Digital Library[ Search Result ]
Lightweight Vertical Autoscaling Method Using Taylor Series for Serverless Computing
http://doi.org/10.5626/JOK.2025.52.3.181
Serverless computing has become essential in modern IT infrastructure by utilizing autoscaling to reduce server management burdens, enabling developers to concentrate on service. However, as serverless environments now handle multiple requests per instance, the limitations of horizontal autoscaling have become more apparent. This underscores the increasing need for vertical autoscaling, which dynamically adjusts the resource allocations for each instance. Traditional vertical autoscaling methods, designed for long-running cloud applications, are not well-suited for serverless environments that require rapid response and short execution times. This paper introduces a lightweight vertical autoscaling method that employs Taylor series to enhance both resource efficiency and performance. Experiments with FunctionBench demonstrate that the proposed method reduces resource reservations and wasted resource slack compared to Vertical Pod Autoscaler (VPA) and Tiny Autoscaler, while also improving average and 99th-percentile tail latency. Specifically, when compared to VPA, resource reservations and slack decreased by 18.6% and 45%, respectively, while average and tail latency improved by 31.5% and 53.8%. Additionally, it exhibited the lowest overhead, confirming its effectiveness as a lightweight autoscaling solution.
Dovetail Usage Prediction Model for Resource-Efficient Virtual Machine Placement in Cloud Computing Environment
Hyeongbin Kang, Hyeon-Jin Yu, Jungbin Kim, Heeseok Jeong, Jae-Hyuck Shin, Seo-Young Noh
http://doi.org/10.5626/JOK.2023.50.12.1041
As IT services have migrated to the cloud, efficient resource management in cloud computing environments has become an important issue. Consequently, research has been conducted on virtual machine placement(VMP), which can increase resource efficiency without the need for additional equipment in data centers. This paper proposes the use of a usage prediction model as a method for selecting and deploying hosts suitable for virtual machine placement. The dovetail usage prediction model, which improves the shortcomings of the existing usage prediction models, measures indicators such as CPU, disk, and memory usage of virtual machines running on hosts and extracts features using a deep learning model by converting them into time series data. By utilizing this approach in virtual machine placement, hosts can be used efficiently while ensuring appropriate load balancing of the virtual machines.
Privacy-preserving Association Rule Mining Algorithm Based on FP-Growth in Cloud Computing Environment
JaeHwan Shin, Hyeong-Jin Kim, JaeWoo Chang, Young-Ho Song
http://doi.org/10.5626/JOK.2020.47.8.707
Recently, with the advancement of cloud computing technology, database owners can outsource their databases to the cloud for professional management of data at low cost. However, outsourcing the original database to the cloud server exposes sensitive information in the database, such as banking and medical treatment. In this paper, we propose a privacy-preserving association rule mining algorithm based on the FP-Growth in the cloud computing environment. To protect the sensitive information, the proposed algorithm encrypts the original data and the user"s queries with homomorphic encryption schemes that support specific operations on cipher-texts. To provide efficient query processing on cipher-texts, we propose a comparison operation protocol that compares ciphertexts without exposing the original data. Through the performance evaluation, the proposed algorithm shows approximately 68～123% performance improvement, compared to the existing algorithm.
A Prediction-based Dynamic Component Offloading Framework for Mobile Cloud Computing
http://doi.org/10.5626/JOK.2018.45.2.141
Nowadays, mobile computing has become a common computing paradigm that provides convenience to people’s daily life. More and more useful mobile applications’ appearance makes it possible for a user to manage personal schedule, enjoy entertainment, and do many useful activities. However, there are some inherent defects in a mobile device that battery constraints and bandwidth limitations. These drawbacks get a user into troubles when to run computationally intensive applications. As a remedy scheme, component offloading makes room for handling mentioned issues via migrating computationally intensive component to the cloud server. In this paper, we will present the predictive offloading method for efficient mobile cloud computing. At last, we will present experiment result for validating applicability and practicability of our proposal.
Efficient and Privacy-Preserving Near-Duplicate Detection in Cloud Computing
Changhee Hahn, Hyung June Shin, Junbeom Hur
http://doi.org/10.5626/JOK.2017.44.10.1112
As content providers further offload content-centric services to the cloud, data retrieval over the cloud typically results in many redundant items because there is a prevalent near-duplication of content on the Internet. Simply fetching all data from the cloud severely degrades efficiency in terms of resource utilization and bandwidth, and data can be encrypted by multiple content providers under different keys to preserve privacy. Thus, locating near-duplicate data in a privacy-preserving way is highly dependent on the ability to deduplicate redundant search results and returns best matches without decrypting data. To this end, we propose an efficient near-duplicate detection scheme for encrypted data in the cloud. Our scheme has the following benefits. First, a single query is enough to locate near-duplicate data even if they are encrypted under different keys of multiple content providers. Second, storage, computation and communication costs are alleviated compared to existing schemes, while achieving the same level of search accuracy. Third, scalability is significantly improved as a result of a novel and efficient two-round detection to locate near-duplicate candidates over large quantities of data in the cloud. An experimental analysis with real-world data demonstrates the applicability of the proposed scheme to a practical cloud system. Last, the proposed scheme is an average of 70.6% faster than an existing scheme.
Privacy-Preserving Self-Certified Public Auditing for Secure Cloud Storage
Mokryeon Baek, Dongmin Kim, Ik Rae Jeong
With a cloud storage service, data owners can easily access their outsourced data in cloud storage on different devices and at different locations, and can share their data with others. However, as the users no longer physically have possession of their outsourced data and the cloud still facing the existence of internal/external threats, the task of checking the data integrity is formidable. Over recent years, numerous schemes have been proposed to ensure data integrity in an untrusted cloud. However, the existing public auditing schemes use a third-party auditor(TPA) to execute high computation to check data integrity and may still face many security threats. In this paper, we first demonstrate that the scheme proposed by Zhang et al. is not secure against our two threat models, and then we propose a self-certified public auditing scheme to eliminate the security threats and guarantee a constant communication cost. Moreover, we prove the securities of our public auditing scheme under three security models.
Quality Metrics of Cloud Service Based on Cross-cutting and SLA Specification Mechanism
Youngmin An, Joonseok Park, Keunhyuk Yeom
Depending on the increase amongst various cloud services, the technology of the Cloud Service Broker (CSB) to find the most appropriate services to meet the needs of cloud service consumers has emerged. In order to advance for cloud services to be used through the CSB, it is important to ensure the quality level that meets the demands of consumers through a negotiation process based on the Service Level Agreement (SLA). However, quality metrics of cloud services are different from each other based on the measurement scale, which represents the quality level, and the calculation for each type of cloud services. Therefore, it is necessary to analyze the variability of the quality of cloud services and establish a SLA model for ensuring and improving the level of quality. In this paper, we analyze the quality metrics for the specific type of cloud services by applying the cross-cutting concept and propose a Virtual SLA (VSLA) meta-model.
Architecture of Virtual Cloud Bank for Mediating Cloud Services based on Cloud User Requirements
Joonseok Park, Youngmin An, Keunhyuk Yeom
The concept of Cloud Service Brokerage (CSB) has been introduced as a result of the expansion of the cloud-computing paradigm. Cloud services that provide similar functionality are registered with a CSB. A CSB intermediates cloud services between cloud users and providers. However, there are differences in the price and performance offered by each of the cloud providers. Thus, cloud users have difficulty in finding suitable services to use. Therefore, a CSB is required in order to provide an approach for cloud services to fulfill the requirements of cloud users. In this paper, we propose a virtual cloud bank architecture that includes both a Service Analysis Model (SAM) that can be used to specify and analyze various cloud services and a requirement analysis method that can be used to collect and analyze the cloud user requirements. The VCB architecture that is herein proposed can be used as a reference architecture to provide user-centric cloud services.
A Function Level Static Offloading Scheme for Saving Energy of Mobile Devices in Mobile Cloud Computing
Hong Min, Jinman Jung, Junyoung Heo
Mobile cloud computing is a technology that uses cloud services to overcome resource constrains of a mobile device, and it applies the computation offloading scheme to transfer a portion of a task which should be executed from a mobile device to the cloud. If the communication cost of the computation offloading is less than the computation cost of a mobile device, the mobile device commits a certain task to the cloud. The previous cost analysis models, which were used for separating functions running on a mobile device and functions transferring to the cloud, only considered the amount of data transfer and response time as the offloading cost. In this paper, we proposed a new task partitioning scheme that considers the frequency of function calls and data synchronization, during the cost estimation of the computation offloading. We also verified the energy efficiency of the proposed scheme by using experimental results.
Service Level Agreement Specification Model of Software and Its Mediation Mechanism for Cloud Service Broker
SLA (Service Level Agreement) is an essential factor that must be guaranteed to provide a reliable and consistent service to user in cloud computing environment. Especially, a contract between user and service provider with SLA is important in an environment using a cloud service brokerage. The cloud computing is classified into IaaS, PaaS, and SaaS according to IT resources of the various cloud service. The existing SLA is difficult to reflect the quality factors of service, because it only considers factors about the physical Network environment and have no methodological approach. In this paper, we suggested a method to specify the quality characteristics of software and proposed a mechanism and structure that can exchange SLA specification between the service provider and consumer. We defined a meta-model for the SLA specification in the SaaS level, and quality requirements of the SaaS were described by the proposed specification language. Through case studies, we verified proposed specification language that can present a variety of software quality factors. By using the UDDI-based mediation process and architecture to interchange this specification, it is stored in the repository of quality specifications and exchanged during service binding time.
Search
Journal of KIISE
- ISSN : 2383-630X(Print)
- ISSN : 2383-6296(Electronic)
- KCI Accredited Journal
Editorial Office
- Tel. +82-2-588-9240
- Fax. +82-2-521-1352
- E-mail. chwoo@kiise.or.kr