Tim Verbelen

Cloudlets: bringing the cloud to the mobile user

Although mobile devices are gaining more and more capabilities (i.e. CPU power, memory, connectivity, ...), they still fall short to execute complex rich media and data analysis applications. Offloading to the cloud is not always a solution, because of the high WAN latencies, especially for applications with real-time constraints such as augmented reality. Therefore the cloud has to be moved closer to the mobile user in the form of cloudlets. Instead of moving a complete virtual machine from the cloud to the cloudlet, we propose a more fine grained cloudlet concept that manages applications on a component level. Cloudlets do not have to be fixed infrastructure close to the wireless access point, but can be formed in a dynamic way with any device in the LAN network with available resources. We present a cloudlet architecture together with a prototype implementation, showing the advantages and capabilities for a mobile real-time augmented reality application.

AIOLOS: Middleware for improving mobile application performance through cyber foraging

As the popularity of smartphones and tablets increases, the mobile platform is becoming a very important target for application developers. Despite recent advances in mobile hardware, most mobile devices fail to execute complex multimedia applications (such as image processing) with an acceptable level of user experience. Cyber foraging is a well-known computing technique to enhance the capabilities of mobile devices, where the mobile device offloads parts of the application to a nearby discovered server in the network. Although first introduced in 2001, cyber foraging is still not widely adopted in current smartphone platforms or applications. In this respect, two major challenges are to be tackled. First, a suitable adaptive decision engine is needed to determine the optimal offloading decision, that takes into account the potentially high and variable latency between the device and the server. Second, an integrated cyber foraging platform with sufficient support for application developers is not publicly available on popular mobile platforms such as Android. In this paper, we present AIOLOS, a mobile middleware framework for cyber foraging on the Android platform. AIOLOS uses an estimation model that takes into account server resources and network state to decide at runtime whether or not a method call should be offloaded. We also introduce developer tools to integrate the AIOLOS framework in the Android platform, enabling easy development of cyber foraging enabled applications. A prototype implementation is presented and evaluated in detail by means of both a chess application and a newly developed photo editor application.

Graph partitioning algorithms for optimizing software deployment in mobile cloud computing

As cloud computing is gaining popularity, an important question is how to optimally deploy software applications on the offered infrastructure in the cloud. Especially in the context of mobile computing where software components could be offloaded from the mobile device to the cloud, it is important to optimize the deployment, by minimizing the network usage. Therefore we have designed and evaluated graph partitioning algorithms that allocate software components to machines in the cloud while minimizing the required bandwidth. Contrary to the traditional graph partitioning problem our algorithms are not restricted to balanced partitions and take into account infrastructure heterogenity. To benchmark our algorithms we evaluated their performance and found they produce 10%-40% smaller graph cut sizes than METIS 4.0 for typical mobile computing scenarios. Highlights? Algorithms for partitioning software on the cloud are presented. ? KL-based algorithm allows fast partitioning for realtime use. ? Simulated annealing improves solution quality at the cost of computation capacity. ? Hybrid approach combines both. ? Comparison to METIS shows our algorithms find 10%-40% better graph cuts.

Dynamic deployment and quality adaptation for mobile augmented reality applications

Abstract: With the increasing popularity of smartphones and netbooks, more and more applications are developed for the mobile platform. Notwithstanding the recent advances in mobile hardware, most mobile devices still lack sufficient resources (e.g. CPU power and memory) to execute complex multimedia applications such as augmented reality. Application developers also have difficulties to cope with the changing device context (e.g. network connectivity and remaining battery life) and the many different hardware platforms and operating systems to run applications on. Therefore, we introduce the concept where the developer can provide different configurations of an application, each having different resource requirements and a different quality offered to the end user. The middleware framework presented in this paper will select and deploy the configuration offering the best quality possible for the current connectivity and available resources. As these change over time, the framework will dynamically adapt the configuration and deployment at runtime, enhancing the quality by offloading parts of the application when a remote server is discovered, or gracefully degrading the quality when the network connection is lost. Based on experimental results on the augmented reality use case the performance and effectiveness of our middleware has been characterized in different scenarios.

Adaptive deployment and configuration for mobile augmented reality in the cloudlet

Abstract Despite recent advances in mobile hardware, most mobile devices still fall short to execute complex multimedia applications with real-time requirements such as augmented reality (AR). Because offloading the application to the cloud is not always an option due to the high and often unpredictable WAN latencies, the concept of cloudlets has been introduced: nearby infrastructure offering virtual machines for remote execution. In this paper we present a cloudlet platform, providing two important contributions. First, the platform allows cloudlets to be formed in a dynamic way, including (fixed) virtualized infrastructure co-located with the wireless access point, as well as any device in the LAN network supporting the platform. The approach can also be extended towards the cloud, facilitating distribution of applications over three tiers (i.e., the device, the cloudlet and the cloud). Second, instead of moving a complete virtual machine to the cloudlet, we propose a more fine-grained approach, by managing and deploying applications on the component level. Application components are declared by the developer, together with their real-time constraints and configuration parameters. In order to meet these constraints and to optimize the user experience, the platform distributes these components among the cloudlet at runtime while also dynamically configuring parameters. An OSGi-based prototype implementation on the Android platform is highlighted and evaluated using a mobile AR use case, showing the need for a component-based approach for the cloudlet.

Mobile device power models for energy efficient dynamic offloading at runtime

Power models of mobile devices CPU, Wi-Fi, Display unit and memory access are presented.The Wi-Fi models clearly differentiate between Send, Receive, Idle and Tail States.AIOLOS dynamically makes offloading decision based on different parameters.Offloading is validated with computational and communication intensive use cases.Energy aware offloading reduces mobile device energy consumption up to 55%. Spectacular advances in hardware and software technologies have resulted in powerful mobile devices, equipped with advanced processing, storage and network capabilities. Therefore, using resource-intensive applications has become a commodity in many contexts. However, the rapid evolution in hardware and software capabilities has not been paralleled by a similar advance in battery technology. A potential avenue to cope with the device energy resource limitation is to offload computational tasks to cloud infrastructure in the network. In order to offload tasks in an energy-aware manner, we present a detailed model of mobile device energy consumption, addressing the main power consuming subsystems, including CPU, display unit, wireless network interface and memory. Applying this model allows to estimate the power consumed by the application when executed locally, remotely or hybridly (i.e. partly on the device and partly in the cloud infrastructure). Offloading parts of the application can subsequently be decided at runtime based on these energy consumption estimates, also taking into account the power consumed by the device-to-cloud communication over the wireless network. The dynamic offloading has been validated with computational and communication intensive applications. Results show that 18-55% energy gains on the mobile device can be achieved, depending on different conditions.

Vision: smart home control with head-mounted sensors for vision and brain activity

Today, an increasing number of household appliances is being connected to the Internet to form a smart home. Intelligent control algorithms in the cloud adapt the configuration of this Internet-of-Things to our daily routines and personal preferences. Frequently, there are unforeseen situations where the control algorithms will not capture the actual desired configuration. In these cases, the user must intervene in the control algorithms and manually adjust the connected objects setting. Browsing to the appropriate web service or launching the vendor-specific companion app for even a simple interaction like lowering the temperature setting is a tedious process. In this paper, we report on our early insights in building a mobile system that provides a common, intuitive interface to all actuators in the smart home. Using a head-mounted camera and a commercial Emotiv EEG neuro-headset, we let the user configure the IoT by merely looking at an object and performing a related facial expression. This way, users only need to look at an object and think about the desired action. We leverage on the home cloudlet for the compute-intensive signal processing for object detection.

Adaptive Online Deployment for Resource Constrained Mobile Smart Clients

Nowadays mobile devices are more and more used as a platform for applications. Contrary to prior generation handheld devices configured with a predefined set of applications, today leading edge devices provide a platform for flexible and customized application deployment. However, these applications have to deal with the limitations (e.g. CPU speed, memory) of these mobile devices and thus cannot handle complex tasks. In order to cope with the handheld limitations and the ever changing device context (e.g. network connections, remaining battery time, etc.) we present a middleware solution that dynamically offloads parts of the software to the most appropriate server. Without a priori knowledge of the application, the optimal deployment is calculated, that lowers the cpu usage at the mobile client, whilst keeping the used bandwidth minimal. The information needed to calculate this optimum is gathered on the fly from runtime information. Experimental results show that the proposed solution enables effective execution of complex applications in a constrained environment. Moreover, we demonstrate that the overhead from the middleware components is below 2%.

Mobile, Collaborative Augmented Reality Using Cloudlets

The evolution in mobile applications to support advanced interactivity and demanding multimedia features is still ongoing. Novel application concepts (e.g. mobile Augmented Reality (AR)) are however hindered by the inherently limited resources available on mobile platforms (not withstanding the dramatic performance increases of mobile hardware). Offloading resource intensive application components to the cloud, also known as ”cyber foraging”, has proven to be a valuable solution in a variety of scenarios. However, also for collaborative scenarios, in which data together with its processing are shared between multiple users, this offloading concept is highly promising. In this paper, we investigate the challenges posed by offloading collaborative mobile applications. We present a middleware platform capable of autonomously deploying software components to minimize average CPU load, while guaranteeing smooth collaboration. As a use case, we present and evaluate a collaborative AR application, offering interaction between users, the physical environment as well as with the virtual objects superimposed on this physical environment.

Discrete-event simulation for efficient and stable resource allocation in collaborative mobile cloudlets

Abstract The deployment of highly interactive, media-rich applications on mobile devices is hindered by the inherent limitations on compute power, memory and battery capacity of these hand-held platforms. The cloudlet concept, opportunistically offloading computation to nearby devices, has proven to be a viable solution in offering resource-intensive applications on mobile devices. In this paper, we propose to extend the cloudlet concept with collaborative scenarios, in which not only hardware resources for processing are shared between all cloudlet users, but also the data computed. In a cloudlet, the resource demand should be spread over all available cloudlet nodes. User mobility and fluctuations in wireless bandwidth will cause the optimal resource allocation to vary over time. The cloudlet middleware must continuously balance the performance gain of reallocating components with the operational costs in terms of user experience and management complexity. In this paper, we formulate this optimization problem based on a theoretical cloudlet model capturing the infrastructure, application structure and user behavior. In order to solve this problem, two heuristic allocation algorithms based on Steepest Descent (SD) and Simulated Annealing (SA) are described. Besides optimality of the found solution, it is also important to limit the number of reallocations at runtime. To evaluate the performance and stability of the algorithms, we propose a discrete-event model for cloudlet simulation. For multiple application scenarios, we observe that SD performs 4 times less reallocations than SA. By introducing hysteresis, the number of reallocations by SA can be nearly halved without any significant degradation of application performance.