Mark J. Stanovich

Defects of the POSIX Sporadic Server and How to Correct Them

The specification of the sporadic server real-time scheduling policy in the IEEE POSIX standard is defective, and needs to be corrected. Via experiments using a POSIX sporadic server implementation under Linux, as well as simulations, we have shown and confirmed previously unreported defects. We propose and demonstrate a corrected sporadic server formulation that eliminates these defects without changes to the syntax of the API or any significant increase in implementation complexity.

Development of a smart-grid cyber-physical systems testbed

Emerging future smart grids will substantially increase the sophistication and diversity of control, communications, and power systems technologies. While many of these technologies are well established in their particular area, the interactions that result when combining them into a fully functioning cyber-physical system can result in many unexpected behaviors. Therefore, appropriate test platforms will become necessary to evaluate the performance of these systems in order to reveal unintended and potentially harmful interactions between subsystems before deploying such technologies in the field. In this paper, we discuss the design and development of a testbed to evaluate various smart-grid based control technologies through the use of controller hardware-in-the-Ioop real-time simulation. In particular, the focus of this testbed is to examine various “intelligent” and distributed control algorithms. The relevance of the testbed is illustrated through a case-study of a smart-grid solution known as the Distributed Grid Intelligence (DGI), which is part of the Future Renewable Electrical Energy Delivery and Management (FREEDM) project. In this case-study, we describe the impacts of various interactions such as communication timings, available computational resources, and distribution and decentralization of higher-level control on a microgrids operations. Based on the case study, this paper concludes with recommendations for future expansion and improvements to the test bed in order to better serve the smart grid research community.

Modeling Device Driver Effects in Real-Time Schedulability Analysis: Study of a Network Driver

Device drivers are integral components of operating systems. The computational workloads imposed by device drivers tend to be aperiodic and unpredictable because they are triggered in response to events that occur in the device, and may arbitrarily block or preempt other time-critical tasks. This characteristic poses significant challenges in real-time systems, where schedulability analysis is essential to guarantee system-wide timing constraints. At the same time, device driver workloads cannot be ignored. Demand-based schedulability analysis is a technique that has been successful in validating the timing constraints in both single and multiprocessor systems. In this paper we present two approaches to demand-based schedulability analysis of systems that include device drivers. First, we derive load-bound functions using empirical measurement techniques. Second, we modify the scheduling of network device driver tasks in Linux to implement an algorithm for which a load-bound function can be derived analytically. We demonstrate the practicality of our approach through detailed experiments with a network device under Linux. Our results show that, even though the network device driver does not conform to conventional periodic or sporadic task models, it can be successfully modeled using hyperbolic load-bound functions that are fitted to empirical performance measurements

TrueErase: per-file secure deletion for the storage data path

The ability to securely delete sensitive data from electronic storage is becoming important. However, current per-file deletion solutions tend to be limited to a segment of the operating systems storage data path or specific to particular file systems or storage media. This paper introduces TrueErase, a holistic secure-deletion framework. Through its design, implementation, verification, and evaluation, TrueErase shows that it is possible to build a legacy-compatible full-storage-data-path framework that performs per-file secure deletion and works with common file systems and solid-state storage, while handling common system failures. In addition, this framework can serve as a building block for encryption- and tainting-based secure-deletion systems.

Throttling On-Disk Schedulers to Meet Soft-Real-Time Requirements

Many contemporary disk drives have built-in queues and schedulers. These features can improve I/O performance, by offloading work from the systems main processor, avoiding disk idle time, and taking advantage of vendor-specific disk characteristics. At the same time, they pose challenges for scheduling requests that have real-time requirements, since the operating system has less visibility and control over service times. While it may be possible for an operating system to obtain more predictable real-time performance by bypassing the on-disk queue and scheduler, the diversity and continuing evolution of disk drives make it difficult to extract the necessary detailed timing characteristics of a specific disk, and to generalize that approach to all hard drives. This paper demonstrates three techniques we developed in the Linux operating system to bound real-time request response times for disks with internal queues and schedulers. The first technique is to use the disks built-in starvation prevention scheme. The second is to prevent requests from being sent to the disk when real-time requests are waiting to be served. The third is to limit the length of the on-disk queue in addition to the second technique. Our results show the ability to guarantee a wide range of desired response times while still allowing the disk to perform scheduling optimizations. These techniques can be generalized to disks from different vendors.

TrueErase: Leveraging an Auxiliary Data Path for Per-File Secure Deletion

One important aspect of privacy is the ability to securely delete sensitive data from electronic storage in such a way that it cannot be recovered; we call this action secure deletion. Short of physically destroying the entire storage medium, existing software secure-deletion solutions tend to be piecemeal at best -- they may only work for one type of storage or file system, may force the user to delete all files instead of selected ones, may require the added complexities of encryption and key storage, may require extensive changes and additions to the computers operating system or storage firmware, and may not handle system crashes gracefully. We present TrueErase, a holistic secure-deletion framework for individual systems that contain sensitive data. Through design, implementation, verification, and evaluation on both a hard drive and NAND flash, TrueErase shows that it is possible to construct a per-file, secure-deletion framework that can accommodate different storage media and legacy file systems, require limited changes to legacy systems, and handle common crash scenarios. TrueErase can serve as a building block by cryptographic systems that securely delete information by erasing encryption keys. The overhead is dependent on spatial locality, number of sensitive files, and workload (computational- or I/O-bound).

Multi-agent testbed for emerging power systems

Controls in power systems such as national utility grids, microgrids, and shipboard electrical infrastructures are evolving and conventional testbeds are inadequately outfitted for effective design, development, and testing. In particular, conventional power system control testbeds typically lack appropriate computational and data communication tools to quickly and accurately represent advanced control architectures. In this paper, we discuss experiences with a distributed control testbed by incorporating general purpose computational platforms and a more extensive data communications infrastructure. These components enhance the testbed by providing access to key technologies expected to be prevalent in emerging power systems and also simplify the implementation of sophisticated control architectures. Evaluation of the improved capabilities of the testbed is provided through two studies. The first explores the control capabilities for a shipboard power system through the use of hierarchical and distributed control structures. The second investigates the effect of data communication latencies on a control algorithm through a test case involving synchronization of multiple generators.

Graph traversal-based automation of fault detection, location, and recovery on MVDC shipboard power systems

This paper describes a graph traversal-based method for automating system-wide programming of differential fault protection and generation of fault isolation steps in MVDC shipboard power systems (SPS). Automation is highly desired due to the increased complexity of isolating faults using disconnect switches rather than breakers. The method in this paper describes the derivation of a graph abstraction from the electrical system that is then used for computing a minimal but sufficient isolation sequence consisting of commands issued to breakers and switching converters.

Controller HIL testing of real-time distributed frequency control for future power systems

With the evolution of power system components and structures driven mainly by renewable energy technologies, reliability of the network could be compromised with traditional control methodologies. Therefore, it is crucial to thoroughly validate and test future power system control concepts before deployment. In this paper, a Controller Hardware in the Loop (CHIL) simulation for a real-time distributed control algorithm concept developed within the ELECTRA IRP project is performed. CHIL allows exploration of many real-world issues such as noise, randomness of event timings, and hardware design issues that are often not present on a simulation-only system. Octave has been used as the programming language of the controller in order to facilitate the transition between software simulation and real-time control testing. The distributed controller achieved frequency restoration with a collaborative response between different controllers very fast after the unbalanced area is located.

Distributed energy storage allocation algorithm for early stage design

This paper presents a novel algorithm for representing the effects of an optimal energy scheduling system in early stage analyses of systems employing distributed energy storage. The algorithm was developed in the context of a framework for analysis of systems employing energy storage, which includes such considerations as: system topology; load buffering, leveling, and shedding; uncertainty; size, weight, and cost. The presented algorithm provides a means for computing an optimal schedule of energy resource allocation for power- and energy-constrained scenarios. Of particular interest, the algorithm considers the possibility to withhold available stored energy from lower priority loads in order to serve higher priority loads at a later time (in a given scenario). By contrast, other works have generally assumed that energy is allocated immediately when a power deficit would otherwise require load to be shed.