Extreme Learning Machines 2013: Algorithms and Applications by Fuchen Sun Kar-Ann Toh Manuel Grana Romay & Kezhi Mao

Author:Fuchen Sun, Kar-Ann Toh, Manuel Grana Romay & Kezhi Mao
Language: eng
Format: epub
Publisher: Springer International Publishing, Cham

4 ELM Based Adaptive Live Migration Approach

We can see from the above analysis, the pre-copy algorithm does not efficiently process VM live migration in memory-intensive application scenarios, so we combine ELM techniques and propose an ELM based adaptive live migration approach of virtual machines (ELMBALMA) to solve the problem. Next we first introduce the ELM, then describe the ELM based VM live migration framework and related algorithms in detail.

4.1 ELM

Extreme learning machine (ELM) is a new learning algorithm for single-hidden layer feedforward neural networks (SLFNs), which is proposed by Huang et al. [2, 3]. It not only can avoid a number of iterations and the local minimum, but also have better generalization, robustness and controllability, and is widely used in regression and classification problems. It randomly assigns the input weights and hidden layer biases and then analytically determines the output weights of SLFNs. ELM can achieve better performance than other conventional learning algorithms for classification [17]. Also, it is less sensitive to user-specified parameters, and can be developed faster and more conveniently [18].

Given and , and an activation function g(x), standard SLFNs with N arbitrary samples are modeled as

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.