Auto-scaling Scheme Research Articles

ScalableDigitalHealth (SDH): An IoT-Based Scalable Framework for Remote Patient Monitoring.

Addressing the increasing demand for remote patient monitoring, especially among the elderly and mobility-impaired, this study proposes the "ScalableDigitalHealth" (SDH) framework. The framework integrates smart digital health solutions with latency-aware edge computing autoscaling, providing a novel approach to remote patient monitoring. By leveraging IoT technology and application autoscaling, the "SDH" enables the real-time tracking of critical health parameters, such as ECG, body temperature, blood pressure, and oxygen saturation. These vital metrics are efficiently transmitted in real time to AWS cloud storage through a layered networking architecture. The contributions are two-fold: (1) establishing real-time remote patient monitoring and (2) developing a scalable architecture that features latency-aware horizontal pod autoscaling for containerized healthcare applications. The architecture incorporates a scalable IoT-based architecture and an innovative microservice autoscaling strategy in edge computing, driven by dynamic latency thresholds and enhanced by the integration of custom metrics. This work ensures heightened accessibility, cost-efficiency, and rapid responsiveness to patient needs, marking a significant leap forward in the field. By dynamically adjusting pod numbers based on latency, the system optimizes system responsiveness, particularly in edge computing's proximity-based processing. This innovative fusion of technologies not only revolutionizes remote healthcare delivery but also enhances Kubernetes performance, preventing unresponsiveness during high usage.

A decision-making mechanism for task offloading using learning automata and deep learning in mobile edge networks

The development of mobile networks has led to the emergence of challenges such as high delays in storage, computing and traffic management. To deal with these challenges, fifth-generation networks emphasize the use of technologies such as mobile cloud computing and mobile edge computing. Mobile Edge Cloud Computing (MECC) is an emerging distributed computing model that provides access to cloud computing services at the edge of the network and near mobile users. With offloading tasks at the edge of the network instead of transferring them to a remote cloud, MECC can realize flexibility and real-time processing. During computation offloading, the requirements of Internet of Things (IoT) applications may change at different stages, which is ignored in existing works. With this motivation, we propose a task offloading method under dynamic resource requirements during the use of IoT applications, which focuses on the problem of workload fluctuations. The proposed method uses a learning automata-based offload decision-maker to offload requests to the edge layer. An auto-scaling strategy is then developed using a long short-term memory network which can estimate the expected number of future requests. Finally, an Asynchronous Advantage Actor-Critic algorithm as a deep reinforcement learning-based approach decides to scale down or scale up. The effectiveness of the proposed method has been confirmed through extensive experiments using the iFogSim simulator. The numerical results show that the proposed method has better scalability and performance in terms of delay and energy consumption than the existing state-of-the-art methods.

Proactive Resource Autoscaling Scheme Based on SCINet for High-Performance Cloud Computing

Proactive Resource Autoscaling Scheme Based on SCINet for High-Performance Cloud Computing

Toward Optimal Load Prediction and Customizable Autoscaling Scheme for Kubernetes

Most enterprise customers now choose to divide a large monolithic service into large numbers of loosely-coupled, specialized microservices, which can be developed and deployed separately. Docker, as a light-weight virtualization technology, has been widely adopted to support diverse microservices. At the moment, Kubernetes is a portable, extensible, and open-source orchestration platform for managing these containerized microservice applications. To adapt to frequently changing user requests, it offers an automated scaling method, Horizontal Pod Autoscaler (HPA), that can scale itself based on the system’s current workload. The native reactive auto-scaling method, however, is unable to foresee the system workload scenario in the future to complete proactive scaling, leading to QoS (quality of service) violations, long tail latency, and insufficient server resource usage. In this paper, we suggest a new proactive scaling scheme based on deep learning approaches to make up for HPA’s inadequacies as the default autoscaler in Kubernetes. After meticulous experimental evaluation and comparative analysis, we use the Gated Recurrent Unit (GRU) model with higher prediction accuracy and efficiency as the prediction model, supplemented by a stability window mechanism to improve the accuracy and stability of the prediction model. Finally, with the third-party custom autoscaling framework, Custom Pod Autoscaler (CPA), we packaged our custom autoscaling algorithm into a framework and deployed the framework into the real Kubernetes cluster. Comprehensive experiment results prove the feasibility of our autoscaling scheme, which significantly outperforms the existing Horizontal Pod Autoscaler (HPA) approach.

Container Scaling Strategy Based on Reinforcement Learning

Elasticity capability is one of the most important capabilities of cloud computing, which combines large-scale resource allocation capability to quickly achieve minute-level resource demand provisioning to meet the elasticity requirements of different scale scenarios. The elasticity capability is mainly determined by the container start-up speed and container scaling strategy together, where the container scaling strategy contains both vertical container scaling strategy and horizontal container scaling strategy. In order to make the container scaling policy more effective and improve the application service quality and resource utilization, we briefly introduce Kubernetes’ horizontal pod autoscaling (HPA) strategy, analyze the existing problem of HPA, and develop a container scaling strategy based on reinforcement learning. First, we analyze the problems of Kubernetes’ existing HPA container autoscaling strategy in the scale-up and scale-down phases, respectively. Second, the Markov decision model is used to model the container scaling problem. Then, we propose a model-based reinforcement learning algorithm to solve the container scaling problem. Finally, we compare the experimental results of the HPA scaling strategy and the model-based reinforcement learning strategy with the results from the resource utilization of the application, the change of the number of pods, and the application response time; through the experimental analysis, we verify that the reinforcement learning-based container scaling strategy can guarantee the application service quality and improve the utilization of the application resources more effectively than the HPA strategy.

Auto-scaling techniques for IoT-based cloud applications: a review

Cloud and IoT applications have inquiring effects that can strongly influence today’s ever-growing internet life along with necessity to resolve numerous challenges for each application such as scalability, security, privacy, and reliability. During the deployment of IoT-based Cloud applications, the demand for Cloud tenants is dynamic that makes challenging to maintain scalability of the system. Developing an effective scaling technique is not merely a big concern, but how to achieve autonomic scaling results using future load prediction and migration policies is also a crucial phase. Also, to evaluate such auto-scaling strategy, certain Quality of Service (QoS) metrics must be recognized, explored and leveraged to enhance the performance of the system. Therefore, in this paper, a survey of existing auto-scaling, load prediction and VM migration techniques for IoT-based Cloud applications has been carried out along with the evaluation of various QoS parameters. Further, the future trends have also been discussed for performing auto-scaling in a Cloud environment.

Heterogeneity-aware elastic scaling of streaming applications on cloud platforms

Rise of Big Data techniques has led to the requirement for low latency analysis of high-velocity continuous data streams in real time. Several solutions, including Stream Processing Systems (SPSs), have been developed to enable real-time distributed stream processing. However, emerging application scenarios such as smart cities and wearable assistance that involve highly variable data rates keep on posing new challenges to the established stream processing engines for maintaining cost-effective executions. To cater to such scenarios, many modern SPSs have been proposed that leverage Cloud environment. The run-time scalability incorporated in these SPSs is in their early adaptations and are based on fixed scale sizes. Moreover, these scaling approaches do not adequately consider both the structure of the hosted streaming applications and the characteristic features of the underlying Cloud environment. Achieving true cost benefits of orchestrating streaming applications on Cloud-based pay-as-you-go model while maintaining the desired QoS, necessitates that both these issues are accounted in making the scaling decisions. This work presents a heterogeneity-aware, efficient auto-scaling strategy StreamScale-H which addresses both these issues. Simulation experiments, on representative stream applications, indicate that the proposed StreamScale-H auto-scaling algorithm exhibits much better performance in comparison with the state-of-the-art algorithms.

Quantitative Modeling and Analytical Calculation of Elasticity in Cloud Computing

Elasticity is a fundamental feature of cloud computing and can be considered as a great advantage and a key benefit of cloud computing. One key challenge in cloud elasticity is lack of consensus on a quantifiable, measurable, observable, and calculable definition of elasticity and systematic approaches to modeling, quantifying, analyzing, and predicting elasticity. Another key challenge in cloud computing is lack of effective ways for prediction and optimization of performance and cost in an elastic cloud platform. The present paper makes the following significant contributions. First, we present a new, quantitative, and formal definition of elasticity in cloud computing, i.e., the probability that the computing resources provided by a cloud platform match the current workload. Our definition is applicable to any cloud platform and can be easily measured and monitored. Furthermore, we develop an analytical model to study elasticity by treating a cloud platform as a queueing system, and use a continuous-time Markov chain (CTMC) model to precisely calculate the elasticity value of a cloud platform by using an analytical and numerical method based on just a few parameters, namely, the task arrival rate, the service rate, the virtual machine start-up and shut-down rates. In addition, we formally define auto-scaling schemes and point out that our model and method can be easily extended to handle arbitrarily sophisticated scaling schemes. Second, we apply our model and method to predict many other important properties of an elastic cloud computing system, such as average task response time, throughput, quality of service, average number of VMs, average number of busy VMs, utilization, cost, cost-performance ratio, productivity, and scalability. In fact, from a cloud consumer's point of view, these performance and cost metrics are even more important than the elasticity metric. Our study in this paper has two significance. On one hand, a cloud service provider can predict its performance and cost guarantee using the results developed in this paper. On the other hand, a cloud service provider can optimize its elastic scaling scheme to deliver the best cost-performance ratio. To the best of our knowledge, this is the first paper that analytically and comprehensively studies elasticity, performance, and cost in cloud computing. Our model and method significantly contribute to the understanding of cloud elasticity and management of elastic cloud computing systems.

A proactive auto-scaling scheme with latency guarantees for multi-tenant NFV cloud

Network Functions Virtualization (NFV) is a promising technology to provide packet processing services. However, dynamic capacity provisioning to meet different tenants’ time-varying demands under service-level agreements is still a challenge for NFV service providers. The existing works generally perform the scaling-in/out actions for separate service chains and cannot promise a guarantee for the total processing time. Therefore, we propose Palm, a proactive auto-scaling framework to minimize the resource consumption while enforcing latency guarantees for multiple intersecting service chains. We first leverage the classed Jackson network model to analyze the packet processing latency. Then, a log-linear Poisson auto-regression method is employed to predict each tenant’s packet arrival rate. Based on the prediction result, we perform the capacity adjustment actions and update the flow forwarding policies. We formulate the capacity provisioning task as a nonlinear integer programming problem and propose an evolution based algorithm to tackle it. To simplify the auto-scaling problem, we develop an adaptive algorithm to divide the NFV cloud into persistent and temporary layers. Our comprehensive experiments show that Palm achieves a steady low-latency performance at a lower cost compared with the state-of-the-art dynamic scaling strategies.

Research on Resource Prediction Model Based on Kubernetes Container Auto-scaling Technology

Cloud computing provides a new way for computing resource acquisition and brings about changes in software development deployment. Docker is a lightweight alternative technology of virtualization, which is simple, convenient and practical when developing and deploying applications. Kubernetes is an open source container management system based on Docker container technology. This paper studies the existing auto-scaling strategy of Kubernetes and proposes an auto-scaling optimization strategy which can solve the response delay problem in the expansion phase. This strategy uses a combination of empirical modal decomposition and ARIMA models to predict the load of Pods and adjust the number of Pods in advance according to the prediction result. Our experiment proves that the strategy can achieve the purpose of capacity expansion before the peak load and reduce the application request response time.

A Lightweight Autoscaling Mechanism for Fog Computing in Industrial Applications

Fog computing provides a more flexible service environment than cloud computing. The lightweight fog environment is suitable for industrial applications. In order to strengthen service scalability, container virtualization has been proposed and studied in recent years. It is vital to explore the tradeoff between service scalability and operating expenses. This paper integrates the hypervisor technique with container virtualization, and constructs an integrated virtualization (IV) fog platform for deploying industrial applications based on the virtual network function. This paper presents a fuzzy-based real-time autoscaling (FRAS) mechanism and implements it in the IV fog platform. The FRAS mechanism provides a dynamic, rapid, lightweight, and low-cost solution to the service autoscaling problem. Experimental results showed that the proposed FRAS mechanism yields a better service scale with lower average delay, error rate, and operating expenses compared to other autoscaling schemes.

Modifying CloudSim to accurately simulate interactive services for cloud autoscaling

SummaryWe study the problem of autoscaling in cloud deployments and issues related to autoscaling strategies and their formal evaluation. With this goal, we propose modifications of the CloudAnalyst distribution of CloudSim for improved autoscaler simulations. We extend the CloudSim platform with virtual machine addition/removal at simulation run time as well as more granular load reporting and implement a simple autoscaler simulation. We point out and fix multiple problems in CloudSim job duration computation methods and make it consistent with both theory and reality, improving the relative errors of simulation from as high as 333% to single‐figure percentages. Our main contribution is a formally evaluated autoscaling strategy and improved version of CloudAnalyst capable of realistic evaluations.

Modeling Deployment Decisions for Elastic Services with ABS

The use of cloud technology can offer significant savings for the deployment of services, provided that the service is able to make efficient use of the available virtual resources to meet service-level requirements. To avoid software designs that scale poorly, it is important to make deployment decisions for the service at design time, early in the development of the service itself. ABS offers a formal, model-based approach which integrates the design of services with the modeling of deployment decisions. In this paper, we illustrate the main concepts of this approach by modeling a scalable pool of workers with an auto-scaling strategy and by using the model to compare deployment decisions with respect to client traffic with peak loads.

Efficient auto-scaling scheme for rapid storage service using many-core of desktop storage virtualization based on IoT

Following the progressive development of IT technology, on-premise IT resources have been shifted to cloud computing environments. The principle reason for this change in IT resource-composing environments is that cloud computing services allow IT resources to be used as and when necessary, which means without buying hardware equipment. For this reason, studies on diverse aspects are being conducted for better security, rapidity, availability, reliability, and elasticity of cloud computing. Among the virtualization technologies that are basic for cloud computing, desktop storage virtualization (DSV) is composed of distributed legacy desktop personal computers. In DSV environments, clustering by unavailable state time and auto-scaling for storage provision as requested by users are considered very important. In addition, deferred processing for analysis of desktop PC performance states in DSV environments to select an appropriate desktop PC is directly connected to the quality of service (QoS). Although diverse algorithms and schemes for clustering and auto-scaling have been developed to this end, they have limited performance or have been made without considering DSV environments. Consequently, large amounts of deferred processing time are required. In the present paper, an efficient auto-scaling scheme (EAS) is proposed that minimizes deferred processing time in Internet of Things (IoT) environments by using many-cores of the GPU for clustering and auto-scaling in DSV environments. The EAS provides higher QoS to storage users compared to the CPU by mapping the information of numerous distributed desktop PCs on individual threads of the GPU and processing the information in parallel.