Combining time series prediction models using genetic algorithm to autoscaling Web applications hosted in the cloud infrastructure

Abstract

In a cloud computing environment, companies have the ability to allocate resources according to demand. However, there is a delay that may take minutes between the request for a new resource and it is ready for using. This causes the reactive techniques, which request a new resource only when the system reaches a certain load threshold, are not suitable for the resource allocation process. To address this problem, it is necessary to predict requests that arrive at the system in the next period of time to allocate the necessary resources, before the system becomes overloaded. There are several time-series forecasting models to calculate the workload predictions based on history of monitoring data. However, it is difficult to know which is the best time series forecasting model to be used in each case. The work becomes even more complicated when the user does not have much historical data to be analyzed. Most related work, considers only single methods to evaluate the results of the forecast. Other work propose an approach that selects suitable forecasting methods for a given context. But in this case, it is necessary to have a significant amount of data to train the classifier. Moreover, the best solution may not be a specific model, but rather a combination of models. In this paper we propose an adaptive prediction method using genetic algorithms to combine time-series forecasting models. Our method does not require a previous phase of training, because it constantly adapts the extent to which the data is coming. To evaluate our proposal we use three logs extracted from real web servers. The results show that our proposal often brings the best result, and is generic enough to adapt to various types of time series.

An intelligent power consumption model for virtual machines under CPU-intensive workload in cloud environment

“…Softwarebased power monitoring has major advantages including high feasibility and low deployment cost. Meanwhile, it is still able to warrant accurate load prediction and power estimation by means of soft computing methodologies mentioned in Messias et al (2015), Aliev et al (2002) and Arroba et al (2014).…”

Application of flower pollination algorithm in load frequency control of multi-area interconnected power system with nonlinearity

“…Extensive studies employed various meta-heuristic optimization algorithms in several applications and for tuning different parameters [27][28][29]. The current study conducted the FPA to tune the LFC parameters of multi-area interconnected power system.…”

An autonomic risk‐ and penalty‐aware resource allocation with probabilistic resource scaling mechanism for multilayer cloud resource provisioning

“…According to the history of cloud service requests, the analysis and prediction of their future status can be performed for the upcoming time interval. In order to predict the future status of cloud layers, this study proposes a hybrid prediction model, which is the improved version of the algorithm presented in Messias et al The proposed algorithm has more computational speed and accuracy compared with the base algorithm. The error rate ( Er ) of p prediction model can be calculated from the Equation .…”