Method and device for processing slice information in communication network and storage medium

Abstract

The invention discloses a slice information processing method and device in a communication network and a storage medium, and the method comprises the steps: obtaining the respective slice information of at least one communication session, obtaining the respective energy consumption information of each communication session, and carrying out the processing of the slice information according to each piece of slice information, and detecting the abnormal state of each energy consumption information. According to the invention, the slice information of the communication session can be fully utilized to judge the abnormal state of the energy consumption information of the communication session, namely whether the energy consumption information is normal or abnormal, so that the state of the communication session can be determined or the communication session can be further processed according to the abnormal state of the energy consumption information of the communication session; therefore, effective management of communication sessions and network slices is realized. The method is widely applied to the technical field of communication.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to a method, device and storage medium for processing slice information in a communication network. Background Art

[0002] With the popularization of 5G networks and more advanced communication systems, more and more devices and applications are beginning to access the network, which makes the requirements for network mobility, security, latency, reliability, etc. more diverse. In order to meet these requirements, network slicing technology came into being.

[0003] In the current communication network environment, user terminals or private network clients use a large number of internal applications in their daily work, and each application may be designed based on multiple network slices. Each network slice has its specific purpose and supports different applications. The data flows generated by these applications can generally be processed by the locally deployed user plane function (UPF).

[0004] Currently, there is a lack of effective management technology for network slicing, which leads to vicious competition among multiple network slices to grab network resources, or individual network slices occupying a large amount of network resources and affecting the use of other network slices. Summary of the invention

[0005] In response to the current technical problem of lack of effective management of network slices, the purpose of the present invention is to provide a slice information processing method, device and storage medium in a communication network.

[0006] On the one hand, an embodiment of the present invention includes a method for processing slice information in a communication network, and the method for processing slice information in a communication network includes the following steps:

[0007] Obtaining slice information of at least one communication session;

[0008] Obtaining energy consumption information of each of the communication sessions;

[0009] According to each of the slice information, an abnormal state of each of the energy consumption information is detected; the abnormal state indicates whether the energy consumption information is normal or abnormal.

[0010] Further, the obtaining of the energy consumption information of each of the communication sessions includes:

[0011] For any of the communication sessions, obtaining idle power consumption information, working bandwidth information, and working time information of the communication session;

[0012] Determining total power consumption information of the communication session according to the idle power consumption information and the working bandwidth information;

[0013] Energy consumption information of the communication session is determined according to the total power consumption information and the working time information.

[0014] Further, detecting the abnormal state of each of the energy consumption information according to each of the slice information includes:

[0015] Dividing the energy consumption information corresponding to the slice information belonging to the same slice type into the same data set;

[0016] For any of the data sets, determining whether each of the energy consumption information therein is an abnormal point or not;

[0017] For the energy consumption information belonging to the abnormal point, determining that the energy consumption information is abnormal;

[0018] For the energy consumption information that does not belong to an abnormal point, it is determined that the energy consumption information is normal.

[0019] Further, for any of the data sets, determining whether each of the energy consumption information therein is an abnormal point or not includes:

[0020] Using the isolation forest algorithm to process each of the data sets respectively;

[0021] According to the isolation forest algorithm, it is identified whether the energy consumption information belongs to an abnormal point or not.

[0022] Furthermore, the using of the isolation forest algorithm to process each of the data sets separately includes:

[0023] For any of the data sets, recursively perform multiple segmentation processes; any of the segmentation processes uses the corresponding segmentation value to divide the energy consumption information in the sub-data set into a left subtree or a right subtree, wherein the sub-data set segmented by the first segmentation process is the data set itself, and the sub-data set segmented by any other segmentation process is the left subtree or the right subtree segmented by the previous segmentation process;

[0024] Determine an isolated tree according to the left subtree and the right subtree respectively segmented by all the segmentation processes;

[0025] Determining an average path length based on the isolation tree;

[0026] For any of the energy consumption information, the path length is determined according to the position of the energy consumption information in the isolated tree, and the anomaly score of the energy consumption information is determined according to the path length and the average path length. When the anomaly score is greater than the score threshold, the energy consumption information is identified as belonging to an anomaly point; when the anomaly score is less than or equal to the score threshold, the energy consumption information is identified as not belonging to an anomaly point.

[0027] Furthermore, the slice information processing method in the communication network further includes:

[0028] According to the abnormal state, restriction processing is performed on the communication session.

[0029] Further, the restricting process on the communication session according to the abnormal state includes:

[0030] For any of the communication sessions whose abnormal state is abnormal, obtaining an energy consumption threshold according to the slice information corresponding to the communication session;

[0031] When the energy consumption information corresponding to the communication session is greater than the energy consumption threshold, the upper limit of the communication data transmission rate of the communication session is reduced; when the energy consumption information corresponding to the communication session is less than or equal to the energy consumption threshold, the upper limit of the communication data transmission rate of the communication session is maintained unchanged.

[0032] Further, the restricting process on the communication session according to the abnormal state includes:

[0033] For any of the communication sessions whose abnormal state is abnormal, obtaining an energy consumption threshold according to the slice information corresponding to the communication session;

[0034] When the energy consumption information corresponding to the communication session is greater than the energy consumption threshold, data rate specification information is obtained according to the slice type corresponding to the slice information, the upper limit of the communication data transmission rate of the communication session is reduced according to the data rate specification information, and the actual communication data transmission rate of the communication session after the upper limit of the communication data transmission rate is reduced is detected; when the actual communication data transmission rate matches the data rate specification information, the reduction of the upper limit of the communication data transmission rate of the communication session is cancelled; when the actual communication data transmission rate does not match the data rate specification information, the reduction of the upper limit of the communication data transmission rate of the communication session is maintained.

[0035] On the other hand, an embodiment of the present invention also includes a computer device, including a memory and a processor, the memory is used to store at least one program, and the processor is used to load at least one program to execute the slice information processing method in the communication network of the embodiment.

[0036] On the other hand, an embodiment of the present invention also includes a computer-readable storage medium, which stores a program executable by a processor, and the program executable by the processor is used to execute the slice information processing method in the communication network in the embodiment when executed by the processor.

[0037] The beneficial effect of the present invention is that the slice information processing method in the communication network in the embodiment can make full use of the slice information of the communication session to determine the abnormal state of the energy consumption information of the communication session, that is, whether the energy consumption information is normal or abnormal, so that the state of the communication session can be determined or the communication session can be further processed according to the abnormal state of the energy consumption information of the communication session, thereby realizing effective management of the communication session and network slices. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 Schematic diagram of the steps of the method for processing slice information in a communication network in an embodiment;

[0039] Figure 2 Schematic diagram of the principle of the isolation forest algorithm in the embodiment. DETAILED DESCRIPTION

[0040] Terminology explanation:

[0041] UPF: User Plane Function, is the unit responsible for user data message processing in the 5GC core network, supporting protocol interfaces such as GTP-U / C and PFCP to communicate with other 5GC network elements.

[0042] Isolation Forest Algorithm: Isolation Forest, referred to as iForest, is an unsupervised learning algorithm that can be used to identify outliers in a data set.

[0043] Network slicing: Network slicing is an on-demand networking method that allows operators to separate multiple virtual end-to-end networks on a unified infrastructure. Each network slice is logically isolated from the wireless access network to the bearer network and then to the core network to adapt to a variety of types of applications.

[0044] Slice type: indicates the type of network service or application scenario provided by the network slice. For example, network slices can be classified into slice types such as eMBB, mMTC or URLLC.

[0045] eMBB: Enhance Mobile Broadband. Typical applications provided by network slices of this type include ultra-high-definition video, virtual reality, and augmented reality.

[0046] mMTC: Massive Machine Type Communication, massive IoT communication. Typical applications provided by network slices belonging to this type of slice include smart cities, smart homes, etc.

[0047] URLLC: Ultra Reliable & Low Latency Communication, ultra-high reliability and ultra-low latency services. Typical applications provided by network slices of this type include industrial control, drone control, and intelligent driving control.

[0048] The slicing information processing method in the communication network in this embodiment can be applied to a 5G communication network or a more advanced communication system, and the 5G communication network is used as an example for illustration. When executing the slicing information processing method in the communication network, each step can be performed by the UPF in the core network of the 5G communication network. When the slicing information processing method in the communication network is applied in a more advanced communication system, the UPF network element may not exist. At this time, the steps in the slicing information processing method in the communication network can be performed by a device with the same function as the UPF.

[0049] In this embodiment, refer to Figure 1 , a method for processing slice information in a communication network comprises the following steps:

[0050] S1. Obtain slice information of at least one communication session;

[0051] S2. Obtaining energy consumption information of each communication session;

[0052] S3. Detect the abnormal state of each energy consumption information according to each slice information.

[0053] In step S1, the UPF may obtain the slice information. Specifically, the UPF may obtain the slice information of the communication session when the user terminal requests to create a communication session, and associate the communication session with the slice information.

[0054] In this embodiment, the slice information represents information such as the slice type, slice granularity, usage time, and average bandwidth of the network slice where the communication session is located.

[0055] In step S1, it is assumed that UPF creates communication session 1, communication session 2, ... communication session n For example, the slice information 1 corresponding to communication session 1, the slice information 2 corresponding to communication session 2, and so on are obtained. n Corresponding slice information n .

[0056] In step S2, the UPF obtains the energy consumption information of each communication session, for example, energy consumption information 1 corresponding to communication session 1, energy consumption information 2 corresponding to communication session 2, and so on. n Corresponding energy consumption information nThe energy consumption information indicates the amount of energy consumed by the user terminal and the communication core network and other devices during the communication session. In this embodiment, the energy consumption information of the communication session can be calculated based on the idle power consumption information, working bandwidth information and working time information of the communication session.

[0057] Communication Session i (i=1,2……n) as an example, we can use the formula

[0058] P i =P i(idle) +αBandwidth i

[0059] Calculate the communication session i Total power consumption information P i . Among them, P i(idle) Indicates a communication session i Idle power consumption information, that is, communication session i The energy consumed by user terminals and communication core network devices per unit time when idle. α is a positive proportional coefficient that reflects the impact of bandwidth on power consumption when user terminals and communication core network devices are working. i Indicates a communication session i The working bandwidth information of the communication session i The calculated total power consumption information P i Indicates a communication session i The energy consumed by user terminals, communication core network and other equipment per unit time during the entire establishment period, including idle and fully loaded.

[0060] Get communication session in computing i Total power consumption information P i Afterwards, we can use the formula

[0061] E i =P i t i

[0062] Calculate the communication session i Energy consumption information E i , where t i Indicates a communication session i Working time information, that is, the duration from establishment to the present.

[0063] In step S3, the abnormal state of each energy consumption information is detected according to the slice information of each communication session. i , according to the communication session i Corresponding slice information i , detect energy consumption informationi abnormal state, that is, detecting energy consumption information i Is it normal or abnormal.

[0064] In this embodiment, by executing steps S1-S3, the slice information of the communication session can be fully utilized to determine the abnormal state of the energy consumption information of the communication session, that is, whether the energy consumption information is normal or abnormal, so that the state of the communication session can be determined or the communication session can be further processed based on the abnormal state of the energy consumption information of the communication session, thereby realizing effective management of the communication session and network slices.

[0065] In this embodiment, when executing step S3, that is, the step of detecting the abnormal state of each energy consumption information according to each slice information, the following steps may be specifically performed:

[0066] S301. Divide the energy consumption information of the corresponding slice information belonging to the same slice type into the same data set;

[0067] S302. For any data set, determine whether each energy consumption information therein is an abnormal point or not;

[0068] S303. For energy consumption information belonging to abnormal points, determine that the energy consumption information is abnormal;

[0069] S304. For energy consumption information that does not belong to an abnormal point, determine that the energy consumption information is normal.

[0070] The communication session 1, communication session 2, ... communication session obtained in step S1 n etc. The corresponding slice information 1, slice information 2... slice information n Etc., respectively belong to slice types such as eMBB, mMTC or URLLC, and each slice information can be classified according to the slice type, for example, the following classification results are obtained:

[0071] eMBB: {slice information 1, slice information 2, ... slice information 9}

[0072] mMTC: {Slice information 10 , slice information 11 , ... Slice information 20}

[0073] URLLC: {Slice information 21 , slice information 22 , ... Slice information 30}

[0074] Since there is a corresponding relationship such as "slice information 1 and energy consumption information 1 both correspond to communication session 1", the above classification actually completes the classification of each energy consumption information, thereby obtaining the following data set:

[0075] The first data set: {energy consumption information 1, energy consumption information 2, ..., energy consumption information 9}

[0076] Second data set: {Energy consumption information 10 , energy consumption information 11 , ...energy consumption information 20}

[0077] The third data set: {Energy consumption information 21 , energy consumption information 22 , ...energy consumption information 30}

[0078] The first data set is a data set consisting of energy consumption information corresponding to the slice type of eMBB, the second data set is a data set consisting of energy consumption information corresponding to the slice type of mMTC, and the third data set is a data set consisting of energy consumption information corresponding to the slice type of URLLC.

[0079] In step S302, energy consumption information belonging to abnormal points in each data set may be detected independently.

[0080] In this embodiment, when executing step S302, an isolation forest algorithm may be used to identify whether the energy consumption information in the same data set is an outlier or not.

[0081] Specifically, the process of the isolation forest algorithm includes the following steps:

[0082] S30201. For any data set, recursively perform multiple segmentation processes;

[0083] S30202. Determine an isolated tree according to the left subtree and the right subtree respectively segmented in the entire segmentation process;

[0084] S30203. Determine the average path length based on the isolated tree;

[0085] S30204. For any energy consumption information, the path length is determined according to the position of the energy consumption information in the isolated tree, and the anomaly score of the energy consumption information is determined according to the path length and the average path length. When the anomaly score is greater than the score threshold, the energy consumption information is identified as an anomaly point. When the anomaly score is less than or equal to the score threshold, the energy consumption information is identified as not belonging to an anomaly point.

[0086] Steps S30201 - S30204 are described by taking identifying abnormal points in the first data set as an example.

[0087] Reference Figure 2In step S30201, for the first data set {energy consumption information 1, energy consumption information 2, ..., energy consumption information 9}, the first round of segmentation process is first performed, as shown in the largest rectangular box, using a segmentation value 1, and energy consumption information 1, energy consumption information 2, energy consumption information 3, and energy consumption information 4, which are less than the segmentation value 1, are divided into the left subtree of the first round of segmentation process, that is, the left part of the largest rectangular box. Similarly, energy consumption information 5, energy consumption information 6, energy consumption information 7, energy consumption information 8, and energy consumption information 9, which are greater than the segmentation value 1, are divided into the right subtree of the first round of segmentation process, that is, the right part of the largest rectangular box; then the second round of segmentation process is performed, as shown in the smaller rectangular box on the left, so that The left subtree segmented in the first round of segmentation process is segmented again with a segmentation value of 2, and one of the left subtrees (including energy consumption information 3 and energy consumption information 4) and one of the right subtrees (including energy consumption information 1 and energy consumption information 2) of the second round of segmentation process is obtained. Similarly, as shown in the smaller rectangular box on the right, the left subtree segmented in the first round of segmentation process is segmented again with a segmentation value of 3, and one of the left subtrees (including energy consumption information 5, energy consumption information 6 and energy consumption information 7) and one of the right subtrees (including energy consumption information 8 and energy consumption information 9) of the second round of segmentation process is obtained. The above segmentation process is recursively performed multiple times, thereby segmenting multiple left subtrees and right subtrees at different levels. In step S30202, the subtree obtained by the segmentation process executed later is used as the descendant of the subtree obtained by the segmentation process executed earlier, so that the left subtree and the right subtree segmented in step S30201 are formed into an isolated tree.

[0088] In step S30203, the average path length corresponding to the isolated tree can be determined based on the isolated tree established in step S30202.

[0089] In this embodiment, if the number of nodes, i.e., energy consumption information, contained in the isolated tree is m, then according to the formula

[0090] c(n)=2H(n-1)-2(n-1) / n

[0091] Calculate the average path length c(n). Where H(j) is the jth harmonic number, which can be obtained by the formula

[0092] H(i)=∑ i k＝1 1 / k

[0093] to calculate.

[0094] In step S30204, each node in the isolated tree, namely, energy consumption information, can calculate the corresponding path length. Specifically, given a node, namely, energy consumption information x, its path length h(x) in the isolated tree is the number of steps from the root node to this node.

[0095] In step S30204, for a given node, namely, energy consumption information x, the average path length c(n) of the isolated tree and the path length h(x) of the energy consumption information x are known, and the formula

[0096] s(x,n)=2 -h(x) / c(n)

[0097] Calculate the anomaly score s(x,n) corresponding to the energy consumption information x.

[0098] When s(x,n) is closer to 1, it means that the energy consumption information x is easier to be isolated, and thus the energy consumption information is more likely to be an abnormal point; when s(x,n) is closer to 0, it means that the energy consumption information x is more difficult to be isolated, and thus the energy consumption information is more likely to be a normal point.

[0099] In step S30204, a threshold value (for example, 0.7) can be set. If s(x,n)>0.7, the energy consumption information x is identified as an abnormal point, and the abnormal state of the energy consumption information x is determined to be abnormal; conversely, if s(x,n)≤0.7, the energy consumption information x is identified as not belonging to an abnormal point, that is, the energy consumption information x is identified as a normal point, and the abnormal state of the energy consumption information x is determined to be normal.

[0100] For example, when executing steps S301-S304, it is assumed that the bandwidth of the user terminal is 200 Mbps and the power is 70 W when fully loaded, and the power is P when idle. idle is 5W, and the slice information is shown in Table 1.

[0101] Table 1

[0102] Slice Type (SST) Slice granularity (Mbps) 001 150 002 200 003 100

[0103] Communication session 1 accesses application 1, carrying a slice service type of 001. After 10 hours of calculation and collection of data, the average bandwidth is 200 Mbps;

[0104] Communication session 2 accesses application 2, carrying the slice service type of 002. After 10 hours of calculation and collection of data, the average bandwidth is 200 Mbps;

[0105] Communication session 3 accesses application 3, carrying the slice service type of 003. After 10 hours of calculation and collection of data, the average bandwidth is 50Mbps.

[0106] The recognition results of the abnormal states of the energy consumption information corresponding to communication session 1, communication session 2 and communication session 3 are shown in Table 2.

[0107] Table 2

[0108]

[0109] It can be seen from Table 2 that the energy consumption information 1 corresponding to the communication session 1 is abnormal, and the communication session 1 can be processed accordingly.

[0110] In this embodiment, the UPF may further perform the following steps based on performing steps S1-S3:

[0111] S4. According to the abnormal state, restrict the communication session.

[0112] By executing step S4 to restrict the communication session with abnormal power consumption, such as limiting the bandwidth, the power consumption can be reduced and energy can be saved.

[0113] In this embodiment, when executing step S4, that is, the step of restricting the communication session according to the abnormal state, the following steps may be specifically performed:

[0114] S401A. For any communication session in which the abnormal state is abnormal, the energy consumption threshold is obtained according to the slice information corresponding to the communication session;

[0115] S402A. When the energy consumption information corresponding to the communication session is greater than the energy consumption threshold, the upper limit of the communication data transmission rate of the communication session is reduced; when the energy consumption information corresponding to the communication session is less than or equal to the energy consumption threshold, the upper limit of the communication data transmission rate of the communication session is maintained unchanged.

[0116] Steps S401A-S402A are the first execution mode of step S4.

[0117] In step S401A, taking communication session 1 as an example, its corresponding energy consumption information 1 is abnormal, so the energy consumption threshold can be obtained according to the slice information corresponding to communication session 1, such as the slice type corresponding to communication session 1. The energy consumption threshold can be a fixed value or a value such as the average value of all communication sessions of the same slice type.

[0118] In step S402A, the energy consumption threshold value obtained in step S401A is used to determine the size of energy consumption information 1 of communication session 1. If the energy consumption information 1 is greater than the energy consumption threshold value, it is determined that the energy consumption information 1 is too large, and the communication data transmission rate upper limit of the communication session 1 is reduced, thereby limiting the network speed of the communication session 1 to reduce the energy consumption generated by the communication session 1; if the energy consumption information 1 is less than or equal to the energy consumption threshold value, it is determined that the energy consumption information 1 is normal, and the communication data transmission rate upper limit of the communication session is maintained unchanged.

[0119] By executing steps S401A-S402A, the power consumption reduction and energy saving effect can be achieved.

[0120] In this embodiment, when executing step S4, that is, the step of restricting the communication session according to the abnormal state, the following steps may be specifically performed:

[0121] S401B. For any communication session in which the abnormal state is abnormal, the energy consumption threshold is obtained according to the slice information corresponding to the communication session;

[0122] S402B. When the energy consumption information corresponding to the communication session is greater than the energy consumption threshold, the data rate specification information is obtained according to the slice type corresponding to the slice information;

[0123] S403B according to the data rate specification information to reduce the upper limit of the communication data transmission rate of the communication session, the detection of the communication data transmission rate upper limit after the actual communication data transmission rate of the communication session is reduced;

[0124] S404B when the actual communication data transmission rate matches the data rate specification information, the removal of the communication session communication data transmission rate limit reduction;

[0125] S405B. When the actual communication data transmission rate does not match the data rate specification information, maintain the reduction of the communication data transmission rate upper limit for the communication session.

[0126] Steps S401B-S405B are a second execution mode of step S4.

[0127] The principle of step S401B is the same as that of step S401A. Taking communication session 1 as an example, the corresponding energy consumption information 1 is abnormal, so the energy consumption threshold can be obtained according to the slice information corresponding to communication session 1, such as the slice type corresponding to communication session 1.

[0128] In step S402B, if it is determined that the energy consumption information 1 corresponding to the communication session 1 is greater than the energy consumption threshold, it indicates that the energy consumption of the communication session 1 is too high, and steps S403B-S405B need to be executed to limit the network speed of the communication session 1. However, in step S402B, the network speed of the communication session 1 is not directly limited, but the data rate specification information is first obtained according to the slice type corresponding to the slice information 1 of the communication session 1.

[0129] In this embodiment, the data rate specification information indicates the communication data transmission rate size or interval and other information when the network slice belonging to this slice type is working normally. For example, assuming that the slice type corresponding to communication session 1 is eMBB, since the typical applications provided by the network slice belonging to this slice type include ultra-high-definition video, etc., its data rate specification information may be the communication data transmission rate level divided according to high-definition videos of different resolutions / bit rates, etc., for example:

[0130] 1080P video: 800Kbps-1.5Mbps

[0131] 2K video: 2Mbps-10Mbps

[0132] 4K video: 20Mbps-50 Mbps

[0133] 8K video: 70Mbps-100 Mbps

[0134] In step S403B, assuming that the upper limit of the communication data transmission rate currently executed by UPF for communication session 1 is a specific value of 100Mbps, which is equivalent to the level of 70Mbps-100 Mbps in the data rate specification information, then when executing step S403B, the upper limit of the communication data transmission rate of communication session 1 can be reduced by less than one level relative to the data rate specification information, so that the lowered upper limit of the communication data transmission rate of communication session 1 does not belong to any level of value in the data rate specification information.

[0135] For example, when executing step S403B, the upper limit of the communication data transmission rate of communication session 1 may be reduced to 60 Mbps, which is higher than the 20 Mbps-50 Mbps level in the data rate specification information, but lower than the currently implemented 70 Mbps-100 Mbps level.

[0136] In step S403B, the actual communication data transmission rate of the communication session 1 after the upper limit of the communication data transmission rate is lowered is detected. Since the upper limit of the communication data transmission rate of the communication session 1 is lowered to 60 Mbps by executing step S403B, the actual communication data transmission rate will not be higher than 60 Mbps. The UPF detects whether the actual communication data transmission rate of the communication session 1 after the lowering matches the data rate specification information.

[0137] In this embodiment, if the actual communication data transmission rate is stably in the data rate specification information, which is equivalent to the next level of the level of the upper limit of the communication data transmission rate before the reduction, then the UPF can determine that the actual communication data transmission rate matches the data rate specification information. For example, if the actual communication data transmission rate detected in step S403B is stably between 20Mbps-50 Mbps, then the UPF can determine that the actual communication data transmission rate matches the data rate specification information; on the contrary, if the actual communication data transmission rate is not stably in the data rate specification information, which is equivalent to the next level of the level of the upper limit of the communication data transmission rate before the reduction, then the UPF can determine that the actual communication data transmission rate does not match the data rate specification information. For example, if the actual communication data transmission rate detected in step S403B is 55Mbps, then the UPF can determine that the actual communication data transmission rate does not match the data rate specification information.

[0138] In this embodiment, another judgment criterion may also be adopted: if the actual communication data transmission rate remains equal to the lowered upper limit of the communication data transmission rate (or the difference is less than a threshold), then the UPF may determine that the actual communication data transmission rate does not match the data rate specification information. For example, if the actual communication data transmission rate is 60Mbps (equal to the lowered upper limit of the communication data transmission rate), then the UPF may determine that the actual communication data transmission rate does not match the data rate specification information. On the contrary, if the actual communication data transmission rate remains unequal to the lowered upper limit of the communication data transmission rate (or the difference is greater than a threshold), then the UPF may determine that the actual communication data transmission rate matches the data rate specification information.

[0139] When it is determined in step S403B that the actual communication data transmission rate matches the data rate specification information, step S404B is executed to cancel the reduction of the communication data transmission rate upper limit of the communication session, so that the communication data transmission rate upper limit is restored to the level before the reduction. For example, step S405B is executed for communication session 1, so that the communication data transmission rate upper limit reduced to 60Mbps can be restored to 100Mbps before the reduction.

[0140] When it is determined in step S403B that the actual communication data transmission rate does not match the data rate specification information, step S405B is executed to maintain the reduction of the communication data transmission rate upper limit of the communication session. For example, step S405B is executed for communication session 1, so that the communication data transmission rate upper limit of communication session 1 is maintained at 60 Mbps after the reduction without executing other operations.

[0141] In this embodiment, the principle of executing steps S401B-S405B is that after the communication data transmission rate upper limit is reduced in step S403B, the actual communication data transmission rate of the communication session will also be reduced, but the actual communication data transmission rate after the reduction may not necessarily comply with the data rate specification information; if the actual communication data transmission rate after the reduction matches the data rate specification information, it indicates that the actual communication data transmission rate of the communication session is more likely to be caused by a network slice that complies with the data rate specification information of the current slice type (for example, a high-definition video service provided by a network slice with a slice type of eMBB automatically reduces the actual communication data transmission rate according to the data rate specification information based on the reduced communication data transmission rate upper limit). Data transmission rate), the energy consumption information of the communication session that was previously judged to be abnormal is more likely to be caused by legitimate reasons such as core network equipment failure, and therefore step S404B can be executed to restore the upper limit of the communication data transmission rate; if the actual communication data transmission rate after the reduction does not match the data rate specification information, it indicates that the actual communication data transmission rate of the communication session is more likely to be caused by factors such as malicious applications that do not comply with the data rate specification information (for example, malicious applications will only use up the network speed that the upper limit of the communication data transmission rate can provide, and will not follow the data rate specification information), and therefore step S405B can be executed to continue to maintain the reduction of the upper limit of the communication data transmission rate to reduce the impact of factors such as malicious applications.

[0142] A computer program for executing the slice information processing method in the communication network in this embodiment can be written and written into a computer device or a storage medium. When the computer program is read out and executed, the slice information processing method in the communication network in this embodiment is executed, thereby achieving the same technical effect as the slice information processing method in the communication network in the embodiment.

[0143] It should be noted that, unless otherwise specified, when a feature is referred to as being "fixed" or "connected" to another feature, it may be directly fixed or connected to the other feature, or it may be indirectly fixed or connected to the other feature. In addition, the descriptions of up, down, left, right, etc. used in the present disclosure are only relative to the relative positional relationship of the components of the present disclosure in the accompanying drawings. The singular forms of "a", "" and "the" used in the present disclosure are also intended to include the plural forms, unless the context clearly indicates other meanings. In addition, unless otherwise defined, all technical and scientific terms used in this embodiment have the same meaning as those generally understood by those skilled in the art. The terms used in the specification of this embodiment are only for describing specific embodiments and are not intended to limit the present invention. The term "and / or" used in this embodiment includes any combination of one or more related listed items.

[0144] It should be understood that, although the term first, second, third etc. may be adopted to describe various elements in the present disclosure, these elements should not be limited to these terms. These terms are only used to distinguish the same type of elements from each other. For example, without departing from the scope of the present disclosure, the first element may also be referred to as the second element, and similarly, the second element may also be referred to as the first element. The use of any and all examples or exemplary language ("for example", "such as" etc.) provided by the present embodiment is only intended to better illustrate embodiments of the present invention, and unless otherwise required, the scope of the present invention will not be limited.

[0145] It should be appreciated that embodiments of the present invention may be implemented or enforced by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer-readable memory. The method may be implemented in a computer program using standard programming techniques - including a non-transitory computer-readable storage medium configured with a computer program, wherein the storage medium so configured causes the computer to operate in a specific and predefined manner - according to the methods and drawings described in the specific embodiments. Each program may be implemented in a high-level procedural or object-oriented programming language to communicate with a computer system. However, if desired, the program may be implemented in assembly or machine language. In any case, the language may be a compiled or interpreted language. In addition, the program may be run on a programmed dedicated integrated circuit for this purpose.

[0146] In addition, the operations of the process described in this embodiment may be performed in any suitable order, unless otherwise indicated in this embodiment or otherwise clearly contradicted by the context. The process described in this embodiment (or variations and / or combinations thereof) may be performed under the control of one or more computer systems configured with executable instructions, and may be implemented as a code (e.g., executable instructions, one or more computer programs, or one or more applications) executed on one or more processors in common, by hardware or a combination thereof. A computer program includes a plurality of instructions that may be executed by one or more processors.

[0147] Further, the method can be implemented in any type of computing platform that is operably connected to a suitable computer, including but not limited to a personal computer, a minicomputer, a mainframe, a workstation, a network or distributed computing environment, a separate or integrated computer platform, or in communication with a charged particle tool or other imaging device, etc. Various aspects of the present invention can be implemented in machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated into a computing platform, such as a hard disk, an optical read and / or write storage medium, a RAM, a ROM, etc., so that it can be read by a programmable computer, and when the storage medium or device is read by the computer, it can be used to configure and operate the computer to perform the process described herein. In addition, the machine-readable code, or part thereof, can be transmitted via a wired or wireless network. When such media includes instructions or programs that implement the above steps in conjunction with a microprocessor or other data processor, the invention of this embodiment includes these and other different types of non-transitory computer-readable storage media. When programmed according to the methods and techniques of the present invention, the present invention also includes the computer itself.

[0148] The computer program can be applied to input data to perform the functions of the present embodiment, thereby converting the input data to generate output data stored in a non-volatile memory. The output information can also be applied to one or more output devices such as a display. In a preferred embodiment of the present invention, the converted data represents a physical and tangible object, including a specific visual depiction of the physical and tangible object produced on the display.

[0149] The above are only preferred embodiments of the present invention. The present invention is not limited to the above embodiments. As long as the technical effects of the present invention are achieved by the same means, any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included in the scope of protection of the present invention. Within the scope of protection of the present invention, its technical solutions and / or implementation methods may have various modifications and changes.

Claims

1. A method for processing slice information in a communication network, characterized in that: The slice information processing method in the communication network includes: Obtaining slice information of at least one communication session; Obtaining energy consumption information of each of the communication sessions; According to each of the slice information, an abnormal state of each of the energy consumption information is detected; the abnormal state indicates whether the energy consumption information is normal or abnormal.

2. The method for processing slice information in a communication network according to claim 1, characterized in that: The obtaining of the energy consumption information of each of the communication sessions comprises: For any of the communication sessions, obtaining idle power consumption information, working bandwidth information, and working time information of the communication session; Determining total power consumption information of the communication session according to the idle power consumption information and the working bandwidth information; Energy consumption information of the communication session is determined according to the total power consumption information and the working time information.

3. The method for processing slice information in a communication network according to claim 1, characterized in that: The detecting, according to each of the slice information, respective abnormal states of each of the energy consumption information, comprises: Dividing the energy consumption information corresponding to the slice information belonging to the same slice type into the same data set; For any of the data sets, determining whether each of the energy consumption information therein is an abnormal point or not; For the energy consumption information belonging to the abnormal point, determining that the energy consumption information is abnormal; For the energy consumption information that does not belong to an abnormal point, it is determined that the energy consumption information is normal.

4. The method for processing slice information in a communication network according to claim 3, characterized in that: For any of the data sets, determining whether each of the energy consumption information therein is an abnormal point or not includes: Using the isolation forest algorithm to process each of the data sets respectively; According to the isolation forest algorithm, it is identified whether the energy consumption information belongs to an abnormal point or not.

5. The method for processing slice information in a communication network according to claim 4, characterized in that: The using of the isolation forest algorithm to process each of the data sets respectively includes: For any of the data sets, recursively perform multiple segmentation processes; any of the segmentation processes uses the corresponding segmentation value to divide the energy consumption information in the sub-data set into a left subtree or a right subtree, wherein the sub-data set segmented by the first segmentation process is the data set itself, and the sub-data set segmented by any other segmentation process is the left subtree or the right subtree segmented by the previous segmentation process; Determine an isolated tree according to the left subtree and the right subtree respectively segmented by all the segmentation processes; Determining an average path length based on the isolation tree; For any of the energy consumption information, the path length is determined according to the position of the energy consumption information in the isolated tree, and the anomaly score of the energy consumption information is determined according to the path length and the average path length. When the anomaly score is greater than the score threshold, the energy consumption information is identified as belonging to an anomaly point; when the anomaly score is less than or equal to the score threshold, the energy consumption information is identified as not belonging to an anomaly point.

6. The method for processing slice information in a communication network according to any one of claims 1 to 5, characterized in that: The slice information processing method in the communication network also includes: According to the abnormal state, restriction processing is performed on the communication session.

7. The method for processing slice information in a communication network according to claim 6, characterized in that: The restricting process on the communication session according to the abnormal state includes: For any of the communication sessions whose abnormal state is abnormal, obtaining an energy consumption threshold according to the slice information corresponding to the communication session; When the energy consumption information corresponding to the communication session is greater than the energy consumption threshold, the upper limit of the communication data transmission rate of the communication session is reduced; when the energy consumption information corresponding to the communication session is less than or equal to the energy consumption threshold, the upper limit of the communication data transmission rate of the communication session is maintained unchanged.

8. The method for processing slice information in a communication network according to claim 6, characterized in that: The restricting process on the communication session according to the abnormal state includes: For any of the communication sessions whose abnormal state is abnormal, obtaining an energy consumption threshold according to the slice information corresponding to the communication session; When the energy consumption information corresponding to the communication session is greater than the energy consumption threshold, data rate specification information is obtained according to the slice type corresponding to the slice information, the upper limit of the communication data transmission rate of the communication session is reduced according to the data rate specification information, and the actual communication data transmission rate of the communication session after the upper limit of the communication data transmission rate is reduced is detected; when the actual communication data transmission rate matches the data rate specification information, the reduction of the upper limit of the communication data transmission rate of the communication session is cancelled; when the actual communication data transmission rate does not match the data rate specification information, the reduction of the upper limit of the communication data transmission rate of the communication session is maintained.

9. A computer device, characterized in that: It includes a memory and a processor, the memory is used to store at least one program, and the processor is used to load at least one program to execute the slice information processing method in a communication network as described in any one of claims 1-8.

10. A computer-readable storage medium storing a program executable by a processor, characterized in that: The processor executable program is used to execute the slice information processing method in the communication network described in any one of claims 1-8 when executed by the processor.

Images