CN110933701B - Network load state detection method and device - Google Patents
Network load state detection method and device Download PDFInfo
- Publication number
- CN110933701B CN110933701B CN201911288966.9A CN201911288966A CN110933701B CN 110933701 B CN110933701 B CN 110933701B CN 201911288966 A CN201911288966 A CN 201911288966A CN 110933701 B CN110933701 B CN 110933701B
- Authority
- CN
- China
- Prior art keywords
- load
- determining
- network
- index
- proportion
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims description 27
- 238000000034 method Methods 0.000 claims abstract description 38
- 230000001186 cumulative effect Effects 0.000 claims description 26
- 238000012163 sequencing technique Methods 0.000 claims description 11
- 238000009825 accumulation Methods 0.000 claims description 8
- 238000007689 inspection Methods 0.000 abstract description 3
- 230000009897 systematic effect Effects 0.000 abstract description 3
- 230000008569 process Effects 0.000 description 15
- 230000006855 networking Effects 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000011156 evaluation Methods 0.000 description 5
- 238000009795 derivation Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000013016 damping Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/08—Testing, supervising or monitoring using real traffic
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0876—Network utilisation, e.g. volume of load or congestion level
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/16—Threshold monitoring
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
- H04L47/12—Avoiding congestion; Recovering from congestion
- H04L47/125—Avoiding congestion; Recovering from congestion by balancing the load, e.g. traffic engineering
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W28/00—Network traffic management; Network resource management
- H04W28/02—Traffic management, e.g. flow control or congestion control
- H04W28/08—Load balancing or load distribution
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Environmental & Geological Engineering (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a method and a device for detecting network load state, wherein the method comprises the following steps: acquiring AP load capacity on each AC in the network; for each AC, acquiring a load upper limit of the AC, and taking a ratio of the AP load capacity of the AC to the load upper limit as a load proportion of the AC; determining a load balancing index of the network based on the load proportion of each AC; and determining whether the network load is balanced according to the load balancing index. After AP load capacity of each AC is obtained, load capacity difference of different types of AC is considered, and load balance indexes are determined by calculating load proportion of the AC so as to eliminate interference caused by heterogeneous factors in a network. And because the load balance index is obtained by integrating the load proportions of all the ACs, which is equivalent to systematic inspection, the load balance index can be used as the basis for evaluating the overall load state of the network, and network jitter caused by frequently executing an adjustment strategy can be avoided.
Description
Technical Field
The invention relates to the technical field of communication, in particular to a network load state detection method and device.
Background
With the wide application of wireless technologies, the number of terminals and APs (Access points) in a wireless networking is also increasing, so that a large-scale AC (Access Controller) cluster is required to replace a single AC management networking, and the types of ACs in the cluster are usually different, which results in different capabilities (number and type) of each AC loading an AP.
At present, load scheduling of the AP among the ACs is uniformly implemented through the cloud server to ensure that load performance among different ACs is kept balanced. When a new AP is on line, after the designated AC is finished by using the load sharing algorithm, if the load capacity of the designated AC exceeds a certain threshold, comparing whether the load capacity of the designated AC exceeds a certain proportion of the load capacities of other ACs, and if so, executing the load sharing algorithm again to designate the AC.
However, the above method is limited by the trigger timing, and only can check for individual AC, and does not perform system check on the network load, so the result obtained based on this is only used to guide local load adjustment, and cannot be used as the basis for evaluating the load balancing status of the whole network.
Disclosure of Invention
The present invention provides a method and an apparatus for detecting a network load status, which are directed to the above deficiencies of the prior art, and the objective is achieved by the following technical solutions.
A first aspect of the present invention provides a method for detecting a network load status, where the method includes:
acquiring AP load capacity on each AC in the network;
for each AC, acquiring the load upper limit of the AC, and taking the ratio of the AP load capacity of the AC to the load upper limit as the load proportion of the AC;
determining a load balancing index of the network based on the load proportion of each AC;
and determining whether the network load is balanced according to the load balancing index.
A second aspect of the present invention provides a network load status detection apparatus, including:
the acquisition module is used for acquiring AP load capacity on each AC in the network, acquiring the load upper limit of each AC, and taking the ratio of the AP load capacity of each AC to the load upper limit as the load proportion of each AC;
the determining module is used for determining a load balancing index of the network based on the load proportion of each AC;
and the detection module is used for determining whether the network load is balanced according to the load balancing index.
A third aspect of the invention proposes a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method according to the first aspect when executing the program.
A fourth aspect of the present invention proposes a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, carries out the steps of the method according to the first aspect as described above.
In the embodiment of the invention, by acquiring the AP load capacity of each AC in the network and acquiring the load upper limit of each AC, the ratio of the AP load capacity of the AC to the load upper limit is used as the load proportion of the AC, then the load balance index of the network is determined based on the load proportion of each AC, and whether the network load is balanced is determined according to the load balance index.
Based on the above description, after the AP load amounts of the ACs are obtained, load balancing indexes are determined by calculating load ratios of the ACs in consideration of load capacity differences of the ACs of different models, so as to eliminate interference caused by heterogeneous factors in the network. And because the load balance index is obtained by integrating the load proportions of all the ACs, which is equivalent to systematic inspection, the load balance index can be used as the basis for evaluating the overall load state of the network, and network jitter caused by frequently executing an adjustment strategy can be avoided.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention and not to limit the invention. In the drawings:
FIG. 1 is a diagram illustrating a virtualized networking architecture in accordance with an exemplary embodiment of the present invention;
fig. 2A is a flowchart illustrating an embodiment of a network load status detection method according to an exemplary embodiment of the present invention;
FIG. 2B is a graph illustrating Lorentz curves and Keyny coefficients in an economic neighborhood according to the embodiment of FIG. 2A;
FIG. 2C is a schematic diagram illustrating an AP load balancing state fitting curve according to the embodiment shown in FIG. 2A;
fig. 3 is a hardware structure diagram of a cloud server according to an exemplary embodiment of the present invention;
fig. 4 is a flowchart illustrating an embodiment of a network load status detection apparatus according to an exemplary embodiment of the present invention.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. The following description refers to the accompanying drawings in which the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the present invention. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the invention, as detailed in the appended claims.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It is to be understood that although the terms first, second, third, etc. may be used herein to describe various information, these information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present invention. The word "if," as used herein, may be interpreted as "at … …" or "when … …" or "in response to a determination," depending on the context.
The virtualized networking structure shown in fig. 1 includes a cloud server and AC clusters, each AC in the AC clusters may access multiple APs, and fig. 1 exemplarily shows that each AC accesses one AP.
The cloud server serves as a unified entrance to respond to the AP online application, executes a load balancing algorithm to distribute the designated AC for the new online AP, compares whether the load of the designated AC exceeds a certain proportion of the loads of other ACs if the load of the designated AC exceeds a certain threshold, and executes the load sharing algorithm again to designate the AC if the load of the designated AC exceeds the certain proportion of the loads of other ACs, so that the load performance among different ACs is kept balanced basically.
For example, assuming that the load upper limit of AC1 is 2K, the load upper limit of AC2 is 1K, the load amount of AC1 is 900, and the load amount of AC2 is 500, after AC1 is allocated to the new online AP, a situation may occur in which the load amount of AC1 exceeds a certain threshold value, and the load balancing algorithm needs to be executed again.
After the initial load distribution is completed, the balance may be broken due to some abnormal external stimulus, so that the load balance state of the network needs to be evaluated to determine whether to execute the adjustment strategy or maintain the status.
However, besides being limited by the trigger timing, the related art can only check for individual AC, and the check result obtained based on this can only guide local load adjustment, and cannot be used as a basis for evaluating the overall load balancing state of the network. And the calculation mode of directly adopting the AP load amount as a parameter is not suitable for heterogeneous networks with different load upper limits of the AC.
In order to solve the technical problem, the invention provides a network load state detection method, wherein a cloud server acquires AP load capacity on each AC in a network and a load upper limit of each AC, a ratio between the AP load capacity of the AC and the load upper limit is used as a load proportion of the AC, then a load balance index of the network is determined based on the load proportion of each AC, and whether the network load is balanced or not is determined according to the load balance index.
Based on the above description, after the AP load amounts of the ACs are obtained, load balancing indexes are determined by calculating load ratios of the ACs in consideration of load capacity differences of the ACs of different models, so as to eliminate interference caused by heterogeneous factors in the network. And because the load balancing index is obtained by integrating the load proportions of all the ACs, which is equivalent to systematic inspection, the load balancing index can be used as the basis for evaluating the overall load state of the network, and meanwhile, network jitter caused by frequently executing an adjustment strategy can be avoided.
The network load status detection scheme proposed by the present invention is explained in detail with specific embodiments below.
Fig. 2A is a flowchart of an embodiment of a network load status detection method according to an exemplary embodiment of the present invention, where the network load status detection method may be applied to a cloud server (for example, a computer device) in networking, and as shown in fig. 2A, the network load status detection method includes the following steps:
step 201: and acquiring the AP load quantity on each AC in the network.
For example, the AC in the network may actively report the current AP load to the cloud server, or the cloud server may obtain the AP load on each AC in a periodic monitoring manner.
Step 202: and acquiring the load upper limit of each AC, and taking the ratio of the AP load amount of the AC to the load upper limit as the load proportion of the AC.
In the invention, the load capacity difference of the AC of different models is considered, and when the load balance state is evaluated, the load balance index is evaluated by using the load proportion of the AC as a calculation parameter instead of the AP load amount, so as to eliminate the interference caused by heterogeneous factors in the network.
For example, the upper limit of the load of AC1 is 2K, the upper limit of the load of AC2 is 1K, if the load amount of AC1 is 900, the load ratio of AC1 is 9/20, and if the load amount of AC2 is 500, the load ratio of AC2 is 1/2.
In one embodiment, the timing to trigger execution of steps 202-204 may include external stimulus for exceptions (e.g., stimulus for batch AP offline, new AC access, batch AP migration while AC offline, etc.), periodic polling, user trigger, etc.
Step 203: and determining a load balancing index of the network based on the load proportion of each AC.
The load balance index may be evaluated by using a kini coefficient of a lorentz curve as an evaluation index, or by using a pareto index in a pareto distribution as an evaluation index, or by using a variance of a load ratio (representing a discrete degree of an AP load) as an evaluation index.
The implementation of the above three evaluation modes is described in the following examples, which will not be detailed herein.
Step 204: and determining whether the network load is balanced according to the load balancing index.
In an embodiment, based on the description in step 203, when the load balancing indicator is a kini coefficient, if the kini coefficient is greater than a first threshold, it is determined that the network load status is unbalanced, and if the kini coefficient is less than or equal to the first threshold, it is determined that the network load status is balanced; when the load balancing index is a pareto index, if the pareto index is larger than a second threshold, determining that the network load state is unbalanced, and if the pareto index is smaller than or equal to the second threshold, determining that the network load state is balanced; when the load balancing index is the variance of the load proportion of each AC, if the variance is larger than a third threshold value, determining that the network load state is unbalanced; and if the variance is less than or equal to a third threshold value, determining that the network load state is balanced.
The value range of the kini coefficient is between 0 and 1, when the kini coefficient is 0, the network load is absolutely balanced, when the kini coefficient is 1, the network load is very unbalanced, the kini coefficient 0.4 is used as a warning line of income distribution gap in the field of economics, and the first threshold value can be set to be 0.4.
The twenty-eight rule, which is the most used for the pareto distribution in the field of economics, means that 20% of people take 80% of income, and therefore the second threshold value can be set to 0.8.
For the load dispersion degree represented by the variance, since the variance is only a number greater than or equal to 0, and when the variance is 0, the network load is absolutely balanced, so that the third threshold value can be set according to actual requirements to determine whether the load balancing state is within a reasonable acceptable range.
Thus, the evaluation process shown in fig. 2A is completed, and the load balancing degree of the network can be effectively measured through the process shown in fig. 2A, so as to provide a quantifiable basis for further executing the load adjustment policy.
As shown in fig. 2B, a lorentz curve is used to reflect the lean-rich gap of a country for the field of economics, and the kuni coefficient is used as an index for determining the distribution equality degree, and the calculation principle of the index is as follows:
assuming that the area between the actual revenue distribution curve (i.e., the lorentz curve) and the absolute equal line of revenue distribution is a, and the area under the actual revenue distribution curve is B, the quotient of a divided by (a + B) represents the kini coefficient, if a is zero, the kini coefficient is zero, indicating that the revenue distribution is completely equal, and if B is zero, the kini coefficient is 1, indicating that the revenue distribution is absolutely unequal.
Based on the theory, the load proportion of each AC replaces the income of the population to fit a Lorentz curve by replacing the number of the AC with the number of the population, the load proportion of each AC is used for reflecting the load balance state of the network, and the Gini coefficient is used as a measurement index.
The following describes a process for implementing load balancing index estimation using the damping coefficient of the lorentz curve:
that is, the step 203 specifically includes the following steps 301 to 304:
step 301: the various ACs are sorted in order of the load proportion from small to large.
Step 302: and traversing each AC in sequence from the first AC in the sequence, and determining the load accumulation ratio of the currently traversed AC by using the load proportion of the traversed AC and the load proportion of the currently traversed AC aiming at the currently traversed AC.
In an embodiment, the sum of the load proportion of the traversed AC and the load proportion of the currently traversed AC may be used as the load cumulative value of the currently traversed AC, and the ratio between the load cumulative value of the currently traversed AC and the total load cumulative value, which is the sum of the load proportions of the respective ACs, is determined as the load cumulative ratio of the currently traversed AC.
Step 304: and acquiring the total number of the ACs in the sequence, calculating a Kernel coefficient according to the load accumulation ratio of each AC and the total number of the ACs, and determining the Kernel coefficient as a load balancing index of the network.
The derivation procedure for calculating the kini coefficients is as follows:
the horizontal axis of the lorentz curve shown in fig. 2B is the cumulative population percentage, which is calculated as the cumulative percentage of the population in each region in the order of the smallest number to the largest number. In the invention, the cumulative percentage of the load proportion of each AC should be calculated from small to large, so that the AC needs to be sorted in the order of the load proportion from small to large, and then the sorting result is traversed in sequence to calculate the abscissa and ordinate of the corresponding node of each AC.
And the AC accumulated quantity is expressed by the traversal times so as to be used for calculating the abscissa value of the corresponding node.
Assuming that the total number of the ACs is n, when the first AC in the sequence is traversed, the current traversal number is 1, when the second AC in the sequence is traversed, the current traversal number is 2, and so on, when the nth AC in the sequence is traversed, the current traversal number is n.
From this, the abscissa (i.e., the cumulative AC number ratio) of the n AC-corresponding nodes in the rank is sequentially X1-1/n, and X2-2/n … … Xn-1.
Assuming that, when traversing the first AC in the ranking, the sum of the load proportions of the traversed AC and the load proportions of the currently traversed AC, S1, is 0+ R1, and when traversing the second AC in the ranking, the sum of the load proportions of the traversed AC and the load proportions of the currently traversed AC, S2, is R1+ R2, and so on, when traversing the nth AC in the ranking, the sum of the load proportions of the traversed AC and the load proportions of the currently traversed AC, Sn, is R1+ R2 … … + Rn.
From S1 to Sn and the total load integrated value Sn obtained as described above, the ordinate (i.e., the load integrated ratio) of the n AC-corresponding nodes in the sequence is, in order, Y1 — S1/Sn, and Y2 — S2/Sn … … Yn 1.
Based on the coordinates of the n AC-corresponding nodes obtained as described above, the coordinates are sequentially (X1, Y1), (X2, Y2) … … (Xn, Yn), and nodes of which X0 is 0 and Y0 is 0 are supplemented, and a lorentz curve is fitted using these nodes as an AP load balancing state fitting curve.
A lorentz curve fitted as shown in fig. 2C, where the horizontal axis represents the AC quantity cumulative ratio, the vertical axis represents the AC load cumulative ratio, and the kini coefficient formula is G ═ a/(a + B), a grouping concept in geometry can be adopted:
a) since the number of nodes used in the fitting is n +1, the area B of the region below the lorentz curve can be divided into n trapezoids according to the number of nodes n +1, the area Si of each trapezoid is (Yi-1+ Yi) × 1/n × 1/2, i is an integer from 1 to n;
b) the area B is the sum of the areas of n trapezoids, i.e.
c) A + B represents the area of the triangle below the absolute equator, i.e., (a + B) ═ Xn × Yn × 1/2 ═ 1/2;
d) coefficient of kini
Based on the derivation process of the kini coefficient, the kini coefficient can be obtained according to the load cumulative ratio of each AC and the total number n of the AC.
It will be appreciated by those skilled in the art that the foregoing kini coefficients are derived based on a normalization process. Whereas the derivation principle regarding the kini coefficient is consistent with the above-described derivation principle if the horizontal axis and/or the vertical axis are not subjected to the normalization process.
And finishing the process of evaluating the load balancing index by adopting the Gini coefficient of the Lorentz curve.
The following describes the implementation of the load balancing index evaluation using the pareto index:
the pareto index is a parameter of the pareto distribution, and is also a measure of the imbalance of the income distribution, reflected in the field of economics. The invention can also evaluate the load balancing index of the network by replacing the number of the AC with the number of the population and replacing the load proportion of each AC with the income of the population.
That is, the step 203 specifically includes the following steps 401 to 402:
step 401: and sequencing all the ACs according to the sequence of the load proportion from large to small, and obtaining the preset number of the ACs from the first AC in the sequencing.
The preset number may be set according to the total number of ACs in the network, for example, in the rule of two eight, the total number of ACs is 100, and the preset number is set to 20% of the total number of ACs, that is, 20%.
Step 402: and determining a pareto index by using the sum of the load proportions of the preset number of ACs and the total load accumulated value, and determining the pareto index as a load balancing index of the network.
Wherein the total load integrated value is the sum of the load proportions of the ACs.
For example, the ratio between the sum of the load ratios of the preset number of ACs and the total load cumulative value may be used as the pareto index.
For the processes of step 401 and step 402, a load balancing index is evaluated by taking a ratio of a sum of load proportions of a preset number of ACs before ranking to a total load cumulative value as a pareto index.
And finishing the process of evaluating the load balancing index by adopting the pareto index.
The following describes an implementation process for evaluating a load balancing index by using variance:
that is, the step 203 specifically includes the following steps 501:
the variance of the load proportions of each AC is determined and the variance is determined as a load balancing indicator for the network.
The variance of the load proportion can evaluate the discrete degree of the AP load, and the AP load balancing state can be reflected to a certain degree.
Fig. 3 is a hardware structure diagram of a cloud server according to an exemplary embodiment of the present invention, where the cloud server includes: a communication interface 301, a processor 302, a machine-readable storage medium 303, and a bus 304; wherein the communication interface 301, the processor 302, and the machine-readable storage medium 303 communicate with each other via a bus 304. The processor 302 may execute the network load status detection method described above by reading and executing machine executable instructions in the machine readable storage medium 303 corresponding to the control logic of the network load status detection method, and the details of the method are described in the above embodiments and will not be described herein again.
The machine-readable storage medium 303 referred to in this disclosure may be any electronic, magnetic, optical, or other physical storage device that can contain or store information such as executable instructions, data, and the like. For example, the machine-readable storage medium may be: volatile memory, non-volatile memory, or similar storage media. In particular, the machine-readable storage medium 303 may be a RAM (random Access Memory), a flash Memory, a storage drive (e.g., a hard drive), any type of storage disk (e.g., an optical disk, a DVD, etc.), or similar storage medium, or a combination thereof.
Corresponding to the embodiment of the network load state detection method, the invention also provides an embodiment of a network load state detection device.
Fig. 4 is a flowchart illustrating an embodiment of a network load status detection apparatus according to an exemplary embodiment of the present invention, where the network load status detection apparatus may be applied to a cloud server in networking, as shown in fig. 4, the network load status detection apparatus includes:
an obtaining module 410, configured to obtain an AP load amount on each AC in a network, obtain, for each AC, a load upper limit of the AC, and use a ratio between the AP load amount of the AC and the load upper limit as a load proportion of the AC;
a determining module 420, configured to determine a load balancing indicator of the network based on a load ratio of each AC;
the detecting module 430 is configured to determine whether the network load is balanced according to the load balancing indicator.
In an optional implementation manner, the determining module 420 is specifically configured to: sequencing the ACs according to the sequence of the load proportion from small to large; sequentially traversing each AC from the first AC in the sequence, and determining the load accumulation ratio of the currently traversed AC by using the load proportion of the traversed AC and the load proportion of the currently traversed AC aiming at the currently traversed AC; and acquiring the total number of the AC in the sequence, calculating a kini coefficient according to the load accumulation ratio of each AC and the total number of the AC, and determining the kini coefficient as a load balance index of the network.
In an optional implementation manner, the determining module 420 is specifically configured to: in the process of determining the load cumulative ratio of the currently traversed AC by using the load proportion of the traversed AC and the load proportion of the currently traversed AC, taking the sum of the load proportion of the traversed AC and the load proportion of the currently traversed AC as the load cumulative value of the currently traversed AC; and determining the ratio of the load cumulative value of the current traversal AC to the total load cumulative value as the load cumulative ratio of the current traversal AC, wherein the total load cumulative value is the sum of the load proportions of all the ACs.
In an optional implementation manner, the detection module 430 is specifically configured to: if the kini coefficient is smaller than or equal to a first threshold value, determining that the network load state is balanced; and if the Gini coefficient is larger than a first threshold value, determining that the network load state is unbalanced.
In an optional implementation manner, the determining module 420 is specifically configured to: sequencing all the ACs according to the sequence of the load proportion from large to small, and obtaining a preset number of ACs from the first AC in the sequencing; determining a pareto index by using the sum of the load proportions of the preset number of ACs and the total load accumulated value, and determining the pareto index as a load balancing index of the network; wherein the total load cumulative value is the sum of the load proportions of the ACs;
the detection module 430 is specifically configured to: if the pareto index is smaller than or equal to a second threshold value, determining that the network load state is balanced; and if the pareto index is larger than a second threshold value, determining that the network load state is unbalanced.
In an optional implementation manner, the determining module 420 is specifically configured to: determining the variance of the load proportion of each AC, and determining the variance as a load balancing index of the network;
the detection module 430 is specifically configured to: if the variance is smaller than or equal to a third threshold value, determining that the network load state is balanced; and if the variance is larger than a third threshold value, determining that the network load state is unbalanced.
The specific details of the implementation process of the functions and actions of each unit in the above device are the implementation processes of the corresponding steps in the above method, and are not described herein again.
For the device embodiment, since it basically corresponds to the method embodiment, reference may be made to the partial description of the method embodiment for relevant points. The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of the invention. One of ordinary skill in the art can understand and implement it without inventive effort.
Other embodiments of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. The invention is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the invention and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the invention being indicated by the following claims.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (9)
1. A method for detecting a network load status, the method comprising:
acquiring the load capacity of an Access Point (AP) on each wireless controller (AC) in a network;
for each AC, acquiring the load upper limit of the AC, and taking the ratio of the AP load capacity of the AC to the load upper limit as the load proportion of the AC;
determining a load balancing index of the network based on the load proportion of each AC;
determining whether the network load is balanced according to the load balancing index;
wherein, the determining the load balance index of the network based on the load proportion of each AC comprises:
sequencing the ACs according to the sequence of the load proportion from small to large;
sequentially traversing each AC from the first AC in the sequence, and determining the load accumulation ratio of the currently traversed AC by using the load proportion of the traversed AC and the load proportion of the currently traversed AC aiming at the currently traversed AC;
and acquiring the total number of the AC in the sequence, calculating a kini coefficient according to the load accumulation ratio of each AC and the total number of the AC, and determining the kini coefficient as a load balance index of the network.
2. The method of claim 1, wherein determining the load cumulative ratio for the currently traversed AC using the load proportions of the traversed AC and the load proportions of the currently traversed AC comprises:
taking the sum of the load proportion of the traversed AC and the load proportion of the current traversed AC as a load accumulated value of the current traversed AC;
and determining the ratio of the load cumulative value of the current traversal AC to the total load cumulative value as the load cumulative ratio of the current traversal AC, wherein the total load cumulative value is the sum of the load proportions of all the ACs.
3. The method of claim 1 or 2, wherein determining whether the network load is balanced according to the load balancing index comprises:
if the kini coefficient is smaller than or equal to a first threshold value, determining that the network load state is balanced;
and if the kini coefficient is larger than a first threshold value, determining that the network load state is unbalanced.
4. The method of claim 1, wherein determining the load balancing metric for the network based on the load ratios of the respective ACs comprises:
sequencing all the ACs according to the sequence of the load proportion from large to small, and obtaining a preset number of ACs from the first AC in the sequencing; determining a pareto index by using the sum of the load proportions of the preset number of ACs and a total load accumulated value, and determining the pareto index as a load balancing index of the network, wherein the total load accumulated value is the sum of the load proportions of the ACs;
the determining whether the network load is balanced according to the load balancing index includes:
if the pareto index is smaller than or equal to a second threshold, determining that the network load state is balanced; and if the pareto index is larger than a second threshold value, determining that the network load state is unbalanced.
5. The method of claim 1, wherein determining the load balancing metric for the network based on the load ratios of the respective ACs comprises:
determining the variance of the load proportion of each AC, and determining the variance as a load balancing index of the network;
the determining whether the network load is balanced according to the load balancing index includes:
if the variance is less than or equal to a third threshold value, determining that the network load state is balanced; and if the variance is larger than a third threshold value, determining that the network load state is unbalanced.
6. A network load status detection apparatus, the apparatus comprising:
the acquisition module is used for acquiring AP (access point) load capacity of each AC (access point) on each wireless controller in the network, acquiring the load upper limit of each AC, and taking the ratio of the AP load capacity of the AC to the load upper limit as the load proportion of the AC;
the determining module is used for determining a load balancing index of the network based on the load proportion of each AC;
the detection module is used for determining whether the network load is balanced according to the load balancing index;
wherein the determining module is specifically configured to: sequencing the ACs according to the sequence of the load proportion from small to large; sequentially traversing each AC from the first AC in the sequence, and determining the load accumulation ratio of the currently traversed AC according to the load proportion of the traversed AC and the load proportion of the currently traversed AC aiming at the currently traversed AC; and acquiring the total number of the ACs in the sequence, calculating a Kernel coefficient according to the load accumulation ratio of each AC and the total number of the ACs, and determining the Kernel coefficient as a load balancing index of the network.
7. The apparatus of claim 6, wherein the detection module is specifically configured to: if the Gini coefficient is less than or equal to a first threshold value, determining that the network load state is balanced; and if the Gini coefficient is larger than a first threshold value, determining that the network load state is unbalanced.
8. The apparatus of claim 6, wherein the determining module is specifically configured to: sequencing all the ACs according to the sequence of the load proportion from large to small, and obtaining a preset number of ACs from the first AC in the sequencing; determining a pareto index by using the sum of the load proportions of the preset number of ACs and the total load accumulated value, and determining the pareto index as a load balancing index of the network; wherein the total load cumulative value is the sum of the load proportions of the ACs;
the detection module is specifically configured to: if the pareto index is smaller than or equal to a second threshold, determining that the network load state is balanced; and if the pareto index is larger than a second threshold value, determining that the network load state is unbalanced.
9. The apparatus of claim 6, wherein the determining module is specifically configured to: determining the variance of the load proportion of each AC, and determining the variance as a load balancing index of the network;
the detection module is specifically configured to: if the variance is smaller than or equal to a third threshold value, determining that the network load state is balanced; and if the variance is larger than a third threshold value, determining that the network load state is unbalanced.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911288966.9A CN110933701B (en) | 2019-12-12 | 2019-12-12 | Network load state detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911288966.9A CN110933701B (en) | 2019-12-12 | 2019-12-12 | Network load state detection method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110933701A CN110933701A (en) | 2020-03-27 |
| CN110933701B true CN110933701B (en) | 2022-07-26 |
Family
ID=69863658
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911288966.9A Active CN110933701B (en) | 2019-12-12 | 2019-12-12 | Network load state detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110933701B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115190075A (en) * | 2021-04-07 | 2022-10-14 | 中国移动通信集团设计院有限公司 | Network element load balancing method, device, equipment and storage medium |
| CN114531333B (en) * | 2022-01-28 | 2023-09-15 | 新华三技术有限公司 | Method for managing operation and maintenance data, cloud platform and AC |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101986608A (en) * | 2010-12-13 | 2011-03-16 | 武汉大学 | Method for evaluating heterogeneous overlay network load balance degree |
| CN105764094A (en) * | 2016-02-04 | 2016-07-13 | 杭州华三通信技术有限公司 | Hybrid load balancing method and device |
| WO2017016499A1 (en) * | 2015-07-29 | 2017-02-02 | 腾讯科技（深圳）有限公司 | Method and device for leveling load of distributed database |
| CN108055677A (en) * | 2018-02-09 | 2018-05-18 | 重庆邮电大学 | Load-balancing method based on software definition wireless network |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102869047A (en) * | 2012-06-27 | 2013-01-09 | 中兴通讯股份有限公司 | Method and device for realizing load balance |
| CN104811396A (en) * | 2014-01-23 | 2015-07-29 | 中兴通讯股份有限公司 | Load balance (LB) method and system |
| CN108009016B (en) * | 2016-10-31 | 2021-10-22 | 华为技术有限公司 | Resource load balancing control method and cluster scheduler |
-
2019
- 2019-12-12 CN CN201911288966.9A patent/CN110933701B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101986608A (en) * | 2010-12-13 | 2011-03-16 | 武汉大学 | Method for evaluating heterogeneous overlay network load balance degree |
| WO2017016499A1 (en) * | 2015-07-29 | 2017-02-02 | 腾讯科技（深圳）有限公司 | Method and device for leveling load of distributed database |
| CN105764094A (en) * | 2016-02-04 | 2016-07-13 | 杭州华三通信技术有限公司 | Hybrid load balancing method and device |
| CN108055677A (en) * | 2018-02-09 | 2018-05-18 | 重庆邮电大学 | Load-balancing method based on software definition wireless network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110933701A (en) | 2020-03-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108009016B (en) | Resource load balancing control method and cluster scheduler | |
| EP3847549B1 (en) | Minimizing impact of migrating virtual services | |
| US8533719B2 (en) | Cache-aware thread scheduling in multi-threaded systems | |
| CN110221915B (en) | Node scheduling method and device | |
| CN103294546B (en) | The online moving method of virtual machine of multi-dimensional resource performance interference aware and system | |
| CN110933701B (en) | Network load state detection method and device | |
| WO2014198001A1 (en) | System and method for determining capacity in computer environments using demand profiles | |
| CN109634744A (en) | A kind of fine matching method based on cloud platform resource allocation, equipment and storage medium | |
| US12093530B2 (en) | Workload management using a trained model | |
| CN112418341A (en) | Model fusion method, prediction method, device, equipment and storage medium | |
| CN115525394A (en) | Method and device for adjusting number of containers | |
| CN117519946A (en) | Memory resource scheduling method, device, equipment and medium in deep learning network | |
| CN116560794A (en) | Exception handling method and device for virtual machine, medium and computer equipment | |
| CN116048773B (en) | Distributed collaborative task assignment method and system based on wave function collapse | |
| CN111783883A (en) | Abnormal data detection method and device | |
| CN116302327A (en) | Resource scheduling method and related equipment | |
| US20200074012A1 (en) | Affinity determination using graphs | |
| Prado et al. | On providing quality of service in grid computing through multi-objective swarm-based knowledge acquisition in fuzzy schedulers | |
| KR20160044623A (en) | Load Balancing Method for a Linux Virtual Server | |
| CN110457280A (en) | A kind of HDFS copy replicates improvement strategy again | |
| CN111277665B (en) | 3D application scheduling method, device, terminal and storage medium based on interference measurement | |
| CN110278125B (en) | Cloud computing resource elasticity evaluation method | |
| CN114448839B (en) | Self-adaptive distributed system pressure measurement method, device and system | |
| CN112416774B (en) | Software reliability testing method with added weight | |
| CN115237610B (en) | Elastic expansion method and device based on Kubernetes container cloud platform and application |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |