CN112714037A - Method, device and equipment for evaluating guarantee performance of online service quality - Google Patents
Method, device and equipment for evaluating guarantee performance of online service quality Download PDFInfo
- Publication number
- CN112714037A CN112714037A CN202010972667.3A CN202010972667A CN112714037A CN 112714037 A CN112714037 A CN 112714037A CN 202010972667 A CN202010972667 A CN 202010972667A CN 112714037 A CN112714037 A CN 112714037A
- Authority
- CN
- China
- Prior art keywords
- service
- delay
- performance
- load
- bound
- 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.)
- Pending
Links
Images
Classifications
-
- 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
-
- 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
- H04L43/0852—Delays
-
- 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
- H04L43/08—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
- H04L43/0894—Packet rate
Abstract
The invention provides a method, a device and equipment for evaluating guarantee performance of on-line service quality, wherein the method comprises the following steps: analyzing the network performance to obtain the service capability and the load of the system; acquiring the time delay upper bound of the system according to the service capacity and the load; and evaluating the quality of the online service according to the upper time delay bound, wherein the invention aims to provide an evaluation result for the online service with burst traffic so as to optimize the service capability of the system.
Description
Technical Field
The invention relates to the field of network performance evaluation, in particular to a method, a device and equipment for evaluating guarantee performance of online service quality.
Background
In the online network traffic performance analysis-based research, a scholars develops the network performance analysis from the research results in the Web service quality analysis. The method uses Bayesian algorithm to classify Web service quality data and obtain the probability of each classification, determines the possible value range of the missing value by using the classification result, and filters similar neighbors of users and services. According to the characteristics of the cloud service, the network service quality under the cloud service is analyzed by using the relative weights of evaluation indexes such as service performance, reliability, throughput rate, utilization rate and the like of the network service and orienting to a service system architecture. The shijing literature and the like provide a flow real-time prediction framework containing uncertainty estimation aiming at flow scenes of large-scale distributed e-commerce clusters and the requirements of dynamic capacity planning. The framework is based on a multivariable long-short term memory network automatic encoder and a Bayesian theory, and accurate uncertainty interval estimation can be given while flow deterministic prediction is carried out. Iosup and the like design a cloud service performance evaluation model by using a scientific computing method based on Amazon EC2, and the model mainly analyzes the aspects of computing performance, load, energy consumption and the like of a cloud computing platform;
however, in the prior art, the present application is proposed to analyze the quality of service of the online teaching network in case of an emergency and provide a more reliable evaluation result.
Disclosure of Invention
The invention discloses a method, a device and equipment for evaluating guarantee performance of online service quality, and aims to provide an evaluation result for online service with burst flow so as to optimize service capacity of a system.
A first embodiment of the present invention provides a method for evaluating performance of guaranteeing quality of online service, including:
analyzing the network performance to obtain the service capability and the load of the system;
acquiring the time delay upper bound of the system according to the service capacity and the load;
and evaluating the service quality on the line according to the time delay upper bound.
Preferably, the analyzing the network performance comprises: analyzing blocking probability, analyzing immediate service probability, analyzing delay time, analyzing service concurrency capability, and analyzing load.
Preferably, the obtaining of the upper time delay bound of the system according to the service capability and the load includes:
the service capability is betae2eThe load is a (t), the delay upper bound DmaxThe delay upper bound of the system is obtained by the following formula:
equation 2: dmax=sup{inf{τ≥0:α(s)≤βe2e(s+τ)}};
wherein R isn1Is the service rate, R, provided by the forward network servicen2Is the service rate, R, of the backward network service offeringcThe service rate provided by the cloud service, and f is an influence factor of the cloud service on data transmission when processing a computing process.
Preferably, the quality of service on the line is evaluated, specifically:
and operating the formulas 1,2 and 3 to obtain:
wherein R ise2e=min{Rn1,Rc,Rn2/f},Te2e=Tn1+Tc+Tn2;
When the load is alpha (t) ═ M + pt, the upper time delay bound of the system is Dmax=Te2e+M/Re2e=Tc+Te+M/Re2e;
Wherein, Tn=Tn1+Tn2;
Preferably, the method further comprises the following steps: in case of ignoring the signal processing delay, the service delay parameter T is the sum of the link transmission delay and the packet processing delay, i.e. T ═ L/R + L/C, where L denotes the maximum packet length, C denotes the minimum link transmission rate, and R denotes the number of requests of the user.
Wherein, Tn=L(1/Rn1+1/Rn2+2/C);
The upper delay bound of the system is Dmax=Tc+L(1/Rn1+1/Rn2+2/C)+M/Re2e(ii) a Wherein R ise2e=min{Rn1,Rc,Rn2/f}。
A second embodiment of the present invention provides an apparatus for evaluating performance of guaranteeing quality of online service, including:
the network performance analysis module is used for analyzing the network performance and acquiring the service capability and the load of the system;
the time delay upper bound obtaining module is used for obtaining the time delay upper bound of the system according to the service capacity and the load;
and the on-line service quality evaluation module is used for evaluating the on-line service quality according to the time delay upper bound.
Preferably, the delay upper bound obtaining module is specifically configured to:
the service capability is betae2eThe load is a (t), the delay upper bound DmaxThe delay upper bound of the system is obtained by the following formula:
equation 2: dmax=sup{inf{τ≥0:α(s)≤βe2e(s+τ)}};
wherein R isn1Is the service rate, R, provided by the forward network servicen2Is the service rate, R, of the backward network service offeringcIs the service rate provided by the cloud service, f is the cloud service processingAnd calculating the influence factors on data transmission during the process.
Preferably, the online service quality assessment module is specifically configured to:
and operating the formulas 1,2 and 3 to obtain:
wherein R ise2e=min{Rn1,Rc,Rn2/f},Te2e=Tn1+Tc+Tn2;
When the load is alpha (t) ═ M + pt, the upper time delay bound of the system is Dmax=Te2e+M/Re2e=Tc+Te+M/Re2e;
Wherein, Tn=Tn1+Tn2;
Preferably, the online service quality assessment module is further specifically configured to: in the case of ignoring the signal processing delay, the service delay parameter T is the sum of the link transmission delay and the packet processing delay, i.e. T ═ L/R + L/C, where L denotes the maximum packet length, C denotes the minimum link transmission rate, and R denotes the number of requests of the user;
wherein, Tn=L(1/Rn1+1/Rn2+2/C);
The upper delay bound of the system is Dmax=Tc+L(1/Rn1+1/Rn2+2/C)+M/Re2e(ii) a Wherein R ise2e=min{Rn1,Rc,Rn2/f}。
A third embodiment of the present invention provides an online quality of service guarantee performance evaluation apparatus, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, where the processor executes the computer program to implement an online quality of service guarantee performance evaluation method as described in any one of the above.
The method, the device and the equipment for evaluating the guarantee performance of the on-line service quality provided by the invention analyze the performance of the network to obtain the service capability and the load of the system, provide a delay upper bound aiming at the service capability and the load obtained by analysis, and analyze different factors of the delay upper bound to obtain an on-line service quality evaluation report with higher reliability.
Drawings
Fig. 1 is a schematic flowchart of a method for evaluating performance of guaranteeing quality of online service according to a first embodiment of the present invention;
FIG. 2 is a diagram illustrating a multi-service-desk hybrid queuing model according to an embodiment of the present invention;
fig. 3 to 10 are simulation experiment diagrams provided by the embodiment of the present invention;
fig. 11 is a schematic structural diagram of a performance-guaranteeing module for online quality of service according to a second embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
For better understanding of the technical solutions of the present invention, the following detailed descriptions of the embodiments of the present invention are provided with reference to the accompanying drawings.
It should be understood that the described embodiments are only some embodiments of the invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The terminology used in the embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the examples of the present invention 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 be understood that the term "and/or" as used herein is merely one type of association that describes an associated object, meaning that three relationships may exist, e.g., a and/or B may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.
The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination" or "in response to a detection", depending on the context. Similarly, the phrases "if determined" or "if detected (a stated condition or event)" may be interpreted as "when determined" or "in response to a determination" or "when detected (a stated condition or event)" or "in response to a detection (a stated condition or event)", depending on the context.
In the embodiments, the references to "first \ second" are merely to distinguish similar objects and do not represent a specific ordering for the objects, and it is to be understood that "first \ second" may be interchanged with a specific order or sequence, where permitted. It should be understood that "first \ second" distinct objects may be interchanged under appropriate circumstances such that the embodiments described herein may be practiced in sequences other than those illustrated or described herein.
The following detailed description of specific embodiments of the invention refers to the accompanying drawings.
The invention discloses a method, a device and equipment for evaluating guarantee performance of online service quality, and aims to provide an evaluation result for online service with burst flow so as to optimize service capacity of a system.
Referring to fig. 1, a first embodiment of the present invention provides a method for evaluating performance of on-line service, which can be executed by an apparatus for evaluating performance of on-line service (hereinafter referred to as "evaluation apparatus"), and in particular, executed by one or more processors in the evaluation apparatus, to implement the following steps:
s101, analyzing network performance, and acquiring service capacity and load of a system;
in this embodiment, the burst traffic may be analyzed first, and particularly, the burst online teaching traffic may be analyzed;
the statistical flow rate of the connected graph N ═ V, E >, N ═ V |, m ═ E |, each edge < i, j > has a non-negative number C (i, j), called edge < i, j >. N has two special vertices s and t, s being called the lower issue point, t being called the receive point, and the remaining vertices being called the intermediate points [11 ]. And the N is called the aggregation flow of the network outlet and is marked as N ═ V, E, c, s and t.
E → R, wherein R is a non-negative number set, and the following conditions are satisfied:
Let f be a feasible flow on the aggregate flow N, let the net flow of the issue point s be f, and be denoted as v (f), that is
The feasible flow with the largest variation in flow value is called a burst flow.
Analysis of the aggregate stream:
From the above, it can be obtained:
If f is any aggregated flow on the network N,is any one of the cut sets, andit is the maximum flow that is limited,is the minimal cut set.
Assuming that there is at most one edge between each vertex in N, if there are two edges < i, j > and < j, i > between i and j, a vertex k can be inserted on < j, i >, dividing < j, i > into two edges < j, k > and < k, i >, and the capacities are all equal to c (j, i). Then:
maxv(f)=s.t.f(i,j)≤c(i,j),<i,j>∈E (9)
f(i,j)≥0,<i,j>∈E (12)
v(f)≥0 (13)
and analyzing the blocking probability:
when a large number of users in a batch cannot enter the queue buffer due to burst traffic, network congestion is caused. The blocking probability [12] is an important measure of network QOS. For the waiting user, the system will adopt a first-come-first-served strategy, and after the user enters the buffer, there may be two different results of queuing or refusing. Assuming that the position of a single user R in the queue conforms to a normal distribution, the probability of R in j batches is:
if the queue length of R is set as the number of requests, then the subsequent user cannot enter the waiting area, i.e. there will be a block for one request in the batch. With a blocking probability of
Analyzing the immediate service probability:
when the server of the R request is in an idle state, service is immediately available. The queue length of the current system is i (i < m), the batch arrival number is j, and when j is less than or equal to m-i, all requests are immediately served; when j > m-i, requests located at [1, j-m + i ] are immediately serviced because the system employs a partial acceptance policy and a first-come-first-served order. Thus, the immediate service probability [13] is
Analyzing the delay time:
the user delay time is the sum of the system service and the waiting time. According to formula 14, Wq(t) is a probability distribution function of the waiting time t, and when the waiting time is 0, the probability is as follows:
if the position of R is n, n belongs to [1, j ], the service can not be obtained immediately, and the service is obtained after the previous service request is finished according to the principle of coming first. Assuming that the number of requests for R is l, m is the number of service stations, and the outgoing flow of l requests conforms to an l-step Erlang distribution of m μ. The two cases of L are respectively:
when i is<m, R requests arrive. When j belongs to (m-i, N-i)]When n is an element (m-j, j)]And then R enters a queue to wait. When j ∈ (N-i, ∞)]And N is an element (m-j, N-j)]It also waits. With l being n-m + i, a distribution function of latencyIs composed of
When i ≧ m, there is no idle helpdesk when the request arrives. When j is equal to [1, N-i ]],n∈[1,j]The request may be queued. When j ∈ (N-i, ∞)]And N is equal to [1, N-i ]]It also waits. With l being n-m + i, a distribution function of latencyIs composed of
Therefore, waiting time Wq(t) is
Wherein the content of the first and second substances,andcan be substituted by formula (18) and formula (19), respectively. Delay time W ═ Wq+Ws, WqAnd WsAre independent of each other. According to the convolution formula of the distribution function, the delay time can be obtained as follows:
analyzing the service concurrency capability:
in a cloud service system, user requests are often arrived in batches (e.g., a user needs to deploy multiple VMs). This document will be referred to the references [14-15 ]]For M, starting from the characteristics of user batch request and flow characteristicsxAnd modeling and analyzing the service performance of cloud computing by using the/M/M/M + r queuing model. According to common performance indexes in the queuing system, an expression of corresponding indexes in the batch queuing is given, and the service quality of the cloud service system is analyzed, so that the QoS is guaranteed and the Service Level Agreement (SLA) is avoided being violated.
When a business system is normally serving, there are usually a large number of users requesting access to the service desk. When the user sends a request, the service desk can provide different types of services in a self-adaptive mode according to the requirements of the user, and the user can queue into a buffer area. Queuing model Mxthe/M/M/M + r is a multi-service desk mixed queuing model, belongs to a Markov process of finite state, and is specifically shown in FIG. 2. The operating characteristics of the model are: data streams arrive at a service desk in batches, and lambda is the arrival time interval of the data streams and obeys Poisson flow; the number of requests in each batch is a random variable X with a probability distribution of P (X) ci,x is 1,2, …, k (k is a positive integer).
The queue length i of the user request number in the system is set as the state variable of the system, and the probability is piiSystem capacity N ═ m + r, flow intensityKnown when p<1, the system has a steady state, and the state transition satisfies the following rule.
For the exit of the state i, starting from any state i, it can reach any subsequent state i +1, i +2, …, or i + k one step to the right, i.e. there is a batch of x requests in the i state to reach the system. But only to the left of its neighbor state i-1, i.e., at the same time, only one request is served and leaves the system.
When i is switched in, the left state of the state i is i-1, i-2, …, i-k is directly reached, namely the queue length of the request with the batch of x is i after the request reaches the system. The states on the right are i +1, i +2, …, i + k, and the i state is reached when adjacent to state i + 1.
After the service is finished, the transition probability of the transition process from the state i to the i-1 state has different change rules according to different values of the parameter i. With state m as a demarcation point, for state i to the left of m (0< i < m), the transition probability is i μ, and the transition probability to the right is m μ.
From Chapman-Kolmogorov-equation [ ], one can obtain:
from the formula (21), πi+1Can be made ofiRecursion to obtain Pi1,π2,…,πNAnd pi0A relationship between them, byA probability distribution of all queue lengths can be obtained.
Through the analysis, the number of the service stations is increased, and the service performance is improved. When a user request with a large burst amount is faced, a terminal server (a virtual machine or a host) needs to be added so as to effectively guarantee the QoS of the user.
The load was analyzed:
when the integrated service system provides the same service capability, the service performance obtained by the user is different due to different loads, and therefore, in order to more accurately analyze the service performance of the cloud service integrated service system, a method needs to be provided to describe the load of the integrated service system, that is, the data flow condition of the terminal user accessing the integrated service system.
The data flow of the user accessing the service system is limited by the access capability of the forward network service system. The forward network service system needs to detect whether the data flow arriving at the entry meets the condition, and when the data flow does not meet the condition, the network needs to perform corresponding adjustment. Therefore, the data flow of the end user accessing the forward network service system is the load of the integrated service system.
In order to express the characteristics of the flow, in practical applications, load balancing is to schedule jobs submitted by users to different virtual machine resources, so that the virtual machines or hosts in the system share the workload together to complete job execution. Of course, the existing resource pool may have tens of thousands or hundreds of thousands of service nodes of virtual machines and hosts, and if the load is unbalanced, the service is likely to be completely interrupted. Thus, it is assumed herein that the load of the on-line tutorial service system can be expressed in the form of a (t) ═ M + pt, where M denotes the maximum burst size, p denotes the arrival rate, and p needs to satisfy p ≦ R, otherwise the delay bound will tend to be infinite.
The limiting burst model was analyzed:
through the analysis of the network flow index in the online teaching, the burst limiting model is firstly set by considering the influence on the large flow burstiness, and is called as burst limitation. We denote a traffic flow on a given communication link by a non-negative number R, and for any two times X and y, and y ≧ X, the integral of R over the interval [ X, y ] denotes the amount of data transmitted on the link during the time [ X, y ] that the traffic is filling. R (t) 0, 1 represents the instantaneous traffic of the on-line traffic at time t. When R (t) is 0, the link is idle; when r (t) is 1, it indicates that its link is transmitting at full load. Given σ ≧ 0 and ρ ≧ 0, R ≧ R (σ, ρ), and when y ≧ x is satisfied for all x and y, then:
where ρ is the average rate and σ is the burst limit, and for a fixed value ρ, the larger σ, the larger the burst capability.
When the traffic is defined as the upper bound burst traffic, then:
where a is a function decay factor when any time period [ x, y ]]There is always an upper bound on the total amount of flow passing internally, the upper bound being a decreasing exponential function, ρ being the upper bound flow rate, Ae-aσIs a limiting function. If the traffic is constrained by this exponential function, the network delay and queue length are exponentially decaying.
For the random restricted burst case, when F (σ) ∈ F, given σ >0, 0 ≦ x < y, then there is:
ρ is the upper boundary flow rate and f (σ) is the limiting function.
S102, acquiring the time delay upper bound of the system according to the service capacity and the load; the method specifically comprises the following steps:
stable performance is a measure of the user's choice of online service. The time delay is an important parameter in performance indexes, and in an actual application scene, the quality of service is directly influenced by the time delay performance. For example, when students choose to perform online cloud education, they want the selected cloud service to be able to complete their requests in as short a time as possible. The traditional time delay analysis method can be divided into two types: one is statistical theory analysis and the other is time series analysis. However, both methods can only obtain the statistical value or approximate value of the average delay, and cannot obtain the delay upper bound which directly influences the cloud service quality and the user service selection. Therefore, the embodiment focuses on the discussion of the upper bound of the time delay of the converged service system.
The service capability is betae2eThe load is a (t), the delay upper bound DmaxThe delay upper bound of the system is obtained by the following formula:
equation 2: dmax=sup{inf{τ≥0:α(s)≤βe2e(s+τ)}};
The service capability curve of each service component in the cloud service system may be represented by an LR function. Therefore, it is assumed herein that the service capability of each service component in the service system and the scaling curve of the scaling function S are respectively
wherein R isn1Is the service rate, R, provided by the forward network servicen2Is the service rate, R, of the backward network service offeringcThe service rate provided by the cloud service, and f is an influence factor of the cloud service on data transmission when processing a computing process.
And S103, evaluating the on-line service quality according to the time delay upper bound. The method specifically comprises the following steps:
calculating the formulas 1,2 and 3 to obtain the end-to-end service capability of the integrated service system as follows:
wherein R ise2e=min{Rn1,Rc,Rn2/f},Te2e=Tn1+Tc+Tn2;
As can be seen from the above formula, for the cloud service integration service system, if each network service component is described as an LR function and the cloud service is described as an LR function with a linear scaling curve, the end-to-end service capability provided by the entire service system can be described as an LR function constrained by the scaling curve. The service delay parameter T is the sum of the delay parameters of each service component in the whole system. The service rate is the minimum value among the forward network service rate, the cloud service rate, and the transmission service rate of the backward network service.
When the load is alpha (t) ═ M + pt, the upper time delay bound of the system is Dmax=Te2e+M/Re2e=Tc+Te+M/Re2e;
Wherein, Tn=Tn1+Tn2;
In this embodiment, for network services, the delay parameter T in the LR function reflects the system properties of the network, which can be considered as the time required for the first bit stream to be transmitted in the worst case during the busy period of a network session. In case of ignoring the signal processing delay, the service delay parameter T is the sum of the link transmission delay and the packet processing delay, i.e. T ═ L/R + L/C, where L denotes the maximum packet length, C denotes the minimum link transmission rate, and R denotes the number of requests of the user.
Wherein, Tn=L(1/Rn1+1/Rn2+2/C);
The upper delay bound of the system is Dmax=Tc+L(1/Rn1+1/Rn2+2/C)+M/Re2e(ii) a Wherein R ise2e=min{Rn1,Rc,Rn2/f}。
From the above equation, when the network service rate is a constant value and the burst size of the data stream is 0, the upper delay bound of the integrated service system is a constant value, which is independent of the arrival rate of the data stream. This is because this chapter assumes that the arrival rate is not greater than the system service rate, so that the data stream entering the system will be serviced immediately without creating latency in the system. At this time, the upper bound of the delay time required by this document is the processing time of the system.
Specifically, referring to fig. 3 and 4, it can be seen that the network delay increases with the increase of the service rate when the network service rate is small, with different scaling factors and different delays of the IP numbers (i.e., the number of users). When f and K are continuously increased, the delay is also continuously increased along with the service rate, the delay upper bound is also continuously reduced, and the load of a backward transmission network is increased after the flow is processed by the server. Therefore, the network service rate and the network delay will have an influence in different situations, and the degree of the influence will be different.
The effect of simulation on network performance data using different numbers of network nodes is shown in fig. 5(f ═ 0.5) and fig. 6(f ═ 2) when the numbers of f ═ 0.5 and f ═ 2 nodes are 50, 100, 500, and 1000, respectively. When the number of the nodes of the used network is less, and the number (n) of the network nodes is 50, the obtained network delay is larger, and the larger the service rate is, the delay is increased all the time; whereas the delay shown in the figure is much less than the 50 network node delays when the number of network nodes (n) is 100 and 500. When n is 1000, the delay becomes smaller, and the delay becomes smaller as the number of nodes increases.
We assume that the maximum burst size is 2000Mb and that the burst sizes of the forward load and the backward load are identical. As can be seen in fig. 7(f is 0.5) and fig. 8(f is 2), as the maximum burst size increases, the delay of the system increases. This is because when the service rate is constant, the network delay of the system increases. This is because when the service rate is constant, the delay of the system is only related to the maximum burst size, and the larger the maximum burst size is, the longer the processing time of the system is. In fig. 8, when f is 2, the system delay will also increase when the system provides a certain service rate due to the load of the backward transmission network increased by the data passing through the server.
Fig. 9(f ═ 0.5) and fig. 10(f ═ 2) depict graphs comparing the performance of the present method against the delay upper bound of the prior art at different scaling factors and at the same forward flow. It can be seen from experiments that at the same service rate, the present evaluation method will achieve a smaller upper bound on the delay when f is 0.5, Rn is 5000Mb/s and f is 2, Rn is 5000 Mb/s. This is because the prior art cannot allocate traffic according to the service capability of the link, which causes an excessive traffic load on the data link, resulting in network congestion, thereby affecting the upper bound of the delay. The main factor for determining that the performance evaluation method for limiting the burst model influences the upper bound of the time delay is burst flow, and although the arrival rate is related, the influence on the time delay is not large.
It follows that the upper delay bound increases with increasing service rate. When the service rate is constant, the burst traffic is a main factor affecting the upper bound of the delay. As the number of users continues to increase, the service capabilities offered to the network services have a significant impact on the upper delay bound. And when the number of the nodes is more, the service capability of the nodes is stronger, and the network delay is smaller, which shows that the computing capability of the nodes also plays a main role in the upper bound of the delay. Therefore, when dealing with burst traffic, in order to avoid network congestion, a network operator should calculate an upper bound of data accumulation of a service node according to its service capability and a request of a user in order to guarantee the service quality of a network, thereby providing a basis for allocation of the size of a buffer area of a network service node. And secondly, the outlet bandwidth is expanded as much as possible, and the load balance of multiple bandwidths is realized to ensure that the bandwidth is not congested. Finally, network operators need to use a network virtual batch technology to provide network resources in a service form and provide abundant and diverse network services to meet the requirements of service personalization and diversification.
Referring to fig. 11, a second embodiment of the present invention provides an apparatus for evaluating performance of guaranteeing quality of online service, including:
a network performance analysis module 201, configured to analyze network performance and obtain a service capability of the system and a load of the system;
a delay upper bound obtaining module 202, configured to obtain a delay upper bound of the system according to the service capability and the load;
and the on-line service quality evaluation module 203 is configured to evaluate the on-line service quality according to the delay upper bound.
Preferably, the delay upper bound obtaining module 202 is specifically configured to:
the service capability is betae2eThe load is a (t), the delay upper bound DmaxThe delay upper bound of the system is obtained by the following formula:
equation 2: dmax=sup{inf{τ≥0:α(s)≤βe2e(s+τ)}};
wherein R isn1Is the service rate, R, provided by the forward network servicen2Is the service rate, R, of the backward network service offeringcThe service rate provided by the cloud service, and f is an influence factor of the cloud service on data transmission when processing a computing process.
Preferably, the online service quality assessment module 203 is specifically configured to:
and operating the formulas 1,2 and 3 to obtain:
wherein R ise2e=min{Rn1,Rc,Rn2/f},Te2e=Tn1+Tc+Tn2;
When the load is alpha (t) ═ M + pt, the upper time delay bound of the system is Dmax=Te2e+M/Re2e=Tc+Te+M/Re2e;
Wherein, Tn=Tn1+Tn2;
Preferably, the online service quality assessment module 203 is further configured to: in the case of ignoring the signal processing delay, the service delay parameter T is the sum of the link transmission delay and the packet processing delay, i.e. T ═ L/R + L/C, where L denotes the maximum packet length, C denotes the minimum link transmission rate, and R denotes the number of requests of the user;
wherein, Tn=L(1/Rn1+1/Rn2+2/C);
The upper delay bound of the system is Dmax=Tc+L(1/Rn1+1/Rn2+2/C)+M/Re2e(ii) a Wherein R ise2e=min{Rn1,Rc,Rn2/f}。
A third embodiment of the present invention provides an online quality of service guarantee performance evaluation apparatus, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, where the processor executes the computer program to implement an online quality of service guarantee performance evaluation method as described in any one of the above.
The method, the device and the equipment for evaluating the guarantee performance of the on-line service quality provided by the invention analyze the performance of the network to obtain the service capability and the load of the system, provide a delay upper bound aiming at the service capability and the load obtained by analysis, and analyze different factors of the delay upper bound to obtain an on-line service quality evaluation report with higher reliability.
A fourth embodiment of the present invention provides a readable storage medium, where a computer program is stored, where the computer program is executable by a processor of a device in which the storage medium is located, so as to implement a method for evaluating performance of online service quality guarantee as described in any one of the above.
Illustratively, the computer programs described in the third and fourth embodiments of the present invention may be partitioned into one or more modules, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules may be a series of computer program instruction segments capable of performing specific functions, which are used for describing the execution process of the computer program in the guaranteed performance assessment apparatus for implementing an online quality of service. For example, the device described in the second embodiment of the present invention.
The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. The general processor can be a microprocessor or the processor can be any conventional processor, etc., the processor is a control center of the method for evaluating the performance of guaranteeing the on-line service quality, and various interfaces and lines are used for connecting all parts of the method for evaluating the performance of guaranteeing the on-line service quality.
The memory may be used to store the computer program and/or module, and the processor may implement various functions of the method for on-line quality of service assurance performance assessment by executing or executing the computer program and/or module stored in the memory and calling data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, a text conversion function, etc.), and the like; the storage data area may store data (such as audio data, text message data, etc.) created according to the use of the cellular phone, etc. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
Wherein the implemented module, if implemented in the form of a software functional unit and sold or used as a stand-alone product, can be stored in a computer readable storage medium. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
It should be noted that the above-described device embodiments are merely illustrative, where the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. In addition, in the drawings of the embodiment of the apparatus provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, and may be specifically implemented as one or more communication buses or signal lines. One of ordinary skill in the art can understand and implement it without inventive effort.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A method for evaluating guarantee performance of online service quality is characterized by comprising the following steps:
analyzing the network performance to obtain the service capability and the load of the system;
acquiring the time delay upper bound of the system according to the service capacity and the load;
and evaluating the service quality on the line according to the time delay upper bound.
2. The method of claim 1, wherein the analyzing the network performance comprises: analyzing blocking probability, analyzing immediate service probability, analyzing delay time, analyzing service concurrency capability, and analyzing load.
3. The method for evaluating performance of guaranteeing online service quality according to claim 1, wherein the obtaining of the upper delay bound of the system according to the service capability and the load specifically comprises:
the service capability is betae2eThe load is a (t), the delay upper bound DmaxThe delay upper bound of the system is obtained by the following formula:
equation 2: dmax=sup{inf{τ≥0:α(s)≤βe2e(s+τ)}};
wherein R isn1Is the service rate, R, provided by the forward network servicen2Is the service rate, R, of the backward network service offeringcThe service rate provided by the cloud service, and f is an influence factor of the cloud service on data transmission when processing a computing process.
4. The method for evaluating performance of guaranteeing online service quality according to claim 3, wherein the evaluating the online service quality according to the upper time delay bound specifically comprises:
and operating the formulas 1,2 and 3 to obtain:
wherein R ise2e=min{Rn1,Rc,Rn2/f},Te2e=Tn1+Tc+Tn2;
When the load is alpha (t) ═ M + pt, the upper time delay bound of the system is Dmax=Te2e+M/Re2e=Tc+Te+M/Re2e;
Wherein, Tn=Tn1+Tn2。
5. The method of claim 4, further comprising: in case of ignoring the signal processing delay, the service delay parameter T is the sum of the link transmission delay and the packet processing delay, i.e. T ═ L/R + L/C, where L denotes the maximum packet length, C denotes the minimum link transmission rate, and R denotes the number of requests of the user.
Wherein, Tn=L(1/Rn1+1/Rn2+2/C);
The upper delay bound of the system is Dmax=Tc+L(1/Rn1+1/Rn2+2/C)+M/Re2e(ii) a Wherein R ise2e=min{Rn1,Rc,Rn2/f}。
6. An apparatus for evaluating guaranteed performance of online service quality, comprising:
the network performance analysis module is used for analyzing the network performance and acquiring the service capability and the load of the system;
the time delay upper bound obtaining module is used for obtaining the time delay upper bound of the system according to the service capacity and the load;
and the on-line service quality evaluation module is used for evaluating the on-line service quality according to the time delay upper bound.
7. The apparatus for assessing performance of guaranteeing online quality of service according to claim 6, wherein the delay upper bound obtaining module is specifically configured to:
the service capability is betae2eThe load is a (t), the delay upper bound DmaxThe delay upper bound of the system is obtained by the following formula:
equation 2: dmax=sup{inf{τ≥0:α(s)≤βe2e(s+τ)}};
wherein R isn1Is the service rate, R, provided by the forward network servicen2Is the service rate, R, of the backward network service offeringcThe service rate provided by the cloud service, and f is an influence factor of the cloud service on data transmission when processing a computing process.
8. The apparatus for assessing performance guarantee of online service quality according to claim 7, wherein the online service quality assessment module is specifically configured to:
and operating the formulas 1,2 and 3 to obtain:
wherein R ise2e=min{Rn1,Rc,Rn2/f},Te2e=Tn1+Tc+Tn2;
When the load is alpha (t) ═ M + pt, the upper time delay bound of the system is Dmax=Te2e+M/Re2e=Tc+Te+M/Re2e;
Wherein, Tn=Tn1+Tn2。
9. The apparatus for assessing performance of ensuring online service quality according to claim 8, wherein the online service quality assessment module is further configured to: in the case of ignoring the signal processing delay, the service delay parameter T is the sum of the link transmission delay and the packet processing delay, i.e. T ═ L/R + L/C, where L denotes the maximum packet length, C denotes the minimum link transmission rate, and R denotes the number of requests of the user;
wherein, Tn=L(1/Rn1+1/Rn2+2/C);
The upper delay bound of the system is Dmax=Tc+L(1/Rn1+1/Rn2+2/C)+M/Re2e(ii) a Wherein R ise2e=min{Rn1,Rc,Rn2/f}。
10. An on-line quality of service assurance performance evaluation apparatus, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement an on-line quality of service assurance performance evaluation method according to any one of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010972667.3A CN112714037A (en) | 2020-09-16 | 2020-09-16 | Method, device and equipment for evaluating guarantee performance of online service quality |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010972667.3A CN112714037A (en) | 2020-09-16 | 2020-09-16 | Method, device and equipment for evaluating guarantee performance of online service quality |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112714037A true CN112714037A (en) | 2021-04-27 |
Family
ID=75542374
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010972667.3A Pending CN112714037A (en) | 2020-09-16 | 2020-09-16 | Method, device and equipment for evaluating guarantee performance of online service quality |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112714037A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114300082A (en) * | 2022-03-14 | 2022-04-08 | 四川大学华西医院 | Information processing method and device and computer readable storage medium |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140188575A1 (en) * | 2012-12-31 | 2014-07-03 | Laureate Education, Inc. | Collaborative quality assurance system and method |
CN106102084A (en) * | 2016-05-24 | 2016-11-09 | 重庆邮电大学 | Wireless sensor network end-to-end time delay upper bound appraisal procedure based on retransmission feedback |
-
2020
- 2020-09-16 CN CN202010972667.3A patent/CN112714037A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140188575A1 (en) * | 2012-12-31 | 2014-07-03 | Laureate Education, Inc. | Collaborative quality assurance system and method |
CN106102084A (en) * | 2016-05-24 | 2016-11-09 | 重庆邮电大学 | Wireless sensor network end-to-end time delay upper bound appraisal procedure based on retransmission feedback |
Non-Patent Citations (3)
Title |
---|
Q. DUAN等: "Holistic Modeling and Performance Evaluation for Converged Network-Cloud Service Provisioning", 《2014 IEEE 28TH INTERNATIONAL CONFERENCE ON ADVANCED INFORMATION NETWORKING AND APPLICATIONS》 * |
Z. WANG等: "Policy-Based SLA-Aware Cloud Service Provision Framework", 《2011 SEVENTH INTERNATIONAL CONFERENCE ON SEMANTICS, KNOWLEDGE AND GRIDS》 * |
刘宴兵等: "面向云服务的网络参数建模与定量分析", 《数学的实践与认识》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114300082A (en) * | 2022-03-14 | 2022-04-08 | 四川大学华西医院 | Information processing method and device and computer readable storage medium |
CN114300082B (en) * | 2022-03-14 | 2022-06-10 | 四川大学华西医院 | Information processing method and device and computer readable storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10460241B2 (en) | Server and cloud computing resource optimization method thereof for cloud big data computing architecture | |
US8144590B2 (en) | Distributed resource allocation in stream processing systems | |
US10091675B2 (en) | System and method for estimating an effective bandwidth | |
CN104901989B (en) | A kind of Site Service offer system and method | |
CN103699445A (en) | Task scheduling method, device and system | |
US7113986B2 (en) | System and method for modeling information system capacity and accepting sessions in an information system | |
CN109615022B (en) | Model online configuration method and device | |
Huang et al. | Auto scaling virtual machines for web applications with queueing theory | |
CN112506619B (en) | Job processing method, job processing device, electronic equipment and storage medium | |
CN113553160A (en) | Task scheduling method and system for edge computing node of artificial intelligence Internet of things | |
CN114268537A (en) | Network slice generation and dynamic configuration system and method for deterministic network | |
CN109688065B (en) | Parameter processing method and device and storage medium | |
CN117082008B (en) | Virtual elastic network data transmission scheduling method, computer device and storage medium | |
CN112714037A (en) | Method, device and equipment for evaluating guarantee performance of online service quality | |
CN111885667B (en) | Network resource allocation method and system | |
CN111405614B (en) | Method for calculating APP load sharing at mobile edge | |
CN103825963B (en) | Virtual Service moving method | |
CN116382892B (en) | Load balancing method and device based on multi-cloud fusion and cloud service | |
CN116915869A (en) | Cloud edge cooperation-based time delay sensitive intelligent service quick response method | |
CN112596985A (en) | IT asset detection method, device, equipment and medium | |
Maglaras et al. | Diffusion approximations for a multiclass Markovian service system with “guaranteed” and “best-effort” service levels | |
CN114936089A (en) | Resource scheduling method, system, device and storage medium | |
CN114448838B (en) | System reliability evaluation method | |
CN113676341B (en) | Quality difference evaluation method and related equipment | |
CN114489463A (en) | Method and device for dynamically adjusting QOS (quality of service) of storage volume and computing equipment |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210427 |
|
RJ01 | Rejection of invention patent application after publication |