| 1. |
- Nguyen, Chanh Le Tan, 1985-, et al.
(författare)
-
Why Cloud Applications Are not Ready for the Edge (yet)
- 2019
-
Ingår i: Proceedings of the 4th ACM/IEEE Symposium on Edge Computing. - New York, NY, USA : IEEE. - 9781450367332 ; , s. 250-263
-
Konferensbidrag (övrigt vetenskapligt/konstnärligt)abstract
- Mobile Edge Clouds (MECs) are distributed platforms in which distant data-centers are complemented with computing and storage capacity located at the edge of the network. Their wide resource distribution enables MECs to fulfill the need of low latency and high bandwidth to offer an improved user experience.As modern cloud applications are increasingly architected as collections of small, independently deployable services, they can be flexibly deployed in various configurations that combines resources from both centralized datacenters and edge locations. In principle, such applications should therefore be well-placed to exploit the advantages of MECs so as to reduce service response times.In this paper, we quantify the benefits of deploying such cloud micro-service applications on MECs. Using two popular benchmarks, we show that, against conventional wisdom, end-to-end latency does not improve significantly even when most application services are deployed in the edge location. We developed a profiler to better understand this phenomenon, allowing us to develop recommendations for adapting applications to MECs. Further, by quantifying the gains of those recommendations, we show that the performance of an application can be made to reach the ideal scenario, in which the latency between an edge datacenter and a remote datacenter has no impact on the application performance.This work thus presents ways of adapting cloud-native applications to take advantage of MECs and provides guidance for developing MEC-native applications. We believe that both these elements are necessary to drive MEC adoption.
|
|
| 2. |
- Nguyen, Chanh Le Tan, 1985-
(författare)
-
Autonomous resource management for Mobile Edge Clouds
- 2019
-
Licentiatavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Mobile Edge Clouds (MECs) are platforms that complement today's centralized clouds by distributing computing and storage capacity across the edge of the network, in Edge Data Centers (EDCs) located in close proximity to end-users. They are particularly attractive because of their potential benefits for the delivery of bandwidth-hungry, latency-critical applications. However, the control of resource allocation and provisioning in MECs is challenging because of the heterogeneous distributed resource capacity of EDCs as well as the need for flexibility in application deployment and the dynamic nature of mobile users. To realize the potential of MECs, efficient resource management systems that can deal with these challenges must be designed and built.This thesis focuses on two problems. The first relates to the fact that it is unrealistic to expect MECs to become successful based solely on MEC-native applications. Thus, to spur the development of MECs, we investigated the benefits MECs can offer to non-MEC-native applications, i.e., applications not specifically engineered for MECs. One class of popular applications that may benefit strongly from deployment on MECs are cloud-native applications, particularly microservice-based applications with high deployment flexibility. We therefore quantified the performance of cloud-native applications deployed using resources from both cloud datacenters and edge locations. We also developed a network communication profiling tool to identify the aspects of these applications that reduce the benefits they derive from deployment on MECs, and proposed design improvements that would allow such applications to better exploit MECs' capabilities.The second problem examined in this thesis relates to the dynamic nature of resource demand in MECs. To overcome the challenges arising from this dynamicity, we make use of statistical time series models and machine learning techniques to develop two workload prediction models for EDCs that account for both user mobility and the correlation of workload changes among EDCs in close physical proximity.
|
|
| 3. |
- Nguyen, Chanh Le Tan, 1985-
(författare)
-
Location-aware resource allocation in mobile edge clouds
- 2021
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Over the last decade, cloud computing has realized the long-held dream of computing as a utility, in which computational and storage services are made available via the Internet to anyone at any time and from anywhere. This has transformed Information Technology (IT) and given rise to new ways of designing and purchasing hardware and software. However, the rapid development of the Internet of Things (IoTs) and mobile technology has brought a new wave of disruptive applications and services whose performance requirements are stretching the limits of current cloud computing systems and platforms. In particular, novel large scale mission-critical IoT systems and latency-intolerant applications strictly require very low latency and strong guarantees of privacy, and can generate massive amounts of data that are only of local interest. These requirements are not readily satisfied using modern application deployment strategies that rely on resources from distant large cloud datacenters because they easily cause network congestion and high latency in service delivery. This has provoked a paradigm shift leading to the emergence of new distributed computing infrastructures known as Mobile Edge Clouds (MECs) in which resource capabilities are widely distributed at the edge of the network, in close proximity to end-users. Experimental studies have validated and quantified many benefits of MECs, which include considerable improvements in response times and enormous reductions in ingress bandwidth demand. However, MECs must cope with several challenges not commonly encountered in traditional cloud systems, including user mobility, hardware heterogeneity, and considerable flexibility in terms of where computing capacity can be used. This makes it especially difficult to analyze, predict, and control resource usage and allocation so as to minimize cost and maximize performance while delivering the expected end-user Quality-of-Service (QoS). Realizing the potential of MECs will thus require the design and development of efficient resource allocation systems that take these factors into consideration. Since the introduction of the MEC concept, the performance benefits achieved by running MEC-native applications (i.e., applications engineered specifically for MECs) on MECs have been clearly demonstrated. However, the benefits of MECs for non-MEC-native applications (i.e., application not specifically engineered for MECs) are still questioned. This is a fundamental issue that must be explored because it will affect the incentives for service providers and application developers to invest in MECs. To spur the development of MECs, the first part of this thesis presents an extensive investigation of the benefits that MECs can offer to non-MEC-native applications. One class of non-MEC-native applications that could potentially benefit significantly from deployment on an MEC is cloud-native applications, particularly micro-service-based applications with high deployment flexibility. We therefore quantitatively compared the performance of cloud-native applications deployed using resources from cloud datacenters and edge locations. We then developed a network communication profiling tool to identify aspects of these applications that reduce the benefits derived from deployment on MECs, and proposed design improvements that would allow such applications to better exploit MECs' capabilities. The second part of this thesis addresses problems related to resource allocation in highly distributed MECs. First, to overcome challenges arising from the dynamic nature of resource demand in MECs, we used statistical time series models and machine learning techniques to develop two location-aware workload prediction models for EDCs that account for both user mobility and the correlation of workload changes among EDCs in close physical proximity. These models were then utilized to develop an elasticity controller for MECs. In essence, the controller helps MECs to perform resource allocation, i.e. to answer the intertwined questions of what and how many resources should be allocated and when and where they should be deployed.The third part of the thesis focuses on problems relating to the real-time placement of stateful applications on MECs. Specifically, it examines the questions of where to place applications so as to minimize total operating costs while delivering the required end-user QoS and whether the requested applications should be migrated to follow the user's movements. Such questions are easy to pose but intrinsically hard to answer due to the scale and complexity of MEC infrastructures and the stochastic nature of user mobility. To this end, we first thoroughly modeled the workloads, stateful applications, and infrastructures to be expected in MECs. We then formulated the various costs associated with operating applications, namely the resource cost, migration cost, and service quality degradation cost. Based on our model, we proposed two online application placement algorithms that take these factors into account to minimize the total cost of operating the application.The methods and algorithms proposed in this thesis were evaluated by implementing prototypes on simulated testbeds and conducting experiments using workloads based on real mobility traces. These evaluations showed that the proposed approaches outperformed alternative state-of-the-art approaches and could thus help improve the efficiency of resource allocation in MECs.
|
|
| 4. |
- Nguyen, Chanh Le Tan, 1985-, et al.
(författare)
-
State-aware application placement in mobile edge clouds
- 2024
-
Ingår i: Proceedings of the 14th International conference on cloud computing and services science. - : Science and Technology Publications. - 9789897587016 ; , s. 117-128
-
Konferensbidrag (refereegranskat)abstract
- Placing applications within Mobile Edge Clouds (MEC) poses challenges due to dynamic user mobility. Maintaining optimal Quality of Service may require frequent application migration in response to changing user locations, potentially leading to bandwidth wastage. This paper addresses application placement challenges in MEC environments by developing a comprehensive model covering workloads, applications, and MEC infrastructures. Following this, various costs associated with application operation, including resource utilization, migration overhead, and potential service quality degradation, are systematically formulated. An online application placement algorithm, App EDC Match, inspired by the Gale-Shapley matching algorithm, is introduced to optimize application placement considering these cost factors. Through experiments that employ real mobility traces to simulate workload dynamics, the results demonstrate that the proposed algorithm efficiently determines near-optimal application placements within Edge Data Centers. It achieves total operating costs within a narrow margin of 8% higher than the approximate global optimum attained by the offline precognition algorithm, which assumes access to future user locations. Additionally, the proposed placement algorithm effectively mitigates resource scarcity in MEC.
|
|
| 5. |
- Nguyen, Chanh, 1985-, et al.
(författare)
-
Multivariate LSTM-Based Location-Aware Workload Prediction for Edge Data Centers
- 2019
-
Ingår i: Proceedings, 19th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing. - : IEEE. - 9781728109121 - 9781728109138 ; , s. 341-350
-
Konferensbidrag (refereegranskat)abstract
- Mobile Edge Clouds (MECs) is a promising computing platform to overcome challenges for the success of bandwidth-hungry, latency-critical applications by distributing computing and storage capacity in the edge of the network as Edge Data Centers (EDCs) within the close vicinity of end-users. Due to the heterogeneous distributed resource capacity in EDCs, the application deployment flexibility coupled with the user mobility, MECs bring significant challenges to control resource allocation and provisioning. In order to develop a self-managed system for MECs which efficiently decides how much and when to activate scaling, where to place and migrate services, it is crucial to predict its workload characteristics, including variations over time and locality. To this end, we present a novel location-aware workload predictor for EDCs. Our approach leverages the correlation among workloads of EDCs in a close physical distance and applies multivariate Long Short-Term Memory network to achieve on-line workload predictions for each EDC. The experiments with two real mobility traces show that our proposed approach can achieve better prediction accuracy than a state-of-the art location-unaware method (up to 44%) and a location-aware method (up to 17%). Further, through an intensive performance measurement using various input shaking methods, we substantiate that the proposed approach achieves a reliable and consistent performance.
|
|
| 6. |
- Bermbach, David, et al.
(författare)
-
Message from the Technical Program Chairs: IC2E 2022
- 2022
-
Ingår i: Proceedings of the IEEE International Conference on Cloud Engineering. - : IEEE. - 2373-3845 .- 2694-0825. - 9781665491150 ; , s. x-x
-
Tidskriftsartikel (refereegranskat)abstract
- Welcome to the 10th International Conference on Cloud Engineering (IC2E-2021), sponsored by IEEE and held inperson in beautiful Pacific Grove, CA (near Monterrey, CA) - returning to the Bay Area of California for this 10th anniversary - the location where IC2E started over a decade ago! We are thrilled to be returning to a safe, yet inperson, event this year after being virtual last year due to the COVID-19 pandemic. We look forward to catching up with you, hearing about your latest cloud computing research, socializing in a beautiful setting, and meeting those of you new to IC2E.
|
|
| 7. |
- Camillo, Frédéric, et al.
(författare)
-
Resource Management Architecture for Fair Scheduling of Optional Computations
- 2013
-
Ingår i: 2013 Eighth International Conference on P2P, Parallel, Grid, Cloud and Internet Computing. - : IEEE Computer Society. ; , s. 113-120
-
Konferensbidrag (refereegranskat)abstract
- Most HPC platforms require users to submit a pre-determined number of computation requests (also called jobs). Unfortunately, this is cumbersome when some of the computations are optional, i.e., they are not critical, but their completion would improve results. For example, given a deadline, the number of requests to submit for a Monte Carlo experiment is difficult to choose. The more requests are completed, the better the results are, however, submitting too many might overload the platform. Conversely, submitting too few requests may leave resources unused and misses an opportunity to improve the results.This paper introduces and solves the problem of scheduling optional computations. An architecture which auto-tunes the number of requests is proposed, then implemented in the DIET GridRPC middleware. Real-life experiments show that several metrics are improved, such as user satisfaction, fairness and the number of completed requests. Moreover, the solution is shown to be scalable.
|
|
| 8. |
- Filieri, Antonio, et al.
(författare)
-
Control Strategies for Self-Adaptive Software Systems
- 2017
-
Ingår i: ACM Transactions on Autonomous and Adaptive Systems. - : Association for Computing Machinery (ACM). - 1556-4665 .- 1556-4703. ; 11:4
-
Tidskriftsartikel (refereegranskat)abstract
- The pervasiveness and growing complexity of software systems are challenging software engineering to design systems that can adapt their behavior to withstand unpredictable, uncertain, and continuously changing execution environments. Control theoretical adaptation mechanisms have received growing interest from the software engineering community in the last few years for their mathematical grounding, allowing formal guarantees on the behavior of the controlled systems. However, most of these mechanisms are tailored to specific applications and can hardly be generalized into broadly applicable software design and development processes.This article discusses a reference control design process, from goal identification to the verification and validation of the controlled system. A taxonomy of the main control strategies is introduced, analyzing their applicability to software adaptation for both functional and nonfunctional goals. A brief extract on how to deal with uncertainty complements the discussion. Finally, the article highlights a set of open challenges, both for the software engineering and the control theory research communities.
|
|
| 9. |
- Klein, Cristian, 1985-, et al.
(författare)
-
Brownout : Building More Robust Cloud Applications
- 2014
-
Ingår i: 36th International Conference on Software Engineering (ICSE 2014). - New York, NY, USA : ACM Digital Library. ; , s. 700-711
-
Konferensbidrag (refereegranskat)abstract
- Self-adaptation is a first class concern for cloud applications, which should be able to withstand diverse runtime changes. Variations are simultaneously happening both at the cloud infrastructure level - for example hardware failures - and at the user workload level - flash crowds. However, robustly withstanding extreme variability, requires costly hardware over-provisioning. In this paper, we introduce a self-adaptation programming paradigm called brownout. Using this paradigm, applications can be designed to robustly withstand unpredictable runtime variations, without over-provisioning. The paradigm is based on optional code that can be dynamically deactivated through decisions based on control theory. We modified two popular web application prototypes - RUBiS and RUBBoS - with less than 170 lines of code, to make them brownout-compliant. Experiments show that brownout self-adaptation dramatically improves the ability to withstand flash-crowds and hardware failures.
|
|
| 10. |
- Klein, Cristian, 1985-, et al.
(författare)
-
Improving Cloud Service Resilience using Brownout-Aware Load-Balancing
- 2014
-
Ingår i: 2014 IEEE 33rd International Symposium On Reliable Distributed Systems (SRDS). - : IEEE Computer Society. - 9781479955848 ; , s. 31-40, s. 31-40
-
Konferensbidrag (refereegranskat)abstract
- We focus on improving resilience of cloud services (e.g., e-commerce website), when correlated or cascading failures lead to computing capacity shortage. We study how to extend the classical cloud service architecture composed of a load-balancer and replicas with a recently proposed self-adaptive paradigm called brownout. Such services are able to reduce their capacity requirements by degrading user experience (e.g., disabling recommendations).Combining resilience with the brownout paradigm is to date an open practical problem. The issue is to ensure that replica self-adaptivity would not confuse the load-balancing algorithm, overloading replicas that are already struggling with capacity shortage. For example, load-balancing strategies based on response times are not able to decide which replicas should be selected, since the response times are already controlled by the brownout paradigm.In this paper we propose two novel brownout-aware load-balancing algorithms. To test their practical applicability, we extended the popular lighttpd web server and load-balancer, thus obtaining a production-ready implementation. Experimental evaluation shows that the approach enables cloud services to remain responsive despite cascading failures. Moreover, when compared to Shortest Queue First (SQF), believed to be near-optimal in the non-adaptive case, our algorithms improve user experience by 5%, with high statistical significance, while preserving response time predictability.
|
|
