Cheolgi Kim

A framework for the safe interoperability of medical devices in the presence of network failures

There exists a growing need for automated interoperability among medical devices in modern healthcare systems. This requirement is not just for convenience, but to prevent the possibility of errors due to the complexity of interactions between the devices and human operators. Hence, a system supporting such interoperability is supposed to provide the means to interconnect distributed medial devices in an open space, so must be designed to account for network failures. In this paper, we introduce a generic framework, the Network-Aware Supervisory System (NASS) to integrate medical devices into such a clinical interoperability system that uses real networks. It provides a development environment, in which medical-device supervisory logic can be developed based on the assumptions of an ideal, robust network. A case study shows that the NASS framework provides the same procedural effectiveness as the original logic based on the ideal network model but with protection against real-world network failures.

System-wide energy optimization for multiple DVS components and real-time tasks

Most dynamic voltage and frequency scaling (DVS) techniques adjust only CPU parameters; however, recent embedded systems provide multiple adjustable clocks which can be independently tuned. When considering multiple components, energy optimal frequencies depend on task set characteristics such as the number of CPU and memory access cycles. In this work, we propose a realistic energy model considering multiple components with individually adjustable frequencies such as CPUs, system bus and memory, and related task set characteristics. The model is validated on a real platform and shows less than 2% relative error compared to measured values. Based on the proposed energy model, we present an optimal static frequency assignment scheme for multiple DVS components to schedule a set of periodic real-time tasks. We simulate the energy gain of the proposed scheme compared to other DVS schemes for various task and system configurations, showing up to a 20% energy reduction. We also experimentally verify energy savings of the proposed scheme on a real hardware platform.

Efficient multicasting for multi-channel multi-interface wireless mesh networks

Multicasting can be an useful service in wireless mesh networks (WMNs), which have gained significant acceptance in recent years due to their potentials of providing a low-cost wireless backhaul service to mobile clients. Many applications in WMNs require efficient and reliable multicast communication, i.e., with high delivery ratio but with less overhead, among a group of recipients. However, in spite of its significance, there has been little work on providing such a multicast service in multi-channel mesh networks. Traditional multicasting protocols for wireless multi-hop networks mostly assume that all nodes (equipped with a single interface) collaborate on the same channel. The single-channel assumption is not always true for WMNs that often provide the nodes with multiple interfaces for the purpose of substantial performance enhancement. In multi-channel/interface mesh environments, the same multicast data needs to be sent multiple times by a sender node if its neighboring nodes operate on different channels. In this paper, we try to tackle this challenging issue of how to design a multicast protocol more suitable for multi-interface and multi-channel WMNs. Our multicasting protocol builds multicast paths while inviting multicast members, and allocates the same channel to each of neighboring members in a bottom up manner. This mechanism can reduce message overheads and delivery delays while guaranteeing successful message deliveries. For the performance evaluation, we have implemented the proposed scheme on a multi-channel/interface mesh network test-bed with two IEEE 802.11a cards per node.

Link-state routing protocol for multi-channel multi-interface wireless networks

A lot of military networks maintain multiple wireless channels and exploit frequency-hopping spread spectrum on those channels for anti-jamming. One drawback of using multichannel communications is the high overhead involved in broadcast operations: a transmitter should transmit a broadcast packet to all channels that are possibly occupied by a receiver. This makes certain broadcast-intensive mechanisms, such as, link-state routing difficult to implement. Link-state routing, however is faster and robust, which makes it suitable for military applications. In this paper, we present a link-state routing protocol tailored for multichannel networks by minimizing the broadcast overheads. This is achieved by means of a special set of nodes called cluster-heads. We have implemented our protocol on a multichannel, multiinterface wireless test bed and have compared its performance with an AODV-like reactive routing protocol, which is also tailored for multichannel multiinterface networks. The measurements on our test bed show that the proposed link-state routing protocol provides transient communications in a comparable or better performance.

Design and implementation of multicasting for multi-channel multi-interface wireless mesh networks

Multicasting is a useful communication method in wireless mesh networks (WMNs). Many applications in WMNs require efficient and reliable multicast communications, i.e., high delivery ratio with low overhead among a group of recipients. In spite of its significance, little work has been done on providing such multicast service in multi-channel WMNs. Traditional multicast protocols for wireless and multi-hop networks tend to assume that all nodes, each of which is equipped with a single interface, collaborate on the same channel. This single-channel assumption is not always true, as WMNs often provide nodes with multiple interfaces to enhance performance. In multi-channel and multi-interface (MCMI) WMNs, the same multicast data must be sent multiple times by a sender node if its neighboring nodes operate on different channels. In this paper, we try to tackle the challenging issue of how to design a multicast protocol more suitable for MCMI WMNs. Our multicast protocol builds multicast paths while inviting multicast members, and tries to allocate the same channel to neighboring members in a bottom-up manner. By unifying fixed channels of one-hop multicast neighbors, the proposed algorithm can improve the performance such as reducing multicast data transmission overhead and delay, while managing a successful delivery ratio. In order to prove such expectation on the performance, we have implemented and evaluated the proposed solution on the real testbed having the maximum 24 nodes, each of which is equipped with two IEEE 802.11a Atheros WLAN cards.

System-Wide Energy Optimization for Multiple DVS Components and Real-Time Tasks

Most dynamic voltage and frequency scaling (DVS) techniques adjust only CPU parameters, however, recent embedded systems provide multiple adjustable clocks which can be independently tuned. When considering multiple components, energy optimal frequencies depend on task set characteristics such as the number of CPU and memory access cycles. In this work, we propose a realistic energy model considering multiple components with individually adjustable frequencies such as CPU, system bus and memory, and related task set characteristics. The model is validated on a real platform and shows less than 2% relative error compared to measured values. Based on the proposed energy model, we present an optimal static frequency assignment scheme for multiple DVS components to schedule a set of periodic realtime tasks. We simulate the energy gain of the proposed scheme compared to other DVS schemes for various task and system configurations, showing up to a 20% energy reduction.

Exploring the design space of IMA system architectures

In systems such as integrated modular avionics (IMA), there is a substantial benefit from maintaining significant portions of a product familys architecture unchanged from one system to the next. When there are tight constraints on resources such as bandwidth and processor capacity, however, certain seemingly small changes in a few components have the potential to create a cascade of timing problems. The ability to rapidly analyze and quantify the impact of these changes prior to implementation and system integration provides the engineering team with early validation of the changes, which can prevent substantially increased costs for design, integration, and verification, as well as delays in the development schedule. However, detailed early evaluation of architecture performance involves analysis of many complex interrelated variables and is therefore challenging. Consider the case of moving a task from a processors IMA partition to another processors partition. The tasks sets need to be updated. The I/O and network traffic must be rerouted. The schedulability equations of processor, I/O and network need to be recreated, and the analysis needs to be propagated end to end. Last but not least, all the architecture specification documents have to be updated. In order to reduce the detailed architecture evaluation effort, we have automated the performance analysis process with a system integration tool prototype called ASIIST (Application-Specific I/O Integration Support Tool). To move a task, we can now use a graphical interface to drag and drop a task from one processors IMA partition to another. All the steps described above are done automatically, including the updating of the architecture specification in AADL (Architecture Analysis and Description Language). In this paper, we show how to use this tool to explore the design space of an IMA system architecture, so as to derive designs with specified performance properties.

Middleware design for physically-asynchronous logically-synchronous (PALS) systems

The Physically-Asynchronous Logically-Synchronous (PALS) system is a recently proposed architectural pattern for cyber-physical systems. It guarantees a logically synchronous design abstraction for real-time distributed computations. In this work, we develop a new middleware, called PALSware, to support an efficient and robust implementation of the PALS system and its extensions. PALSware guarantees consistency in distributed applications by eliminating any asynchronous interactions resulting from distributed clocks and node failures. We present a layered design for this middle-ware that is both reusable in different system architectures and can be extended with architecture-specific solutions for fault management. We demonstrate the middleware for an academic control testbed and show the consistency in a fault injection framework designed for this middleware.

How to reliably integrate medical devices over wireless

This demonstration presents our NASS (Network Aware Supervisory System) framework prototype for medical device integration systems. The NASS framework interconnects medical devices over wireless for convenience, seamlessness and sanitation, and provides safety-guaranteed supervision. Our prototype was developed in Sun Java Real-time Environment. Real-time Java provides well-formed convenience of dynamically loading and unloading medical application logic and safety rules on the fly in real-time environments. To tackle the complexity of using real-time Java in the safety-critical system, we also applied HW/SW codesign method. Real-time Java Environment + Linux operating system may not be robust enough for medical devices to fully rely on. In our prototype, the supervisor software in Java performs all logical decisions including contingency plan generation derived from the safety rules. Once logic is decided, the decisions and plans for the devices are delivered to the hardware implemented in FPGA at each device to physically drive medical equipments. Since the execution of decisions and plans are delegated to the hardware, any failure in software does not harm the integrated safety. Our demonstration shows how safety is managed in different kinds of failures from wireless network failures to device software failures.

A reduced complexity design pattern for distributed hierarchical command and control system

Cyber Physical Systems (CPS) get a lot of attention due to the strong demand for the integration of physical devices and computing systems. There are many design aspects involved in CPS, such as efficiency, real-time, reliability and security. One of the major issues is system integration and verification. In many safety critical systems verification plays an essential role in system design. However, the high complexity for the composition of diverse systems is a major challenge for system verification. In this paper, we focus on command and control systems for search and rescue missions and propose a systematic design pattern called Interruptible RPC to compose complex systems while keeping the verification costs low. This has been made possible due to the reduced state space of the systems designed using our pattern. Therefore, the system models can be efficiently verified using available verification tools. In our experiments, the search and rescue system based on Interruptible RPC pattern had fewer states than the asynchronous one by several orders of magnitude.