A device optimization method, device and storage medium based on SPN network

Abstract

The present invention relates to the technical field of equipment optimization, and in particular to an equipment optimization method, device and storage medium based on an SPN network. The method includes obtaining the historical data of a single disk of the equipment and the historical data of a virtual network, and constructing a Prophet model, using the Prophet model to predict the port traffic of the single disk port of the equipment and the port traffic of the virtual network, and obtaining the traffic prediction value of the equipment in each time period of a day; using the service power allocation method to obtain the power of the equipment service in each time period of a day, and using the energy consumption calculation formula to calculate the energy consumption value of the equipment; setting the energy consumption threshold of the equipment, and comparing the calculated energy consumption value with the energy consumption threshold, and optimizing according to the comparison result. The present invention obtains the power of the equipment in each time period based on the SPN network by an allocation method, obtains the traffic of the equipment in each time period, and the energy consumption value of the equipment by using the Prophet model, and compares the energy consumption value with the threshold set by the equipment, so as to optimize the equipment and save energy.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment optimization, and in particular to an equipment optimization method, device and storage medium based on an SPN network. Background Art

[0002] In order to accelerate the development of all-optical network technology, various operators have purchased a large number of various optical switching or electrical switching equipment, and these equipment consumes a lot of electricity every day, accounting for a large cost. For operators, the equipment collected based on the SPN network is usually a batch of equipment with the same configuration. Since each device is based on the needs of different time periods, it is inevitable that the use of each single disk or virtual network port in the equipment will be surplus or full load during the use of the equipment. When the equipment is in surplus, the single disk in the equipment will be idle; on the one hand, the idling of the single disk will consume part of the electricity, and this part of the energy is wasted electricity. On the other hand, when the single disk in the equipment is always in an idle state, it means that the single disk in the equipment is always in a surplus state. At this time, the existence of the single disk is bound to increase the cost of the equipment. When the equipment is in full load, the equipment just or is not enough to meet the use demand. When the equipment is in full load for a long time and the equipment is not expanded, the equipment will work at full load for a long time, which will inevitably reduce the service life of the equipment and even have the risk of burning out the equipment.

[0003] In view of this, overcoming the defects of the prior art is an urgent problem to be solved in the field of this technology. Summary of the invention

[0004] The technical problem to be solved by the present invention is how to optimize the equipment to avoid the waste of resources caused by surplus or full load of the equipment in the SPN network and the reduction of the equipment life.

[0005] The embodiment of the present invention adopts the following technical solution:

[0006] In a first aspect, the present invention provides a device optimization method based on an SPN network, comprising:

[0007] Obtain the historical data of the device's single disk and the virtual network, and build a Prophet model. Use the Prophet model to predict the port traffic of the device's single disk port and the virtual network, and obtain the traffic forecast value of the device in each time period of the day.

[0008] According to the characteristics of SPN services, the service power allocation method is used to obtain the power of equipment services in each time period of a day, and the energy consumption value of the equipment is calculated using the energy consumption calculation formula;

[0009] Set an energy consumption threshold for the device, compare the calculated energy consumption value with the energy consumption threshold, and perform optimization based on the comparison result.

[0010] Preferably, the data of a single disk of the device includes power data of the single disk and flow data of the single disk. Before building the Prophet model, historical data of the single disk of the device is obtained, specifically including:

[0011] A power meter is installed at the port of each single disk of the equipment, and the full-load power, no-load power, and working power of each single disk are measured by the power meter at preset intervals;

[0012] The flow monitoring software is used to detect the flow of the single disk port issued by the single disk, and the flow monitoring software is used to measure the flow of the single disk port at each preset time interval.

[0013] Preferably, the data of the virtual network includes network service data and network topology information data, wherein the network service includes a Channel layer, a Flexe-Group layer and an L2VPN layer; and the network topology includes a network element, a single disk and a port.

[0014] Preferably, the formula of the Prophet model is:

[0015] y(t)=g(t)+s(t)+h(t)+∈t

[0016] Among them, g(t) represents the growth function of device traffic over time, which is used to fit non-periodic changes; s(t) represents the Fourier function, which is used to fit periodic changes; h(t) represents changes caused by special reasons such as holidays and festivals; ∈t is a noise function, which is used to represent random and unpredictable traffic fluctuations.

[0017] Preferably, the formula of the Fourier function is:

[0018]

[0019] Among them, s(t) represents the periodic change of the flow of the device over time, P represents a fixed time period, An and Bn represent the parameters that need to be learned, among which, by default, N=10 is used to characterize the periodic change in years, and N=3 is used to characterize the periodic change in weeks.

[0020] Preferably, the SPN service includes a 5G service and a dedicated line service, and the method of using service power allocation to obtain the power of the device service in each time period of a day specifically includes:

[0021] Search for service-hit single disks, public single disks, and sub-frames in the network element layer, and obtain the single disk power of the single disk allocated by the network element service bandwidth ratio, the power of the public single disk and the sub-frame allocated by the network element service bandwidth ratio, and the power of the service-missing single disk;

[0022] Search for service-hitting single disks, public single disks, and sub-frames in the core layer; when the network element does not carry dedicated line services, allocate the network element power according to the bandwidth ratio of all 5G services in the network; when the network element carries dedicated line services, allocate the network element power according to the bandwidth ratio of the dedicated line and all 5G services; and find the power of the single disk for the missed services and set it to;

[0023] According to the SPN service type, the 5G service power and dedicated line service power of the device in each time period of the day are obtained by accumulation, and the 5G service power and dedicated line service power are added together to obtain the total power of the device in each time period of the day.

[0024] Preferably, the energy consumption threshold of the device includes an upper threshold and a lower threshold, and the calculated energy consumption value is compared with the energy consumption threshold, and optimization is performed according to the comparison result, specifically including:

[0025] When the lower threshold is less than or equal to the calculated energy consumption value, and the upper threshold is greater than or equal to the calculated energy consumption value, it indicates that the device is in a stable working state and does not need to be optimized.

[0026] When the lower limit of the threshold is greater than the calculated energy consumption value, it indicates that the device is in surplus state. At this time, the idle disks in the device are shut down to reduce the power in the device.

[0027] When the upper threshold is less than the calculated energy consumption value, it means that the device is under full load. In this case, the load of the device can be reduced by increasing the number of single disks in the device.

[0028] Preferably, when there are a first device and a second device, and the first device is in a surplus state and the second device is in a full load state, the optimization method also includes establishing a temporary cascade relationship between the first device and the second device, and sharing the load in the second device through the first device, so as to utilize the surplus in the first device to reduce the load of the second device.

[0029] In a second aspect, based on the device optimization method based on the SPN network in the first aspect, the present invention further provides a device based on the SPN network, including:

[0030] 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 processor to execute the device optimization method based on the SPN network described in the first aspect.

[0031] In a third aspect, the present invention further provides a non-volatile computer storage medium, wherein the computer storage medium stores computer executable instructions, which are executed by one or more processors to complete the device optimization method based on the SPN network described in the first aspect.

[0032] In the existing measurement system, the energy consumption of the equipment based on the SPN network is not measured. The energy consumption of the equipment is usually adjusted based on experience, which makes it difficult to achieve accurate control of the energy consumption of the equipment based on the SPN network.

[0033] The present invention obtains the power of the equipment in each time period based on the SPN network through the allocation method, uses the Prophet model to predict the traffic of the equipment in each time period, and then predicts the energy consumption value of the equipment in each time period. By comparing the energy consumption value with the threshold set by the equipment, the equipment is optimized to avoid the problem of surplus or full load of the equipment in the SPN network causing waste of resources for the equipment and shortening the life of the equipment, thereby achieving the effect of energy saving and emission reduction. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0035] Figure 1 It is a flow chart of a device optimization method based on SPN network provided by an embodiment of the present invention;

[0036] Figure 2 It is a flow chart of a device optimization method based on SPN network provided by an embodiment of the present invention;

[0037] Figure 3 It is a flow chart of a device optimization method based on SPN network provided by an embodiment of the present invention;

[0038] Figure 4 It is a calculation framework diagram of 5G service power of a device optimization method based on an SPN network provided in an embodiment of the present invention;

[0039] Figure 5 It is a calculation framework diagram of a dedicated line service power of a device optimization method based on an SPN network provided by an embodiment of the present invention;

[0040] Figure 6It is a flow chart of a device optimization method based on SPN network provided by an embodiment of the present invention;

[0041] Figure 7 It is a schematic diagram of a device structure based on an SPN network provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0043] In the description of the present invention, the terms "inside", "outside", "longitudinal", "lateral", "upper", "lower", "top", "bottom" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings. They are only for the convenience of describing the present invention and do not require that the present invention must be constructed and operated in a specific orientation. Therefore, they should not be understood as limitations on the present invention.

[0044] In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0045] Embodiment 1:

[0046] Embodiment 1 of the present invention provides a device optimization method based on SPN network, such as Figure 1 As shown, including:

[0047] Step 201: Obtain historical data of a single disk of the device and historical data of a virtual network, and construct a Prophet model. Use the Prophet model to predict the port traffic of a single disk port of the device and the virtual network, and obtain traffic prediction values ​​of the device in each time period of a day.

[0048] Among them, the data in the device based on the SPN (Slicing-Packet-Network) network of the embodiment of the present invention includes the data of the device single disk (the single disk in the embodiment of the present invention refers to the physical single disk) and the virtual network port. Among them, the energy consumption of the virtual service is the service energy consumption, which is equal to the traffic of the virtual service divided by the power of the virtual service; based on this, in order to optimize the embodiment of the present invention, it is first necessary to obtain the energy consumption value of the SPN device based on the embodiment of the present invention, that is, to obtain the total traffic and total power of the SPN device based on the embodiment of the present invention, and calculate the total energy consumption value of the device through the energy consumption calculation formula of the device (the energy consumption value in the embodiment of the present invention represents the effective energy consumption value, and the corresponding power and traffic are also represented as effective power and effective traffic; in the calculation process, the power and traffic of the missed single disk are not calculated in the corresponding traffic and power). During the operation of the device, the power and traffic of the device are always in a fluctuating state according to actual needs, so the energy consumption of the device is also always in a fluctuating state. By measuring the power and traffic of the SPN device at the same time, the energy consumption at that time can be obtained. The embodiment of the present invention first obtains the historical data of the device single disk and the historical data of the virtual network, and uses the Prophet model for training to achieve the purpose of predicting the total traffic of the device. The traffic prediction value of the device in each time period of a day is obtained through the Prophet model. In theory, as long as enough historical data of the device single disk and the historical data of the virtual network are obtained, the Prophet model can be used to accurately predict the total traffic of the device in each time period of a day (including holidays).

[0049] Step 202: According to the SPN service characteristics, the service power allocation method is used to obtain the power of the equipment service in each time period of a day, and the energy consumption value of the equipment is calculated using the energy consumption calculation formula.

[0050] The data in the device of the SPN network of the embodiment of the present invention includes the data of the single disk of the device (physical single disk) and the virtual network port. Since there is an intersection between the power generated by the single disk and the virtual network port in the process of using the device of the embodiment of the present invention, it will cause the device to have inaccurate calculation problems in the process of calculating power; therefore, based on the characteristics of the SPN service, the embodiment of the present invention adopts a power sharing method to obtain the power of the device. The virtual service of the SPN of the embodiment of the present invention can be divided into 5G service and dedicated line service according to the type. In the process of calculation, the power of the single disk, network element, sub-frame, and core layer in the service is calculated, and then the power under the corresponding service is obtained by adding them, and then the power of the device is obtained. It is worth noting that the embodiment of the present invention uses traffic monitoring software for measurement to obtain the precise traffic corresponding to the equipment under each service.

[0051] Step 203: Set an energy consumption threshold of the device, compare the calculated energy consumption value with the energy consumption threshold, and perform optimization based on the comparison result.

[0052] Among them, after obtaining the power and flow of the device in each time period of a day, the energy consumption of the device can be obtained through the energy consumption calculation formula. It is worth noting that the flow of the embodiment of the present invention is predicted based on the Prophet model, so the energy consumption value of the embodiment of the present invention can also be considered as a predicted value; in addition, in the process of obtaining the power consumption of the device, the embodiment of the present invention needs to calculate the energy consumption of the measured values ​​of the power and flow of the device at the same time to obtain different dynamic energy consumption values ​​at each time, and then it can be but not limited to drawing a table of the energy consumption at each time, so as to facilitate the prediction of the devices of the SPN network of the present invention.

[0053] The present invention obtains the power of the equipment in each time period based on the SPN network through the allocation method, uses the Prophet model to predict the traffic of the equipment in each time period, and then predicts the energy consumption value of the equipment in each time period, and compares the energy consumption value with the threshold set by the equipment to optimize the equipment.

[0054] In order to illustrate the complete solution of the present invention, the specific contents of the present invention are explained in detail below. Furthermore, the data of a single disk of the equipment includes power data of a single disk and flow data of a single disk. Before building the Prophet model, the historical data of a single disk of the equipment is obtained, such as Figure 2 As shown, specifically including:

[0055] Step 301: a power meter is provided at the port of each single disk of the device, and the full load power, no-load power, and working power of each single disk are measured by the power meter at preset intervals.

[0056] Among them, the power of the device in the embodiment of the present invention is mainly divided into two parts, the first part is the power of a single disk, and the second part is the power shared by the virtual service. Among them, the power of the first part can be used, but not limited to, by inserting a power meter at the port of the single disk, and obtaining the real-time power, full-load power and no-load power of each single disk through the power meter; the second part is the core layer shared power corresponding to the virtual service port, which is also measured by the power meter, and will not be repeated here (in the actual operation process, the power at each port is usually detected by a power meter, and the total power of the device is calculated by superposition). The SPN network service of the embodiment of the present invention is divided into the following layers: link layer, channel layer, FlexeGroup layer, L2VPN layer. Among them, the link layer is a plurality of single disks (corresponding to physical ports, i.e., single disk ports) connected to the physical layer; the other layers are virtual layers (corresponding to virtual network ports), which are above the physical layer, and the identifiers used for device communication are added. The network topology is divided into: network element, single disk, port. The network element is an artificial combination of a group of single disks of different types to provide a complete Internet access service. A single disk is an SPN single disk, which is a group of packet slice networks that can provide 5G standards. A port is an interface on a single disk that is used to connect to other devices. Network basic data is collected by obtaining it from a device management software. The device management software is modeled in a 1:1 manner and in a visual way. The device management software translates business information into a format that can be recognized by the device and sends it to the device through the protocol specified by the device.

[0057] Step 302: Use the traffic monitoring software to detect the traffic of the single disk port issued by the single disk, and use the traffic monitoring software to measure the traffic of the single disk port at every preset time interval.

[0058] The embodiment of the present invention obtains the flow of a single disk port by setting flow monitoring software, obtains the flow of a virtual port by corresponding software, and then calculates the total flow of the device by superposition.

[0059] Furthermore, the formula of the Prophet model described in the embodiment of the present invention is:

[0060] y(t)=g(t)+s(t)+h(t)+∈t

[0061] Among them, g(t) represents the growth function of device traffic over time, which is used to fit non-periodic changes; s(t) represents the Fourier function, which is used to fit periodic changes; h(t) represents changes caused by special reasons such as holidays and festivals; ∈t is a noise function, which is used to represent random and unpredictable traffic fluctuations.

[0062] The formula of the Fourier function is:

[0063]

[0064] Wherein, s(t) represents the periodic change of the flow of the device over time, P represents a fixed time period, An and Bn represent the parameters to be learned, where N=10 is used by default to characterize the periodic change in years, and N=3 is used to characterize the periodic change in weeks. It is worth noting that the fixed time period of P (selecting years or weeks) is determined according to the actual situation. In addition, the preset time described in step 301 and step 302 is set according to the actual situation (for example, the preset time interval can be set to 15 minutes but is not limited to), and the flow of the device at any time point can be obtained or predicted through the Prophet model.

[0065] Furthermore, the SPN service described in the embodiment of the present invention includes 5G service and dedicated line service, and the method of using service power allocation to obtain the power of the device service in each time period of a day is as follows: Figure 3 As shown, specifically including:

[0066] Step 401: Search for service-hitting single disks, public single disks and sub-frames in the network element layer, obtain the single disk power of the single disk allocated by the network element service bandwidth ratio, the power of the public single disk and sub-frame allocated by the network element service bandwidth ratio, and the power of the missed service single disk.

[0067] Among them, the embodiment of the present invention needs to find the service hitting single disk through the system at the "access network element (UPE, User-end-Provider-Edge, user-side operator edge device), ordinary aggregation and backbone aggregation (SPE, Superstratum-Provider-Edge, upper layer operator edge device)" level, allocate the service bandwidth ratio passing through the single disk to the single disk power a, then find the public single disk and sub-frame to allocate the service bandwidth ratio passing through the network element to the network element power b, and then set the single disk power of the missed service to c.

[0068] Step 402: Search for service-hitting single disks, public single disks, and sub-frames in the core layer; when the network element does not carry dedicated line services, allocate the network element power according to the bandwidth ratio of all 5G services in the network; when the network element carries dedicated line services, allocate the network element power according to the bandwidth ratio of the dedicated line and all 5G services; and find the power of the single disk for the missed service and set it to.

[0069] Among them, the embodiment of the present invention finds the service hit single disk, public single disk and sub-frame at the "core scheduling, core landing (NPE, Network-Provider-Edge, network side operator edge equipment)" level. The allocation is carried out according to the following two rules: 1. When the network element does not carry a dedicated line service, the network element power d is allocated according to the bandwidth ratio of all 5G services in the network; 2. When the network element carries a dedicated line service, the network element power e is allocated according to the bandwidth ratio of the dedicated line and all 5G services; then the power of the single disk of the missed service is set to f.

[0070] Step 403: According to the SPN service type, the 5G service power and the dedicated line service power of the device in each time period of the day are obtained by cumulative means, and the 5G service power and the dedicated line service power are added together to obtain the total power of the device in each time period of the day.

[0071] The calculation method of the SPN service power of the embodiment of the present invention calculates the power of a single disk and a network element by allocating and allocating, and finally sums up to complete the power measurement of the entire line; according to the SPN service type of the embodiment of the present invention, such as Figure 4 and Figure 5 As shown, the service power of 5G in the embodiment of the present invention = the power shared by the single disk through which the service is routed Σa + the power shared by the network element through which the service is routed Σb + the power shared by the core layer Σd + the power shared by the core layer Σe; the dedicated line service power = the power shared by the single disk through which the service is routed Σa + the power shared by the network element through which the service is routed Σb + the power shared by the core layer Σe. It is worth noting that the 5G service in the embodiment of the present invention includes base stations and LTE (macro base stations or indoor stations); the dedicated line service in the embodiment of the present invention includes group customer services, home broadband and other services.

[0072] In order to further optimize the equipment of the SPN network in the embodiment of the present invention, to avoid the problem of surplus or full load of the equipment in the SPN network causing waste of resources and shortening the life of the equipment, and thus achieve the effect of energy saving and emission reduction. The energy consumption threshold of the equipment in the embodiment of the present invention includes an upper threshold and a lower threshold. The calculated energy consumption value is compared with the energy consumption threshold, and optimization is performed according to the comparison result. By comparing the thresholds, it is determined that the equipment of the SPN network is optimized, such as Figure 6 As shown, specifically including:

[0073] Step 501: When the lower threshold is less than or equal to the calculated energy consumption value, and the upper threshold is greater than or equal to the calculated energy consumption value, it indicates that the device is in a stable working state, and the device does not need to be optimized.

[0074] Step 502: When the lower limit of the threshold is greater than the calculated energy consumption value, it indicates that the device is in a surplus state. At this time, the idle disks in the device are shut down to reduce the power in the device.

[0075] Step 503: When the upper threshold value is less than the calculated energy consumption value, it indicates that the device is in a full load state. At this time, the load of the device can be reduced by increasing the number of single disks in the device.

[0076] The embodiment of the present invention sets an upper threshold and a lower threshold, and compares the energy consumption value with the threshold set by the device, so as to optimize the device with corresponding measures, thereby avoiding the problem of resource waste caused by the surplus or full load of the device in the SPN network, and reducing the life of the device. It is worth noting that when there are a first device and a second device in the specific scenario of the embodiment of the present invention, and the first device is in a surplus state and the second device is in a full load state, the optimization method also includes establishing a temporary cascade relationship between the first device and the second device, and sharing the load in the second device through the first device, so as to use the surplus in the first device to reduce the load of the second device.

[0077] Compared with the prior art, the present invention obtains the power of the equipment in each time period based on the SPN network through the allocation method, uses the Prophet model to predict the traffic of the equipment in each time period, and then predicts the energy consumption value of the equipment in each time period, and compares the energy consumption value with the threshold set by the equipment to optimize the equipment, avoid the problem of surplus or full load of the equipment in the SPN network causing waste of resources and shortening the life of the equipment, thereby achieving the effect of energy saving and emission reduction.

[0078] Embodiment 2:

[0079] like Figure 7 , which is a schematic diagram of the architecture of a device based on an SPN network according to an embodiment of the present invention. The device based on an SPN network according to this embodiment includes one or more processors 21 and a memory 22. Figure 7 A processor 21 is taken as an example.

[0080] The processor 21 and the memory 22 may be connected via a bus or other means. Figure 7 The example of connecting through bus is taken in the following.

[0081] The memory 22 is a non-volatile computer-readable storage medium that can be used to store non-volatile software programs and non-volatile computer executable programs, such as the device optimization method based on the SPN network in Example 1. The processor 21 executes the device optimization method based on the SPN network by running the non-volatile software programs and instructions stored in the memory 22.

[0082] The memory 22 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage devices. In some embodiments, the memory 22 may optionally include a memory remotely arranged relative to the processor 21, and these remote memories may be connected to the processor 21 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0083] The program instructions / modules are stored in the memory 22, and when executed by the one or more processors 21, the device optimization method based on the SPN network in the above embodiment 1 is executed, for example, the above described Figure 1-6 The steps shown.

[0084] It is worth noting that the information interaction, execution process, etc. between the modules and units within the above-mentioned devices and systems are based on the same concept as the processing method embodiment of the present invention. The specific contents can be found in the description of the method embodiment of the present invention and will not be repeated here.

[0085] A person skilled in the art may understand that all or part of the steps in the various methods of the embodiments may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the storage medium may include: a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc.

[0086] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A device optimization method based on SPN network, characterized in that: include: Obtain the historical data of the device's single disk and the virtual network, and build a Prophet model. Use the Prophet model to predict the port traffic of the device's single disk port and the virtual network, and obtain the traffic forecast value of the device in each time period of the day. According to the characteristics of SPN services, the service power allocation method is used to obtain the power of equipment services in each time period of a day, and the energy consumption value of the equipment is calculated using the energy consumption calculation formula; Setting an energy consumption threshold of the device, comparing the calculated energy consumption value with the energy consumption threshold, and optimizing according to the comparison result; The SPN service includes 5G service and dedicated line service. The method of using service power allocation to obtain the power of the equipment service in each time period of a day specifically includes: Search for service-hit single disks, public single disks, and sub-frames in the network element layer, and obtain the single disk power of the single disk allocated by the network element service bandwidth ratio, the power of the public single disk and the sub-frame allocated by the network element service bandwidth ratio, and the power of the service-missing single disk; Find the service-hitting single disk, public single disk and sub-frame in the core layer; when the network element does not carry a dedicated line service, allocate the network element power according to the bandwidth ratio of all 5G services in the network; when the network element carries a dedicated line service, allocate the network element power according to the bandwidth ratio of the dedicated line and all 5G services; and find the power of the single disk of the missed service; According to the SPN service type, the 5G service power and dedicated line service power of the device in each time period of the day are obtained by accumulation, and the 5G service power and dedicated line service power are added together to obtain the total power of the device in each time period of the day.

2. The device optimization method based on SPN network according to claim 1 is characterized in that: The data of a single disk of a device includes the power data and flow data of a single disk. Before building the Prophet model, obtain the historical data of a single disk of the device, including: A power meter is installed at the port of each single disk of the equipment, and the full-load power, no-load power, and working power of each single disk are measured by the power meter at preset intervals; The flow monitoring software is used to detect the flow of the single disk port issued by the single disk, and the flow monitoring software is used to measure the flow of the single disk port at each preset time interval.

3. The device optimization method based on SPN network according to claim 1 is characterized in that: The data of the virtual network includes network service data and network topology information data, wherein the network service includes the Channel layer, the Flexe-Group layer and the L2VPN layer; the network topology includes network elements, single disks and ports.

4. The device optimization method based on SPN network according to claim 1 is characterized in that: The formula of the Prophet model is: in, It represents the growth function of equipment flow over time, which is used to fit non-periodic changes; represents the Fourier function, which is used to fit periodic changes; Indicates changes caused by special reasons such as holidays and festivals; is a noise function, which is used to represent random and unpredictable traffic fluctuations.

5. The device optimization method based on SPN network according to claim 4 is characterized in that: The formula of the Fourier function is: in, It indicates the periodic change of the flow rate of the equipment over time, P indicates a fixed time period, and Indicates the parameters that need to be learned, where the default is Describe the periodic changes in years. Characterizes periodic changes in weeks.

6. The device optimization method based on SPN network according to claim 1 is characterized in that: The energy consumption threshold of the device includes an upper threshold and a lower threshold. The calculated energy consumption value is compared with the energy consumption threshold, and optimization is performed according to the comparison result, specifically including: When the lower threshold is less than or equal to the calculated energy consumption value, and the upper threshold is greater than or equal to the calculated energy consumption value, it indicates that the device is in a stable working state and does not need to be optimized. When the lower limit of the threshold is greater than the calculated energy consumption value, it indicates that the device is in surplus state. At this time, the idle disks in the device are shut down to reduce the power in the device. When the upper threshold is less than the calculated energy consumption value, it means that the device is under full load. In this case, the load of the device can be reduced by increasing the number of single disks in the device.

7. The device optimization method based on SPN network according to claim 6 is characterized in that: When there are a first device and a second device, and the first device is in a surplus state and the second device is in a full load state, the optimization method also includes establishing a temporary cascade relationship between the first device and the second device, and sharing the load in the second device through the first device, so as to utilize the surplus in the first device to reduce the load of the second device.

8. A device based on SPN network, characterized in that: include: at least one processor; at least one memory; Among them, the at least one processor and the at least one memory are communicatively connected to each other, the at least one memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute a device optimization method based on an SPN network provided in any one of claims 1 to 7.

9. A non-volatile computer storage medium, characterized in that: The computer storage medium stores computer executable instructions, which are executed by one or more processors to complete the device optimization method based on the SPN network as described in any one of claims 1-7.

Images