Towards a Low Power Virtual Machine forWireless Sensor Network Motes

Abstract

Virtual Machines (VMs) have been proposed as an efficient programming model for Wireless Sensor Network (WSN) devices. However, the processing overhead required for VM execution has a significant impact on the power consumption and battery lifetime of these devices. This paper analyses the sources of power consumption in the Maté VM for WSNs. The paper proposes a generalised processor architecture allowing for hardware acceleration of VM execution. The paper proposes a number of hardware accelerators for Maté VM execution and assesses their effectiveness.

A self-adaptation framework for resource constrained miniature search and rescue robots

“…Unlike conventional virtual machines in wireless sensor networks [16] [17], whose interactions are assumed to be between an end-user and a single isolated node in a network and not among the nodes themselves, the Embedded Virtual Machine (EVM) provides an inter-node interaction that standardizes the programming interfaces and synchronizes connectivity between the heterogeneous categories of hardware platforms [10].…”

Performance Boost-Up by Using an Efficient Network Management Schemes in Wireless Sensor Network

“…Processing of Virtual Machine (VM) under wireless sensor networks environment has certain challenges of high power consumption and insufficient battery lifetime for execution on the wireless sensor network's nodes [14].…”

“…Proposed generalized processor architecture which allows hardware acceleration to reduce the power consumption for execution of Virtual Machine on WSN nodes [14]. This architecture, allows the accelerator to interfere in the execution of VM applications.…”

Hardware support for a wireless sensor network virtual machine

“…The design of our VM is based on Maté and the hardware accelerator consists of two modules: operand stack module and synchronization module. These two modules implement the operations of Maté that are identified as the major sources of the overhead for VM execution [6,10]. Figure 1 shows the architecture of the wireless sensor network processor with the proposed hardware accelerator for virtual machine.…”

“…This paper describes work carried out with the goal of developing a low power Maté compliant VM suitable for WSN motes. Previously, we have pointed out that two major sources of execution overhead in Maté are synchronization and stack-based operations [6]. In this paper, we describe the design of a hardware accelerator that reduces the execution overhead of Maté and compare the execution overhead of Maté in the original software implementation and the proposed hardware-assisted implementation.…”