A Multi Variable Optimization Approach for the Design of Integrated Dependable Real-Time Embedded Systems

Abstract

Abstract. Embedded systems increasingly encompass both dependability and responsiveness requirements. While sophisticated techniques exist, on a discrete basis, for both dependability/fault-tolerance (FT) and real-time (RT), the composite considerations for FT+RT are still evolving. Obviously the different objectives needed for FT and RT make composite optimization hard. In this paper, the proposed Multi Variable Optimization (MVO) process develops integrated FT+RT considerations. We introduce dependability as an initial optimization criteria by confining error propagation probability, i.e., limiting the interactions. Subsequently, quantification of interactions together with RT optimization by minimizing scheduling length is developed. A simulated annealing approach is utilized to find optimized solutions. We provide experimental results for our approach, showing significant design improvements over contemporary analytical initial feasibility solutions.

An optimization based design for integrated dependable real-time embedded systems

“…The output of the algorithm derives the basic scheduling. An optimized solution can then be easily found by using CPLEX or any other approaches like [37]. The initial feasible mapping guides the optimization process in an efficient way to find the solution (see the validation and comparative study in Sect.…”

“…Design optimization Different objectives are combined into a single composite function by applying weights expressing their importance, or reached by using multi-objective optimization techniques [37]. In this design process, optimization is primarily realized by using the ordering heuristics.…”

Software Architecture Optimization Methods: A Systematic Literature Review

“…Performance (84) ADL(4) [145], [160], [161], [170], ANY(2) [133], [153], CUSTOMAM(5) [90], [152], [196]- [198], OPTIMPL(3) ALLOCATION(20) [61], [83], [88], [121]- [123], [133], [153], [155], [160], [161], [164], [175]- [178], [186], [187], [192], [214], CLUSTERING(3) [67], [122], [214], COMPONENT SELECTION(12) [7], [18], [96], [97], [147], [149], [160], [161], [177], [178], [182], [232], HARDWARE PARAMETERS(2) [160], [161], HARDWARE REPLICATION(29) [31], [51]- [57], …”

“…Performance(84) EXACT PROBLEM-SPECIFIC(3) [1], [112], [126], EXACT STANDARD(14) [12]- [15], [42]- [44], [69], [117], [169], [174], [218], [236], [241], GENERAL(1) [153], METAHEURIS-TIC(45) [2], [3], [23], [29], [32], [35], [38]- [40], [45], [46], [66], [73], [77], [83], [84], [88], [114], [122]- [124], [130], [133], [141], [143], [145], [160], [161], [170], [175]- [177], [188], [189], [196]- [198], [200], [220], …”

Aiding Modular Design and Verification of Safety-Critical Time-Triggered Systems by Use of Executable Formal Specifications

“…Different techniques such as constraint propagation, branch and bound, backtracking or mixed integer programming have been proposed (e.g., [15,12,2]), however, they require either the development of new computation engines (e.g., written in C [12] or Java [15]) or the use of existing dedicated engines (e.g., [2]) to solve (or even optimize) the constraint problem. Although our method, when used for scheduling, might be outperformed by other techniques, it uses the same system representation that is used for other tasks.…”