PSO-Based Ensemble Meta-Learning Approach for Cloud Virtual Machine Resource Usage Prediction
Open Access
Abstract
To meet the increasing demand for its services, a cloud system should make optimum use of its available resources. Additionally, the high and low oscillations in cloud workload are another significant symmetrical issue that necessitates consideration. A suggested particle swarm optimization (PSO)-based ensemble meta-learning workload forecasting approach uses base models and the PSO-optimized weights of their network inputs. The proposed model employs a blended ensemble learning strategy to merge three recurrent neural networks (RNNs), followed by a dense neural network layer. The CPU utilization of GWA-T-12 and PlanetLab traces is used to assess the method’s efficacy. In terms of RMSE, the approach is compared to the LSTM, GRU, and BiLSTM sub-models.Keywords
Funding Information
- National Natural Science Foundation of China (62271128, 61802033, 2020YFQ0018, 2022ZDX0004, 22ZDX0046, 2022YFG0212, 2021YFG0027, 2020YFG0475, 2019YJ0543)
- Sichuan Regional Innovation Cooperation Project (62271128, 61802033, 2020YFQ0018, 2022ZDX0004, 22ZDX0046, 2022YFG0212, 2021YFG0027, 2020YFG0475, 2019YJ0543)
- key Rand D Projects of Sichuan Science and Technology Program (62271128, 61802033, 2020YFQ0018, 2022ZDX0004, 22ZDX0046, 2022YFG0212, 2021YFG0027, 2020YFG0475, 2019YJ0543)
This publication has 46 references indexed in Scilit:
- Optimizing Resource Utilization of a Data CenterIEEE Communications Surveys & Tutorials, 2016
- Assessing and forecasting energy efficiency on Cloud computing platformsFuture Generation Computer Systems, 2015
- Self-Adaptive Prediction of Cloud Resource Demands Using Ensemble Model and Subtractive-Fuzzy Clustering Based Fuzzy Neural NetworkComputational Intelligence and Neuroscience, 2015
- Cloud resource management: A survey on forecasting and profiling modelsJournal of Network and Computer Applications, 2015
- Resource management for Infrastructure as a Service (IaaS) in cloud computing: A surveyJournal of Network and Computer Applications, 2014
- Ensemble Learning for Large-Scale Workload PredictionIEEE Transactions on Emerging Topics in Computing, 2014
- Optimizing Energy Consumption with Task Consolidation in CloudsInformation Sciences, 2014
- On the Properties of Neural Machine Translation: Encoder–Decoder Approaches2014
- Long Short-Term MemoryNeural Computation, 1997
- Controlled-Potential Coulometric Analysis of N-Substituted Phenothiazine Derivatives.Analytical Chemistry, 1964