Man Lin

Embedded Software and Systems

Practical Controls embedded software team have experience in large multiprocessor designs through to small single low power embedded software devices. We are ISO9001 certified and have rigorous quality procedures for software development, change control, defect tracking and software verification. We follow agile development practices and are experienced in project managing large and complex developments. We have a history in safety critical software development which leads to robust product development.

Static Security Optimization for Real-Time Systems

An increasing number of real-time applications like railway signaling control systems and medical electronics systems require high quality of security to assure confidentiality and integrity of information. Therefore, it is desirable and essential to fulfill security requirements in security-critical real-time systems. This paper addresses the issue of optimizing quality of security in real-time systems. To meet the needs of a wide variety of security requirements imposed by real-time systems, a group-based security service model is used in which the security services are partitioned into several groups depending on security types. While services within the same security group provide the identical type of security service, the services in the group can achieve different quality of security. Security services from a number of groups can be combined to deliver better quality of security. In this study, we seamlessly integrate the group-based security model with a traditional real-time scheduling algorithm, namely earliest deadline first (EDF). Moreover, we design and develop a security-aware EDF schedulability test. Given a set of real-time tasks with chosen security services, our scheduling scheme aims at optimizing the combined security value of the selected services while guaranteeing the schedulability of the real-time tasks. We study two approaches to solve the security-aware optimization problem. Experimental results show that the combined security values are substantially higher than those achieved by alternatives for real-time tasks without violating real-time constraints.

Energy minimization with loop fusion and multi-functional-unit scheduling for multidimensional DSP

Energy saving is becoming one of the major design issues in processor architectures with multiple functional units (FUs). Nested loops are usually the most critical part in multimedia and high-performance DSP systems. There is a tradeoff between power saving and performance, such as timing constraint and code size requirement, of nested loops. This paper studies how to minimize the total energy while satisfying performance requirement for applications with multidimensional nested loops. An algorithm, energy minimization with loop fusion and FU schedule (EMLFS), is proposed. We first use retiming and partition to fuse nested loops. Then we use novel FU scheduling algorithms to maximize energy saving without sacrificing performance. The experimental results show that the average improvement on energy saving is significant by using our EMLFS algorithm.

TaskShadow: Toward Seamless Task Migration across Smart Environments

The OSGi-based platform TaskShadow supports seamless task migration across smart environments using a task-to-service mapping algorithm to semantically search for suitable low-level services that achieve high-level tasks.

Scheduling Co-Design for Reliability and Energy in Cyber-Physical Systems

Energy aware scheduling and reliability are both very critical for real-time cyber-physical system design. However, it has been shown that the transient faults of a system will increase when the processor runs at reduced speed to save energy consumption. In this paper, we study total energy and reliability scheduling co-design problem for real-time cyber-physical systems. Total energy refers the sum of static and dynamic energy. Our goal is to minimize total energy while guaranteeing reliability constraints. We approach the problem from two directions based on the two different ways of guaranteeing the reliability of the tasks. The first approach aims at guaranteeing reliability at least as high as that of without speed scaling by reserving recovery job for each scaled down task. Heuristics have been used to guide the speed scaling and shutdown techniques that are used to lower total energy consumption while guaranteeing the reliability. The second way to guarantee the reliability of the tasks is to satisfy a known minimum reliability constraint for the tasks. The minimum reliable speed guarantees the reliability level of tasks, and is used as a constraint in the energy minimization problem. Both static and dynamic co-design methods are explored. Experimental results show that our methods are effective.

Enhancing Battery Efficiency for Pervasive Health-Monitoring Systems Based on Electronic Textiles

Electronic textiles are regarded as one of the most important computation platforms for future computer-assisted health-monitoring applications. In these novel systems, multiple batteries are used in order to prolong their operational lifetime, which is a significant metric for system usability. However, due to the nonlinear features of batteries, computing systems with multiple batteries cannot achieve the same battery efficiency as those powered by a monolithic battery of equal capacity. In this paper, we propose an algorithm aiming to maximize battery efficiency globally for the computer-assisted health-care systems with multiple batteries. Based on an accurate analytical battery model, the concept of weighted battery fatigue degree is introduced and the novel battery-scheduling algorithm called predicted weighted fatigue degree least first (PWFDLF) is developed. Besides, we also discuss our attempts during search PWFDLF: a weighted round-robin (WRR) and a greedy algorithm achieving highest local battery efficiency, which reduces to the sequential discharging policy. Evaluation results show that a considerable improvement in battery efficiency can be obtained by PWFDLF under various battery configurations and current profiles compared to conventional sequential and WRR discharging policies.

Real-time scheduling with quality of security constraints

An increasing number of real-time applications such as aircraft control and medical electronics systems require high quality of security to assure confidentiality, authenticity and integrity of information. However, security requirements of real-time tasks were not adequately considered in most existing scheduling algorithms. This paper proposes a novel dynamic scheduling algorithm with security awareness for scheduling independent tasks in real-time systems. Extensive simulation experiments have been conducted to quantitatively evaluate the performance of our approach. Experimental results based on synthetic and real world traces show that compared with three baseline algorithms, the proposed algorithm can consistently improve overall system performance in terms of quality of security and guarantee ratio under a wide range of workload characteristics.

Infrastructure and Reliability Analysis of Electric Networks for E-Textiles

Electronic textiles (e-textiles), known as computational fabrics, offer an emerging platform for constructing ambient intelligent applications. Computational nodes in e-textiles are driven by batteries. Unlike wireless sensor networks, not each computational node in e-textiles has its own battery. Instead, many computational nodes in e-textiles share a battery. Existing e-textiles use one fixed battery to drive a fixed set of computation nodes (or power consuming electronic components). The fixed battery-component connection may result in electronic components stopping functioning and/or energy waste in batteries when link connection problems occur. In this paper, we propose a new infrastructure of the power networks for e-textiles: flexible power network (FPN). Under the FPN infrastructure, a power consuming node (PCN) is not just connected to one single fixed battery. Instead, it is connected to multiple batteries and can obtain power energy from one of the available battery nodes (BNs) with the help of a battery selector. The electrical features of battery selectors and overcurrent protectors that protect the batteries from wasting the charge when short-circuit faults occur are illustrated. Moreover, by modeling the number of fault occurrence at conductive wires and nodes stochastically, an evaluation algorithm is proposed to analyze the reliability of FPN and to compare the metrics of different design schemes under the perspective of both the BNs and the PCNs. Experimental results show that our FPN is more dependable than some common e-textile electric networks published before with the occurrence of short- and/or open-circuit faults.

Pervasive Service Bus: Smart SOA Infrastructure for Ambient Intelligence

Ambient intelligence (AmI) aims to make our everyday environments intelligent--that is, sensitive, adaptive, and responsive to the presence of people--in a transparent manner. Several challenges exist to building an efficient infrastructure for AmI, including interoperation of heterogeneous systems, intelligence for anticipatory user assistance, adaptability to dynamic environments for good user experience, and scalability to additional users and spaces. Here, the authors propose Pervasive Service Bus (PSB), a smart service-oriented architecture (SOA) framework for AmI spaces that models all computing activities as unified pervasive services. They present an online planning algorithm to adapt service flows to contexts and user tasks. PSB employs a sub-bus-based layout to maintain efficiency in large-scale service interactions. They also discuss their results in evaluating PSBs performance in a Smart Home testbed.

A parallel GNFS algorithm based on a reliable look-ahead block lanczos method for integer factorization

The Rivest-Shamir-Adleman (RSA) algorithm is a very popular and secure public key cryptosystem, but its security relies on the difficulty of factoring large integers. The General Number Field Sieve (GNFS) algorithm is currently the best known method for factoring large integers over 110 digits. Our previous work on the parallel GNFS algorithm, which integrated the Montgomerys block Lanczos method to solve large and sparse linear systems over GF(2), is less reliable. In this paper, we have successfully implemented and integrated the parallel General Number Field Sieve (GNFS) algorithm with the new look-ahead block Lanczos method for solving large and sparse linear systems generated by the GNFS algorithm. This new look-ahead block Lanczos method is based on the look-ahead technique, which is more reliable, avoiding the break-down of the algorithm due to the domain of GF(2). The algorithm can find more dependencies than Montgomerys block Lanczos method with less iterations. The detailed experimental results on a SUN cluster will be presented in this paper as well.