WL/AAKR, Bldg. 7 2530 C Street Wright Patterson AFB, OH 45433-7607

A -- DYNAMIC AVIONICS REAL-TIME SCHEDULING. PART 1 OF 2 SOL PRDA 95-12-AAK DUE 042095 POC Dawn M. Ross, Contract Negotiator, 513-255-6908. A--INTRODUCTION: DYNAMIC AVIONICS REAL-TIME SCHEDULING (DARTS), PRDA #95-12-AAK. This is a Program Research and Development Announcement (PRDA). Wright Laboratory (WL/AAAT) is interested in receiving proposals (Technical and Cost) on the research effort described below. Proposals in response to this PRDA shall be submitted by 25 April 95, 1500 hours Eastern Daylight Time, to Wright Laboratory, Directorate of R&D Contracting, Attn: Dawn M. Ross, WL/AAKR, Bldg 7, Area B, 2530 C Street, Wright-Patterson AFB OH 45433-7607. This is an unrestricted solicitation. Small businesses are encouraged to propose on all or any part of this solicitation. Teaming arrangements between private industry and universities will also be considered and are encouraged. Proposals submitted shall be in accordance with this announcement. Proposal receipt after the cut off date and time specified herein shall be treated in accordance with restrictions of FAR 52.215-10. A copy of this provision may be obtained from the contracting point of contact. There will be no other solicitation issued in regard to this requirement. Offerors should be alert for any PRDA amendments, including those that may permit subsequent submission of proposal dates. Offerors should request a copy of the WL Guide entitled ''PRDA and BAA Guide for Industry.'' This Guide was specifically designed to assist offerors in understanding the PRDA/BAA proposal process. Copies may be requested from the contracting officer cited in this announcement B-REQUIREMENTS: Note that a previous PRDA (#94-10-AAK) entitled ''Real-Time Schedulers for Parallel Processors'' was published in Mar 94 but a contract was not awarded due to government funding constraints. This new PRDA has very similar, but more focused objectives than the previous PRDA. However, resubmittal of proposals for the previous PRDA is not acceptable. (1) BACKGROUND: Avionics application software (e.g., flight control, situation assessment, automatic target recognition) is composed of complex, time-critical tasks which demand sophisticated schedulers to orchestrate overall real-time task execution. Current realtime system design employs skilled craftsman who handcraft execution of tasks by performing successive time-line analysis. Timing issues, rather than software engineering, drive the whole design approach leading to brittle software which is costly in terms of time and expense to modify. Operating system designers develop the mechanisms for scheduling software execution, with cyclic executives representing the state of the practice for realtime avionics. Rate Monotonic Scheduling (RMS) represents the state of the art for static (off-line) scheduling of uniprocessor systems, with methods for predicting real-time system behavior. In contrast, dynamic scheduling algorithms schedule tasks on-line based on the actual sequence of requests, providing an application with a dynamic response to its operating environment. Both techniques have advantages and disadvantages. RMS is optimal for uniprocessors but must be adapted to apply to multiprocessor systems common on avionics platforms. Dynamic scheduling provides the most efficient use of resources, but requires overhead processing and lacks the predictability of RMS. Since avionics applications are dynamic in nature, it is desirable to combine the adaptability and flexibility of dynamic scheduling with the predictability and analysis techniques of RMS. (2) TECHNICAL DESCRIPTION: The objective of this effort is to develop and demonstrate a scheduling methodology for engineering harddeadline, real-time scheduling solutions for distributed, heterogeneous, avionics processor architectures. This methodology shall combine dynamic scheduling theory with Rate Monotonic Scheduling theory and be compatible with Ada 95. The payoffs are dynamic response to changing mission needs, predictable performance, design techniques for real-time design, applicability to aging aircraft, significant reduction in time and cost to design and upgrade software, and improved software reliability and maintainability. (3) TECHNICAL REQUIREMENTS: (a) Requirements Study. The contractor shall determine the requirements relative to scheduling real-time avionics applications on distributed, heterogeneous, multiprocessor avionics architectures. Retrofit requirements for legacy systems shall also be addressed. The contractor shall define metrics for qualitative and quantitative measurement of real-time software design and performance. The offeror shall propose baseline avionics applications from his corporate experience base. From these applications, the contractor shall develop strenuous real-time avionics benchmarks which shall be used to evaluate the developed scheduling methodology, (b) Scheduling Methodology. The contractor shall develop a real-time scheduling methodology which combines dynamic scheduling techniques with Rate Monotonic Scheduling such that the derived avionics real-time scheduling requirements are met. The methodology shall embody the concepts of RMS while providing the benefits of dynamic scheduling. The contractor shall incorporate or develop scheduling algorithms as necessary. These algorithms shall be independent of the implementation language, but implementable using the Ada 95 language. The contractor may also develop software support tools or simulations as necessary to support this effort. This software need not be written in Ada, (c) Evaluation. The contractor shall develop a plan for evaluation of the scheduling methodology and algorithms. Using the Government approved plan, the contractor shall evaluate the scheduling methodology using the defined benchmarks and metrics in performing the evaluation, (d) Transition Study. The contractor shall identify potential avionics platforms for transition and develop strategies for application of the scheduling methodology to those platforms, (e) Demonstrations. The offeror shall propose a baseline set of demonstrations that incrementally exhibit program progress culminating in a final demonstration of the scheduling methodology, this set may be further refined during the contract. C--DATA AND OTHER DELIVERABLES: (1) DATA: The contractor shall prepare and deliver the following data (The term ''/T'' means tailored.): (a) Status Report, DI-MGMT-80368/T (monthly), (b) Funds and Man-Hour Expenditure Report, DI-FNCL 80331/T (monthly), (c) Contract Funds Status Report, DI-F-6004B/T (quarterly), (d) Scientific and Technical Reports - Contractor's Billing Voucher, DI-MISC-80711/T (monthly), (e) Project Planning Chart, DI-MGMT-80507A/T (monthly), (f) Presentation Material, DI ADMN-81373/T (ASREQ), (g) Scientific and Technical Reports - Final Report, DI-MISC-80711/T (Draft and Camera Ready Copy), (h) Test Plans/Procedures: Evaluation Plan, DI-NDTI-80808/T, (i) Technical Report - Study/Services: Requirements Study, DI-MISC-80508/T. (j) Technical Report - Study/Services: Scheduling Methodology, DIMISC- 80508/T, (k) Software User's Manual, DI-MCCR-80019A/T, (l) Computer Software Product End Items: Scheduling Algorithms, Tools, Benchmarks, DI-MCCR-80700/T. (2) REVIEWS: A Kickoff Meeting shall be held at Wright-Patterson AFB approximately two weeks after contract award. Quarterly technical reviews shall be conducted at the contractor's facility. One of the quarterly reviews shall be devoted to discussing the Requirements Study. D- -SPECIAL CONSIDERATIONS: (1) INTERNATIONAL TRAFFIC IN ARMS RESTRICTIONS (ITAR): ITAR requirements apply to this effort. Generation of classified material for this solicitation effort is authorized only on equipment approved for classified processing by Air Force TEMPEST authorities. (2) SECURITY REQUIREMENTS: After award, access to classified information is required to review avionic real-time applications in order to determine scheduling requirements. A Contract Security Classification Specification (DD Form 254) will be included in the contract. E--ADDITIONAL INFORMATION: (1) ANTICIPATED PERIOD OF PERFORMANCE: The total length of the technical effort is 27 months. The contractor shall also provide for an additional 4 months for processing/completion of the final report, for a total contract duration of 31 months. (2) EXPECTED AWARD DATE: Sep 95. (3) GOVERNMENT ESTIMATE: The government anticipates a single award, with a funding profile of $1,000 in FY95, $300,000 in FY96, $280,000 in FY97, and $119,000 in FY98. This funding profile is an estimate only and not a promise for funding as all funding is subject to change due to Government discretion and availability. (4) TYPE OF CONTRACT: Cost Plus Fixed Fee (CPFF) completion or Cost (no fee). Any grants or cooperative agreements awarded will be cost (no fee). End of Part 1. (0067)

Loren Data Corp. http://www.ld.com (SYN# 0001 19950309\A-0001.SOL)