Method and apparatus for establishing network performance model

1. A method for establishing a network performance model used for showing the performance of a computer network node, the method comprising:

receiving, by a performance model establishing device, performance data provided by the computer network node;

rounding, by the performance model establishing device, the performance data or dividing the performance data into blocks;

determining, by the performance model establishing device, according to at least one of the rounded and divided performance data, the performance data being provided by the computer network node, a parameter α showing a correlation of the performance data of different computer network nodes in a whole network and a parameter β showing a distribution pattern of the performance data in the network; and

establishing, by the performance model establishing device, a Latent Dirichlet Allocation, LDA, network performance model by using the determined parameter α and the parameter β.

2. The method of claim 1 , wherein the determining the parameter α and the parameter β comprises:

determining the parameters α and β that make the received performance data occur with the maximum probability.

3. The method of claim 2 , wherein the determining the parameters α and β that make the received performance data occur with the maximum probability comprises:

determining the parameters α and β that make the received performance data occur with the maximum probability by using the maximum likelihood approach.

4. The method of claim 3 , wherein the determining the parameters α and β that make the received performance data occur with the maximum probability by using the maximum likelihood approach comprises:

initializing a component number K of the LDA network performance model, in which K is greater than or equals to 2;

establishing a likelihood function l(α,β) containing the parameters α and β ; and

calculating, according to the received performance data, the parameters α and β that make the likelihood function l(α,β) reach the maximum value.

5. The method of claim 4 , wherein the likelihood function l(α,β) containing the parameters α and β is

l

⁡

(

α

,

β

)

=

∑

d

=

1

M

⁢

⁢

log

⁢

⁢

p

⁡

(

w

d

❘

α

,

β

)

,

in which

M is the number of computer network nodes selected for sending performance data, w d is the performance data sent from the d th computer network node, and p(w d |α,β) is the probability of w d occurring under conditions of the parameters β and α; and

the likelihood function l(α,β) contains internal latent variables θ and Z d , θ showing a distribution pattern of the performance data of the computer network node and complying with a Dirichlet distribution Dir(α), and θ being a parameter of K dimension; Z d showing the distribution pattern of performance data of the d th computer network node and complying with multinomial distribution Multinomial(θ); α a is a parameter of K dimension; when the probability of w d is p(w d |Z d ,β) with the parameters β and Z d , β shall be a parameter characterized by K and V; wherein V indicates a numerical value of a sample space of performance data.

6. The method of claim 5 , wherein, when the probability of w d is p(w d |Z d ,β) with the parameters Z d and β the calculating of the parameters α and β that make the likelihood function l(α,β) reach the maximum value further comprises:

calculating, by using a variational inference, the parameters α and β that make the likelihood function l(α,β) reach the maximum value.

7. The method of claim 6 , wherein the calculating, by using a variational inference, the parameters α and β that make the likelihood function l(α,β) reach the maximum value comprises:

introducing intermediate variables γ and φ into the likelihood function l(α,β) to obtain a simplified equivalent function L(γ,φ,α,β) of the likelihood function l(α,β), in which γ is a parameter of K dimension and φ is a parameter of K×V dimension;

calculating, with the parameters α and β as known variables and the parameters φ and φ as independent variables, optimized values of the parameters γ and φ by calculating the extremum of the simplified equivalent function L(γ,φ,α,β); and

using the optimized values of the parameters γ and φ in the simplified equivalent function L(γ,φ,α,β), calculating the extremum of the simplified equivalent function L(γ,φ,α,β) with the parameters α and β as the independent variables, and obtaining the values of the parameters α and β as the values of the parameters α and β that make the likelihood function l(α,β) reach the maximum value.

8. The method of claim 5 , wherein the establishing the LDA network performance model by using the determined parameters α and β comprises:

determining, according to the determined parameters α and β ,the Dir(α) with which the internal latent variable θ complies and the multinomial distribution Multinomial(θ) with which the internal latent variable Z d complies.

9. The method of claim 8 , further comprising:

generating simulated performance data by using the established LDA performance model.

10. The method of claim 9 , wherein the generating the simulated performance data by using the established LDA performance model comprises:

selecting N as the amount number of performance data generated by the d th computer network node, wherein N complies with Poisson distribution;

making, by using the determined parameter α, the internal variable θ to comply with the Dir(α);

making Z dn , which corresponds to simulated performance data w dn , to comply with the multinomial distribution Multinomial(θ);

making w dn to comply with p(w n |Z dn ,β) according to the determined parameter βwhen the probability of w dn with the parameters Z dn and βis p(w dn |Z dn ,β); or making w dn to comply with Gaussian distribution when w dn with the parameters Z dn and β complies with Gaussian distribution; wherein w dn is the n th simulated performance data of the d th computer network node and Z dn is a distribution pattern of the n th performance data of the d th computer network node.