Novel, Emerging Computing System Technologies Lab - NECST Lab -
http://necst.it/

Activities

The NECST Lab (Novel, Emerging Computing System Technologies Laboratory) comprises a number of different research lines on advanced topics in computing systems, ranging from architectural characteristics, to hardware-software codesign methodologies, to security and dependability issues of complex system architectures (scaling from mobile devices to large virtualized datacenters). Furthermore, the laboratory pursues its “historical” tradition of research in the definition of methodologies and techniques regarding testability, auto-diagnosis and fault tolerance both for hardware architectures and hardware-software systems. Some representative research topics are:

  • Design methodologies for the architectures of digital embedded systems
    This research focuses on the definition of architectures of embedded systems with processors and bus guaranteeing low power consumption and high performances, and of specific architectures for classification and elaboration of signals and for image processing. The definition of methodologies and software frameworks supporting the development of hardware-software system for embedded applications, in the telecommunication, automotive, industrial and consumer fields, characterizes the methodological activities.
Sspecial attention is devoted to the methodologies for developing multiprocessors systems on a single chip (also known as Multiprocessor System on Chip, or MPSoC), studying methodologies to model, simulate, design and optimize those architectures, both in terms of performances and power consumption.

  • Systems security
    We focus on applied computer security techniques, with a broad range of interests. We mainly focus on malware and threat analysis, ranging from automated reverse engineering of malware samples to the study of the emerging threats (in the social network space, on mobile devices, in the cloud, in cyber-physical systems...). We have a deep interest in real-world attack scenarios and practical defenses. Moreover, we still develop our traditional research area of anomaly-based intrusion detection, applying that know how to modern, emerging scenarios (such as the cloud), and applying key concepts to different domains (such as the protection of mobile devices)

  • Reconfigurable computing

    Reconfigurable architectures are another interesting field of application, both in terms of hardware systems and of multiprocessors platforms, to which software components of the application are added. The study of these systems deals not only with the design and development of novel architectures for such systems, but also on the definition of new methodologies able to take into account the reconfigurability, be it external/internal, static/dynamic and partial/total, in the different design phases of embedded systems. Software infrastructure are available, that were developed in the laboratory, providing the basis for the development of new tools supporting the designer of embedded systems.


  • Operating Systems and self-aware computing technologies
    Self-Aware computing is a research area aimed at leveraging the new balance of resources to improve performance, utilization, reliability and programmability, overcoming the burden imposed by the increasing complexity and the associated workload of modern computing systems. Imagine a revolutionary computing system that can observe its own execution and optimize its behavior with respect to the external environment, the user desiderata and the applications demands. In this area we want to address the main challenges on the way to such a vision, that are: (i) to define methods and tools to let users and developers to specify and formulate desired behaviors; (ii) to add self-awareness capabilities to digital devices, granting them the ability to measure the gap between the specified goals and the actual behavior; (iii) to define, analyze and implement operating systems components and hardware computing architecture elements that will allow devices to modify their behavior towards the specified goals.

  • Mobile technologies in smart environments
    Mobile devices, due to their wide distribution and to their increasing smartness and availability of computational power, can become the interaction point between users and their surrounding environments. However, current mobile devices OSes lack of the ability to anticipate and overcome internal and external changes. Integrating mechanisms of self-awareness and self-adaptability in nowadays smartphones is an attractive perspective to match with these requirements. Moreover, adaptive behaviors can enhance the management by the mobile device itself, of the available resources at its best, e.g., the battery life. This research area envisions various situations in which a self-aware mobile device can interact with the surrounding environment and support the user in performing everyday actions.

  • Cryptographic architectures
    We study efficient and secure cryptographic architectures, ranging from the hardware-software codesign for encryption algorithms to the evaluation of their resilience against hardware-based attacks (such as power or fault analysis).

  • Performance evaluation
    We are interested in performance evaluation and design of high performance computing systems. The analysis is performed by means of measurements tools and mathematical models based on queuing networks and operational research. Current interest areas are, specifically, the performance models of virtualized systems and cloud computing.

  • IP television and video-on-demand
    An application area (which is interesting due to several high-profile industrial links) in which performance evaluation and capacity planning meet a broad set of intelligent systems and algorithms for recommendations on video content.

  • Design methodologies wireless sensor networks and RFId
    This research revolves around the methodological, real life application and implementation related aspects of passive RFId technologies and of the wireless sensors networks. Passive RFId technologies with sensorial potentialities (SRFId) and of elaboration (SPRFId) are studied both at methodological (ex. auto-localization issues, power consumption) and applicative levels. In the field of sensory wireless nets, research focuses on energetic supply (ex. solar panels) and the integration of ad-hoc sensors on hardware platforms, on the auto localization of the net’s nodes in indoor and outdoor environments, on the restart mechanisms of the functionalities of the cold and hot plugs of the nodes, and eventually on the definition of routing algorithms multihop power and location aware. The methodologies and the embedded systems are aimed both at the industrial world and at applications for personal and public security.















Fig. 1 and 2. Boards for the creation of reconfigurable embedded systems and of MPSoC
Fig. 3. JTST card, JigTeST for Diopsis740, for the study of heterogeneous multiprocessors systems DSP-ARM
Fig. 4. The probe developed to estimate the state of snow (avalanche prediction)
Fig. 5. Embedded System for estimating the care needs in patients

Fig. 1 and 2. copyright © Ing. Giorgio Uccellini 2009

Research Lines

Information service


The laboratory is located at the DEIB (Department of Electronics, Information and Bioengineering), building 20, via Ponzio, 34/5.
Entrance is allowed during the department’s opening hours.
Part of this laboratory is located at the Lecco campus of Politecnico; for specific instrumentation, it makes use of the Mechanical and Thermal Measures laboratory.
More information is available on the website: http://sagroup.elet.polimi.it