Abstract—Cloud computing augments applications with easeof-access to the enormous resources on the Internet. Combined with mobile computing technologies, mobile applications can exploit the Cloud everywhere by statically distributing code segments or dynamically migrating running processes onto cloud services. Existing migration techniques are however too coarse-grained for mobile devices, so the overheads often offset the benefits of migration. To build a truly elastic mobile cloud computing infrastructure, we introduce eXCloud (eXtensible Cloud)–a middleware system with multi-level mobility support, ranging from as coarse as a VM instance to as fine as a runtime stack frame, and allows resources to be integrated and used dynamically. In eXCloud, a stack-on-demand (SOD) approach is used to support computation mobility throughout the mobile cloud environment. The approach is fully adaptive, goal-driven and transparent. By downward task migration, applications running on the cloud nodes can exploit or take control of special resources in mobile devices such as GPS and cameras. With a restorable MPI layer, task migrations of MPI parallel programs can happen between cloud nodes or be initiated from a mobile device. Our evaluation shows that SOD outperforms several existing migration mechanisms in terms of migration overhead and latency. All our techniques result in better resource utilization through task migrations among cloud nodes and mobile nodes. Keywords-stack-on-demand;mobile cloud;computation migration; cloud computing I.

Abstract—Mobile cloud computing allows mobile applications to use the enormous resources in the clouds. In order to seamlessly utilize the resources, it is common to migrate computation among mobile nodes and cloud nodes. Therefore, a highly portable and transparent migration approach is needed. In terms of portability, application-level migration with code instrumentation is the most portable approach. However, in the existing literature, this approach imposes significant runtime overhead, even when no migration takes place. Most of these works are for mobile agents, and migrations are to be invoked by the programs. Migration points are also restricted to certain locations where migration status is being polled. In this paper, we propose a Java bytecode transformation technique for realizing task migration without imposing significant overhead on normal execution. Asynchronous migration technique is used to allow migrations to take place virtually anywhere in the user codes, and the proposed Twin Method Hierarchy minimizes the overhead resulting from state-restoration codes in normal execution. We have implemented our approach in our middleware. The results show that our approach can allow lightweight computation migration at application level, achieve considerable speedups and utilize the cloud resources from mobile devices. Keywords-computation migration; migration technqiue; stack-on-demand I.

Abstract—A Virtual Private Cloud (VPC) is a secure collection of computing, storage and network resources spanning multiple sites over Wide Area Network (WAN). With VPC, computation and services are no longer restricted to a fixed site but can be relocated dynamically across geographical sites to improve manageability, performance and fault tolerance. We propose WAVNet, a layer 2 virtual private network (VPN) which supports virtual machine live migration over WAN to realize mobility of execution environment across multiple security domains. WAVNet adopts a UDP hole punching technique to achieve direct network connection between two Internet hosts without special router configuration. We evaluate our design in an emulated WAN with 64 hosts and also in a real WAN environment with 10 machines located at seven different sites across the Asia-Pacific region. The experimental results show that WAVNet not only achieves close-to-native host-tohost network bandwidth and latency, but also guarantees more effective VM live migration than existing solutions. I.