An official website of the United States government
Advances in virtualization technologies and edge computing have inspired a new paradigm for Internet-of-Things (IoT) application development. By breaking a monolithic application into loosely coupled microservices, great gain can be achieved in performance, flexibility and robustness. In this paper, we study the important problem of load balancing across IoT microservice instances. A key difficulty in this problem is the interdependencies among microservices: the load on a successor microservice instance directly depends on the load distributed from its predecessor microservice instances. We propose a graph-based model for describing the load dependencies among microservices. Based on the model, we first propose a basic formulation for load balancing, which can be solved optimally in polynomial time. The basic model neglects the quality-of-service (QoS) of the IoT application. We then propose a QoS-aware load balancing model, based on a novel abstraction that captures a realization of the application’s internal logic. The QoS-aware load balancing problem is NP-hard. We propose a fully polynomialtime approximation scheme for the QoS-aware problem. We show through simulation experiments that our proposed algorithm achieves enhanced QoS compared to heuristic solutions.
more »
« less
Application Provisioning in FOG Computing-enabled Internet-of-Things: A Network Perspective
The emergence of the Internet-of-Things (IoT) has inspired numerous new applications. However, due to the limited resources in current IoT infrastructures and the stringent quality-of-service requirements of the applications, providing computing and communication supports for the applications is becoming increasingly difficult. In this paper, we consider IoT applications that receive continuous data streams from multiple sources in the network, and study joint application placement and data routing to support all data streams with both bandwidth and delay guarantees. We formulate the application provisioning problem both for a single application and for multiple applications, with both cases proved to be NP-hard. For the case with a single application, we propose a fully polynomial-time approximation scheme. For the multi-application scenario, if the applications can be parallelized among multiple distributed instances, we propose a fully polynomial-time approximation scheme; for general non-parallelizable applications, we propose a randomized algorithm and analyze its performance. Simulations show that the proposed algorithms greatly improve the quality-of-service of the IoT applications compared to the heuristics.
more »
« less
- PAR ID:
- 10095999
- Date Published:
- Journal Name:
- IEEE INFOCOM'2018
- Page Range / eLocation ID:
- 783 to 791
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
5G services and applications explicitly reserve compute and network resources in today’s complex and dynamic infrastructure of multi-tiered computing and cellular networking to ensure application-specific service quality metrics, and the infrastructure providers charge the 5G services for the resources reserved. A static, one-time reservation of resources at service deployment typically results in extended periods of under-utilization of reserved resources during the lifetime of the service operation. This is due to a plethora of reasons like changes in content from the IoT sensors (for example, change in number of people in the field of view of a camera) or a change in the environmental conditions around the IoT sensors (for example, time of the day, rain or fog can affect data acquisition by sensors). Under-utilization of a specific resource like compute can also be due to temporary inadequate availability of another resource like the network bandwidth in a dynamic 5G infrastructure. We propose a novel Reinforcement Learning-based online method to dynamically adjust an application’s compute and network resource reservations to minimize under-utilization of requested resources, while ensuring acceptable service quality metrics. We observe that a complex application-specific coupling exists between the compute and network usage of an application. Our proposed method learns this coupling during the operation of the service, and dynamically modulates the compute and network resource requests to minimize under-utilization of reserved resources. Through experimental evaluation using real-world video analytics application, we show that our technique is able to capture complex compute-network coupling relationship in an online manner i.e. while the application is running, and dynamically adapts and saves up to 65% compute and 93% network resources on average (over multiple runs), without significantly impacting application accuracy.more » « less
-
null (Ed.)An increasing number of big data applications in various domains generate datasets continuously, which must be processed for various purposes in a timely manner. As one of the most popular streaming data processing systems, Spark Streaming applies a batch-based mechanism, which receives real-time input data streams and divides the data into multiple batches before passing them to Spark processing engine. As such, inappropriate system configurations including batch interval and executor count may lead to unstable states, hence undermining the capability and efficiency of real-time computing. Hence, determining suitable configurations is crucial to the performance of such systems. Many machine learning- and search-based algorithms have been proposed to provide configuration recommendations for streaming applications where input data streams are fed at a constant speed, which, however, is extremely rare in practice. Most real-life streaming applications process data streams arriving at a time-varying rate and hence require real-time system monitoring and continuous configuration adjustment, which still remains largely unexplored. We propose a novel streaming optimization scheme based on Simultaneous Perturbation Stochastic Approximation (SPSA), referred to as NoStop, which dynamically tunes system configurations to optimize real-time system performance with negligible overhead and proved convergence. The performance superiority of NoStop is illustrated by real-life experiments in comparison with Bayesian Optimization and Spark Back Pressure solutions. Extensive experimental results show that NoStop is able to keep track of the changing pattern of input data in real time and provide optimal configuration settings to achieve the best system performance. This optimization scheme could also be applied to other streaming data processing engines with tunable parameters.more » « less
-
Internet of Drones (IoD) employs drones as the internet of things (IoT) devices to provision applications such as traffic surveillance and object tracking. Data collection service is a typical application where multiple drones are deployed to collect information from the ground and send them to the IoT gateway for further processing. The performance of IoD networks is constrained by drones’ battery capacities, and hence we utilize both energy harvesting technologies and power control to address this limitation. Specifically, we optimize drones’ wireless transmission power at each time epoch in energy harvesting aided time-varying IoD networks for the data collection service with the objective to minimize the average system energy cost. We then formulate a Markov Decision Process (MDP) model to characterize the power control process in dynamic IoD networks, which is then solved by our proposed model-free deep actor-critic reinforcement learning algorithm. The performance of our algorithm is demonstrated via extensive simulations.more » « less
-
The emergence of Internet of Things (IoT) is participating to the increase of data-and energy-hungry applications. As connected devices do not yet offer enough capabilities for sustaining these applications, users perform computation offloading to the cloud. To avoid network bottlenecks and reduce the costs associated to data movement, edge cloud solutions have started being deployed, thus improving the Quality of Service. In this paper, we advocate for leveraging on-site renewable energy production in the different edge cloud nodes to green IoT systems while offering improved QoS compared to core cloud solutions. We propose an analytic model to decide whether to offload computation from the objects to the edge or to the core Cloud, depending on the renewable energy availability and the desired application QoS. This model is validated on our application use-case that deals with video stream analysis from vehicle cameras.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/INFOCOM.2018.8486269
