higher than a preset high load threshold and the bandwidth of the network traffic data is lower than the minimum bandwidth threshold, the bandwidth of the network traffic data is set to the minimum bandwidth threshold.

8. A switch service quality optimization device based on intelligent prediction and adaptive scheduling, characterized in that: The device comprises: A selection module is used to select a multi-dimensional feature model based on real-time network traffic data; A prediction module, configured to obtain a flow demand prediction result based on the multi-dimensional feature model; An adjustment module, configured to adjust service priorities based on the traffic demand prediction result and the real-time network load; The setting module is used to set a differentiated services code point value based on the adjusted service priority to achieve differentiated services for network traffic.

9. A switch service quality optimization device based on intelligent prediction and adaptive scheduling, characterized in that: The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the switch service quality optimization method based on intelligent prediction and adaptive scheduling according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the switch service quality optimization method based on intelligent prediction and adaptive scheduling are implemented as described in any one of claims 1 to 7.

Images