Excess load estimation method, device, equipment and storage medium in distributed system

Abstract

The embodiment of the present invention discloses a method, device, equipment and storage medium for estimating excess load in a distributed system. The method includes: obtaining shape parameters and inverse scale parameters of the distributed system at the current collection time, wherein the inverse scale parameters are determined according to the frequency of excess load in the system operation history data; determining the excess load probability based on the shape parameters and inverse scale parameters combined with a predetermined load estimation model. The problem of being unable to accurately estimate the excess load situation in the system is solved. A load estimation model is pre-constructed, and the probability of excess load of the distributed system is estimated through the load estimation model. The shape parameters and inverse scale parameters of the current collection time are obtained, and the probability of excess load of the distributed system at the current collection time is determined according to the shape parameters and inverse scale parameters combined with the load estimation model, and the excess load in the system is accurately estimated, thereby improving the accuracy of the excess load probability estimation.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of distributed technology, and in particular to an excess load estimation method, apparatus, device and storage medium in a distributed system. Background Art

[0002] Microservice distributed system is a common architecture used by modern computers for large-scale application development. Each microservice in a distributed system is called a node. Each node handles different businesses. The same microservice may have one or more nodes as the medium of its service. Each node in the system will handle various requests. Each node has limited resources, so its ability to handle requests is limited. If a node has too many instantaneous requests, it will be overloaded. This will make the response time of a service lengthy, affecting the user experience and even the system security, resulting in economic losses. Therefore, accurate prediction of overload becomes very important. Summary of the invention

[0003] The present invention provides a method, device, equipment and storage medium for estimating excess load in a distributed system, so as to realize accurate estimation of excess load in the distributed system.

[0004] In a first aspect, an embodiment of the present invention provides a method for estimating excess load in a distributed system, the method for estimating excess load in a distributed system comprising:

[0005] Obtaining shape parameters and inverse scale parameters of the distributed system at the current acquisition time, wherein the inverse scale parameters are determined according to the frequency of excess load in the system operation history data;

[0006] An excess load probability is determined based on the shape parameter and the inverse scale parameter in combination with a predetermined load estimation model.

[0007] Further, the determining the excess load probability based on the shape parameter and the inverse scale parameter in combination with a predetermined load estimation model includes:

[0008] Determining a density distribution parameter according to the shape parameter and the inverse scale parameter;

[0009] The excess load probability is determined according to the density distribution parameter and the probability calculation formula of the load estimation model.

[0010] Further, determining the density distribution parameter according to the shape parameter and the inverse scale parameter includes:

[0011] Determining a target distribution parameter according to the product of the shape parameter and the inverse scale parameter;

[0012] The density distribution parameter is determined according to the target distribution parameter and a calculation formula of the load estimation model.

[0013] Furthermore, the method further comprises:

[0014] Based on the probability of excess load per unit time of the nodes in the distributed system, an exponential distribution model of the nodes is constructed to determine the exponential model parameters;

[0015] Gamma distribution modeling of node excess load is performed according to the exponential model parameters, system node load relationship and the total number of nodes;

[0016] Poisson distribution modeling of the distributed system is performed according to the actual number of excess loads per unit time of the distributed system and the modeling results of the gamma distribution modeling to obtain a load estimation model.

[0017] Furthermore, the method further comprises:

[0018] comparing the excess load probability with a predetermined probability threshold;

[0019] If the overload probability is greater than the probability threshold, an overload alarm is issued.

[0020] In a second aspect, an embodiment of the present invention further provides an excess load estimation device in a distributed system, wherein the excess load estimation device in the distributed system comprises:

[0021] A parameter acquisition module, used to acquire shape parameters and inverse scale parameters of the distributed system at the current acquisition moment, wherein the inverse scale parameters are determined according to the frequency of excess load in the system operation history data;

[0022] A probability determination module is used to determine the excess load probability based on the shape parameter and the inverse scale parameter in combination with a predetermined load estimation model.

[0023] Furthermore, the probability determination module includes:

[0024] A parameter determination unit, used to determine a density distribution parameter according to the shape parameter and the inverse scale parameter;

[0025] The probability determination unit is used to determine the excess load probability according to the density distribution parameter and the probability calculation formula of the load estimation model.

[0026] Furthermore, the parameter determination unit is specifically used to determine the target distribution parameter according to the product of the shape parameter and the inverse scale parameter; and determine the density distribution parameter according to the target distribution parameter and a calculation formula of the load estimation model.

[0027] Furthermore, the device also includes:

[0028] An exponential modeling module is used to perform exponential distribution modeling of nodes according to the probability of excess load per unit time of nodes in a distributed system and determine exponential model parameters;

[0029] A gamma modeling module, used for performing gamma distribution modeling of node excess load according to the exponential model parameters, system node load relationship and total number of nodes;

[0030] The Poisson modeling module is used to perform Poisson distribution modeling of the distributed system according to the actual number of excess loads per unit time of the distributed system and the modeling results of the gamma distribution modeling to obtain a load estimation model.

[0031] Furthermore, the device also includes:

[0032] a threshold comparison module, configured to compare the excess load probability with a predetermined probability threshold;

[0033] The alarm module is used to issue an overload alarm if the overload probability is greater than the probability threshold.

[0034] In a third aspect, an embodiment of the present invention further provides a computer device, the device comprising:

[0035] one or more processors;

[0036] a memory for storing one or more programs,

[0037] When the one or more programs are executed by the one or more processors, the one or more processors implement a method for estimating excess load in a distributed system as described in any one of the embodiments of the present invention.

[0038] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a method for estimating excess load in a distributed system as described in any one of the embodiments of the present invention.

[0039] The embodiments of the present invention provide a method, apparatus, device and storage medium for estimating excess load in a distributed system, by obtaining shape parameters and inverse scale parameters of the distributed system at the current collection moment, wherein the inverse scale parameters are determined according to the frequency of excess load in the system operation history data; and determining the excess load probability based on the shape parameters and inverse scale parameters combined with a predetermined load estimation model. This solves the problem of being unable to accurately estimate the excess load situation in the system. A load estimation model is pre-constructed, and the probability of excess load of the distributed system is estimated through the load estimation model. The shape parameters and inverse scale parameters of the current collection moment are obtained, and the probability of excess load of the distributed system at the current collection moment is determined based on the shape parameters and inverse scale parameters combined with the load estimation model, so as to accurately estimate the excess load in the system and improve the accuracy of the excess load probability estimation. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 is a flow chart of an excess load estimation method in a distributed system in Embodiment 1 of the present invention;

[0041] Figure 2 is a flow chart of a method for estimating excess load in a distributed system in Embodiment 2 of the present invention;

[0042] Figure 3 This is an example diagram of an implementation of an excess load estimation method in a distributed system in Embodiment 2 of the present invention;

[0043] Figure 4 It is a structural diagram of an excess load estimation device in a distributed system in Embodiment 3 of the present invention;

[0044] Figure 5 It is a structural diagram of a computer device in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solutions and advantages of the present application clearer, the embodiments of the present application will be further described in detail below in conjunction with the accompanying drawings. It should be clear that the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0046] When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Instead, they are only examples of devices and methods consistent with some aspects of the present application as detailed in the attached claims.

[0047] In the description of the present application, it should be understood that the terms "first", "second", "third", etc. are only used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence, nor can they be understood as indicating or implying relative importance. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to the specific circumstances. In addition, in the description of the present application, unless otherwise specified, "multiple" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects associated before and after are in an "or" relationship.

[0048] Embodiment 1

[0049] Figure 1 A flow chart of a method for estimating excess load in a distributed system provided in Embodiment 1 of the present application is provided, and the method is applicable to the case of accurately estimating excess load in a distributed system. The method can be executed by a computer device, and the computer device can be composed of two or more physical entities, or can be composed of one physical entity. Generally speaking, the computer device can be a notebook, a desktop computer, a smart tablet, etc.

[0050] like Figure 1 As shown, the present embodiment 1 provides a method for estimating excess load in a distributed system, which specifically includes the following steps:

[0051] S110: Obtain shape parameters and inverse scale parameters of the distributed system at the current collection time, wherein the inverse scale parameter is determined according to the frequency of excess load in historical system operation data.

[0052] It should be noted that the current collection time refers to the time when the load estimation is currently being performed. The method for estimating excess load in a distributed system provided in the embodiment of the present application can estimate the excess load in the distributed system in real time. For example, a collection interval is set, and data is collected regularly according to the collection interval. At each data collection time, parameter collection is performed to achieve an excess load estimation. The method used for any excess load estimation is the same, that is, excess load estimation is performed through S120.

[0053] In this embodiment, the shape parameter can be specifically understood as the parameter required for estimating the excess load of the distributed system; the shape parameter in the embodiment of the present application is usually selected as any real number greater than 0, and can be set to a fixed value, that is, the value of the shape parameter obtained each time is the same, or a value can be randomly selected each time the shape parameter is obtained, for example, by a random number generation function. The inverse scale parameter can be specifically understood as a parameter for estimating the excess load, which is related to the probability of the excess load occurring. The system operation history data can be specifically understood as the historical data generated during the operation of the distributed system, for example, whether an excess load occurs, the time when the excess load occurs, the cutoff time, and so on.

[0054] Specifically, the shape parameter and the inverse scale parameter can be determined before acquisition. If the shape parameter is a fixed value, the shape parameter can be selected in advance, and the set shape parameter can be directly obtained when the excess load estimation is performed later. The inverse scale parameter can be determined based on the historical data of the distributed system, and the inverse scale parameter can also be updated once every period of time through the historical data, for example, 1 day, a week, etc.; or, each time the excess load estimation is performed, the inverse scale parameter is determined in real time based on the historical data before the current acquisition time.

[0055] The method for determining the inverse scale parameter can be: obtaining the system operation history data, counting the time when the excess load occurs in each node per unit time, obtaining the time value by calculating the time mean, median, maximum value, minimum value, weighted average, etc., and taking the reciprocal of this time value as the frequency of the excess load, and taking the frequency as the inverse scale parameter.

[0056] It should be noted that when determining the inverse scale parameter at the current collection time, the inverse scale parameter may be determined at regular intervals, for example, once a day. Excess loads may be determined multiple times in a day, so the inverse scale parameter used each time the excess load is determined in a day is the same. Alternatively, the inverse scale parameter may be determined each time the excess load is determined, and the inverse scale parameter is determined based on the frequency of excess loads in the system operation history data before the current collection time.

[0057] S120: Determine an excess load probability based on the shape parameter and the inverse scale parameter in combination with a predetermined load estimation model.

[0058] In this embodiment, the load estimation model can be specifically understood as a mathematical statistical model for overload estimation; the overload probability can be specifically understood as the probability of overload when a node in the system processes a request. The load estimation model in the embodiment of the present application is formed by Bayesian statistical modeling.

[0059] Specifically, the shape parameter and the inverse scale parameter are used as parameters of the load estimation model, and the excess load probability is obtained by performing calculation and prediction through the calculation formula of the load estimation model.

[0060] An embodiment of the present invention provides a method for estimating excess load in a distributed system, by obtaining shape parameters and inverse scale parameters of the distributed system at the current collection moment, wherein the inverse scale parameters are determined according to the frequency of excess load in the system operation history data; and determining the excess load probability based on the shape parameters and inverse scale parameters combined with a predetermined load estimation model. This solves the problem of being unable to accurately estimate the excess load situation in the system. A load estimation model is pre-constructed, and the probability of excess load of the distributed system is estimated through the load estimation model. The shape parameters and inverse scale parameters of the current collection moment are obtained, and the probability of excess load of the distributed system at the current collection moment is determined based on the shape parameters and inverse scale parameters combined with the load estimation model, so as to accurately estimate the excess load in the system and improve the accuracy of the estimation of the excess load probability.

[0061] Embodiment 2

[0062] Figure 2 A flowchart of a method for estimating excess load in a distributed system provided in Embodiment 2 of the present invention. The technical solution of this embodiment is further refined on the basis of the above technical solution, and specifically mainly includes the following steps:

[0063] S210 , performing exponential distribution modeling of nodes according to the unit time excess load probability of nodes in the distributed system, and determining exponential model parameters.

[0064] In this embodiment, the overload probability per unit time may be specifically understood as the probability of an overload situation occurring at each node per unit time.

[0065] Specifically, the system usually contains multiple nodes, X i Indicates that the i-node is overloaded; τ i is the probability of excess load on node i per unit time, i.e., the excess load probability per unit time. i We can use a parameter τ i The exponential distribution model of X i |τ i ~Exp(τ i ), the density function is (Formula 1). Parameter τ i are exponential model parameters.

[0066] S220, performing gamma distribution modeling of node excess load according to exponential model parameters, system node load relationship and the total number of nodes.

[0067] In this embodiment, the total number of nodes refers to the total number of service nodes that process requests in the distributed system. The system node load relationship is the situation where there is an overload in the system, that is, when any node in the system is overloaded, (Formula 2) indicates that n is the total number of nodes. For example, the case where n nodes are overloaded independently of each other is taken as an example.

[0068] Due to X i |τ i ~Exp(τ i ), assuming that all nodes are equally overloaded independently, i.e., τ i =τ. According to the knowledge of statistical distribution, the prior distribution model can be obtained by combining Formula 1 and Formula 2, that is, the result of gamma distribution modeling: Y|τ~Gamma(n,τ), where n is the total number of nodes and τ can be estimated based on experience or historical data, so in the system model, τ is a known number.

[0069] S230 , performing Poisson distribution modeling of the distributed system according to the actual number of excess loads per unit time of the distributed system and the modeling result of the gamma distribution modeling, to obtain a load estimation model.

[0070] Specifically, before building the load estimation model, the actual number of excess loads k that occur per unit time in the distributed system is determined in advance based on the historical data of system operation. The actual number of excess loads per unit time can also be counted multiple times, and the actual number of excess loads k per unit time of the distributed system can be determined by calculating the average value.

[0071] Y is the situation where excess load occurs in the system; λ is the expected number of times the system will experience excess load per unit time; Y is modeled using a Poisson distribution with a parameter of λ, i.e., Y|λ~Poisson(λ);

[0072] The density function is (Formula 3)

[0073] Since Y|λ~Poisson(λ), assume that λ|Y obeys the conjugate distribution of Poisson distribution, that is, λ|Y∝Gamma(α,β), where any real number greater than 0 can be randomly selected from α and β. Since β involves frequency, τ can be used as an estimate, that is, β=τ. The likelihood function can be obtained by formula 3: λ|Y∝Gamma(α,τ). According to Posson(2τλ)∝Gamma(n,τ)*gamma(α,τ), the final load estimation model Y|λ∝Poisson(2τλ) is obtained.

[0074] It should be noted that after the load estimation model is constructed through S210-S230, when performing subsequent excess load probability estimation, since the excess load probability is repeated, only the constructed load estimation model needs to be used at this time, and there is no need to repeatedly execute S210-S230 to construct the load estimation model.

[0075] S240: Obtain shape parameters and inverse scale parameters of the distributed system at the current collection time, wherein the inverse scale parameter is determined according to the frequency of excess load in the system operation history data.

[0076] S250: Determine a density distribution parameter according to the shape parameter and the inverse scale parameter.

[0077] In this embodiment, the density distribution parameter can be specifically understood as the number of occurrences of excess load in the system. The density distribution parameter in the embodiment of the present application is used as the parameter λ in the Poisson distribution for probability calculation. The density distribution parameter is obtained by calculating the mathematical meaning represented by the shape parameter and the inverse scale parameter in combination with the calculation formula of the load estimation model.

[0078] As an optional embodiment of this embodiment, this optional embodiment further optimizes the density distribution parameter determined according to the shape parameter and the inverse scale parameter as follows:

[0079] A1. Determine the target distribution parameter according to the product of the shape parameter and the inverse scale parameter.

[0080] In this embodiment, the target distribution parameter can be specifically understood as the parameter used in the model calculation when the excess load is estimated through the model. The mean ατ of the model likelihood function Gamma(α,τ) is calculated, and the shape parameter is taken as α and the inverse scale parameter is taken as τ, and they are multiplied, and the product is taken as the target distribution parameter.

[0081] A2. Determine density distribution parameters according to the target distribution parameters and a calculation formula of a load estimation model.

[0082] The calculation formula of the load estimation model in the embodiment of the present application refers to 2τλ in Poisson(2τλ), that is, the inverse scale parameter is multiplied by the target distribution parameter, and then multiplied by a multiple of 2 to obtain the density distribution parameter.

[0083] S260: Determine the excess load probability according to the density distribution parameter and the probability calculation formula of the load estimation model.

[0084] The probability calculation formula of the load estimation model in the embodiment of the present application is Formula 3: Where k is the actual number of overloads per unit time of the distributed system. The density distribution parameter is substituted into Formula 3 as λ in Formula 3 to calculate the overload probability.

[0085] S270: Compare the excess load probability with a predetermined probability threshold.

[0086] In this embodiment, the probability threshold can be specifically understood as a pre-set boundary value for determining whether the probability of overload meets the requirements. The probability threshold is the maximum probability of overload that the system can tolerate. The probability threshold can also be adjusted in real time according to the actual operation of the system.

[0087] Specifically, a probability threshold is set in advance according to the specific service tolerance and the actual overload impact, and can be set to 80% by way of example. After determining the overload probability, the overload probability is compared with the probability threshold.

[0088] S280: If the overload probability is greater than the probability threshold, an overload alarm is issued.

[0089] If the overload probability is greater than the probability threshold, it means that the system load is already overloaded, and an overload alarm is issued to the staff. The overload alarm can be a voice prompt (e.g., continuously playing an alarm, playing an alarm at a set time, playing a voice message saying "system load is overloaded"), an email prompt, or a flashing light. If the overload probability is less than the probability threshold, wait for the next collection moment and continue to monitor the system's overload probability.

[0090] For example, Figure 3 An example diagram of an implementation of an excess load estimation method in a distributed system provided in an embodiment of the present invention.

[0091] S31. Obtain system operation history data.

[0092] S32. Determine an inverse scale parameter τ according to the probability of excess load in the historical data of system operation.

[0093] S33. Randomly select a real number greater than 0 as the shape parameter α at the current acquisition moment.

[0094] It should be noted that S1-S2 and S3 are parallel steps and have no order of execution, and the inverse scale parameter τ can be determined in real time or kept unchanged for a period of time after being determined and used directly. Figure 3 Take the example of a period of time after determination.

[0095] S34. Determine the statistical distribution Gamma(α, τ) according to the pre-constructed load estimation model in combination with the inverse scale parameter τ and the shape parameter α.

[0096] S35. Use the mean value of Gamma(α, τ) to estimate the target distribution parameter ατ.

[0097] S36. Construct the distribution Poisson(2τ(ατ)).

[0098] S37. Calculate the probability of Y=1 according to the density function, that is, the excess load probability p.

[0099] That is, 2τ*ατ is substituted into p is calculated in , where k is the actual number of excess loads per unit time of the distributed system, which is a known value.

[0100] S38. Determine whether p is greater than q (probability threshold). If so, execute S39; otherwise, return to S33.

[0101] S39. Issue an overload alarm.

[0102] Figure 3 The implementation process of the provided method for estimating excess load in a distributed system takes the example of checking the excess load of the system at regular intervals. When the regular check time is reached, the probability p of the excess load of the system is determined. If p is greater than q, an alarm is issued; if p is less than q, the probability p of the excess load of the system is continuously checked. If an alarm is issued, if the system is monitored to be restored to normal after the alarm (repaired by the staff or self-repaired by the system), the execution of S33 is returned; or after the alarm for a period of time, regardless of whether the system is restored to normal, the execution of S33 is returned.

[0103] The embodiment of the present invention provides a method for estimating excess load in a distributed system, by obtaining the shape parameter and inverse scale parameter of the distributed system at the current collection time, wherein the inverse scale parameter is determined according to the frequency of excess load in the system operation history data; and determining the excess load probability based on the shape parameter and the inverse scale parameter combined with a predetermined load estimation model. The problem of being unable to accurately estimate the excess load situation of the system is solved. The load estimation model is constructed using the Bayesian statistical method, and the load excess probability of the distributed system is estimated through the load estimation model. The shape parameter and the inverse scale parameter at the current collection time are obtained, and the shape parameter and the inverse scale parameter are combined with the calculation formula of the load estimation model to calculate and determine the excess load probability of the distributed system at the current collection time, and accurately estimate the excess load in the system, thereby improving the accuracy of the excess load probability estimation, and when the excess load probability is greater than the probability threshold, an excess load alarm is issued, and an excess load alarm is issued in time so that the staff can perform maintenance.

[0104] Embodiment 3

[0105] Figure 4This is a schematic diagram of the structure of an excess load estimation device in a distributed system provided in Embodiment 3 of the present invention. The device includes: a parameter acquisition module 41 and a probability determination module 42.

[0106] The parameter acquisition module 41 is used to acquire the shape parameter and the inverse scale parameter of the distributed system at the current moment, wherein the inverse scale parameter is determined according to the frequency of the excess load in the historical data of the system operation;

[0107] The probability determination module 42 is used to determine the excess load probability based on the shape parameter and the inverse scale parameter in combination with a predetermined load estimation model.

[0108] An embodiment of the present invention provides an excess load estimation device in a distributed system, which obtains shape parameters and inverse scale parameters of the distributed system at the current collection moment; and determines the excess load probability based on the shape parameters and inverse scale parameters combined with a predetermined load estimation model. The problem of being unable to accurately estimate the overload situation in the system is solved. A load estimation model is pre-constructed, and the load estimation model is used to estimate the load excess probability of the distributed system, and the shape parameters and inverse scale parameters of the current collection moment are obtained. The excess load probability of the distributed system at the current collection moment is determined based on the shape parameters and inverse scale parameters combined with the load estimation model, and the excess load in the system is accurately estimated, thereby improving the accuracy of the excess load probability estimation.

[0109] Further, the probability determination module 42 includes:

[0110] A parameter determination unit, used to determine a density distribution parameter according to the shape parameter and the inverse scale parameter;

[0111] The probability determination unit is used to determine the excess load probability according to the density distribution parameter and the probability calculation formula of the load estimation model.

[0112] Furthermore, the parameter determination unit is specifically used to determine the target distribution parameter according to the product of the shape parameter and the inverse scale parameter; and determine the density distribution parameter according to the target distribution parameter and a calculation formula of the load estimation model.

[0113] Furthermore, the device also includes:

[0114] An exponential modeling module is used to perform exponential distribution modeling of nodes according to the unit excess load probability of nodes in the distributed system and determine exponential model parameters;

[0115] A gamma modeling module, used for performing gamma distribution modeling of node excess load according to the exponential model parameters, system node load relationship and total number of nodes;

[0116] The Poisson modeling module is used to perform Poisson distribution modeling of the distributed system according to the actual number of excess loads per unit time of the distributed system and the modeling results of the gamma distribution modeling to obtain a load estimation model.

[0117] Furthermore, the device also includes:

[0118] a threshold comparison module, configured to compare the excess load probability with a predetermined probability threshold;

[0119] The alarm module is used to issue an overload alarm if the overload probability is greater than the probability threshold.

[0120] The excess load estimation device in a distributed system provided by an embodiment of the present invention can execute the excess load estimation method in a distributed system provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0121] Embodiment 4

[0122] Figure 5 A schematic diagram of the structure of a computer device provided in Embodiment 4 of the present invention is shown in FIG. Figure 5 As shown, the device includes a processor 50, a memory 51, an input device 52 and an output device 53; the number of processors 50 in the device can be one or more. Figure 5 A processor 50 is taken as an example; the processor 50, memory 51, input device 52 and output device 53 in the device can be connected by a bus or other means. Figure 5 The example of connecting through bus is taken in the following.

[0123] The memory 51, as a computer-readable storage medium, can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the method for estimating excess load in a distributed system in an embodiment of the present invention (for example, the parameter acquisition module 41 and the probability determination module 42 in the device for estimating excess load in a distributed system). The processor 50 executes various functional applications and data processing of the device by running the software programs, instructions and modules stored in the memory 51, that is, implements the above-mentioned method for estimating excess load in a distributed system.

[0124] The memory 51 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created according to the use of the terminal, etc. In addition, the memory 51 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 51 may further include a memory remotely arranged relative to the processor 50, and these remote memories may be connected to the device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0125] The input device 52 may be used to receive input digital or character information and generate key signal input related to user settings and function control of the device. The output device 53 may include a display device such as a display screen.

[0126] Embodiment 5

[0127] Embodiment 5 of the present invention further provides a storage medium including computer executable instructions, wherein the computer executable instructions are used to execute a method for estimating excess load in a distributed system when executed by a computer processor, the method comprising:

[0128] Obtaining a shape parameter and an inverse scale parameter of the distributed system at a current moment, wherein the inverse scale parameter is determined according to the frequency of excess load in historical operation data of the system;

[0129] An excess load probability is determined based on the shape parameter and the inverse scale parameter in combination with a predetermined load estimation model.

[0130] Of course, the storage medium containing computer executable instructions provided by an embodiment of the present invention, whose computer executable instructions are not limited to the method operations described above, can also execute related operations in the excess load estimation method in a distributed system provided by any embodiment of the present invention.

[0131] Through the above description of the implementation methods, the technicians in the relevant field can clearly understand that the present invention can be implemented by means of software and necessary general hardware, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0132] It is worth noting that in the embodiment of the excess load estimation device in the above-mentioned distributed system, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0133] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for estimating excess load in a distributed system, characterized in that: include: Obtaining shape parameters and inverse scale parameters of the distributed system at the current collection time, wherein the inverse scale parameters are determined according to the frequency of excess load in the system operation history data; determining an excess load probability based on the shape parameter and the inverse scale parameter in combination with a predetermined load estimation model; The determining of the excess load probability based on the shape parameter and the inverse scale parameter in combination with a predetermined load estimation model comprises: Determining a density distribution parameter according to the shape parameter and the inverse scale parameter; Determining the excess load probability according to the density distribution parameter and the probability calculation formula of the load estimation model; The method further comprises: Based on the probability of excess load per unit time of nodes in the distributed system, an exponential distribution model of nodes is constructed to determine the exponential model parameters; Gamma distribution modeling of node excess load is performed according to the exponential model parameters, system node load relationship and the total number of nodes; Poisson distribution modeling of the distributed system is performed according to the actual number of excess loads per unit time of the distributed system and the modeling results of the gamma distribution modeling to obtain a load estimation model.

2. The method according to claim 1, characterized in that The step of determining the density distribution parameter according to the shape parameter and the inverse scale parameter comprises: Determining a target distribution parameter according to the product of the shape parameter and the inverse scale parameter; The density distribution parameter is determined according to the target distribution parameter and a calculation formula of the load estimation model.

3. The method according to any one of claims 1 to 2, characterized in that: Also includes: comparing the excess load probability with a predetermined probability threshold; If the overload probability is greater than the probability threshold, an overload alarm is issued.

4. An excess load estimation device in a distributed system, characterized in that: include: A parameter acquisition module, used to acquire shape parameters and inverse scale parameters of the distributed system at the current acquisition moment, wherein the inverse scale parameters are determined according to the frequency of excess load in the system operation history data; a probability determination module, configured to determine an excess load probability based on the shape parameter and the inverse scale parameter in combination with a predetermined load estimation model; The probability determination module comprises: A parameter determination unit, used to determine a density distribution parameter according to the shape parameter and the inverse scale parameter; A probability determination unit, configured to determine the excess load probability according to the density distribution parameter and the probability calculation formula of the load estimation model; The device also includes: An exponential modeling module is used to perform exponential distribution modeling of nodes according to the probability of excess load per unit time of nodes in a distributed system and determine exponential model parameters; A gamma modeling module, used for performing gamma distribution modeling of node excess load according to the exponential model parameters, system node load relationship and total number of nodes; The Poisson modeling module is used to perform Poisson distribution modeling of the distributed system according to the actual number of excess loads per unit time of the distributed system and the modeling results of the gamma distribution modeling to obtain a load estimation model.

5. A computer device, characterized in that: The device comprises: one or more processors; a memory for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the excess load estimation method in a distributed system as described in any one of claims 1-3.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the excess load estimation method in a distributed system as described in any one of claims 1 to 3 is implemented.

Images