Content uploaded by Sara Tucci-Piergiovanni
Author content
All content in this area was uploaded by Sara Tucci-Piergiovanni on Apr 14, 2015
Content may be subject to copyright.
A preview of the PDF is not available
Multi-Agent Optimization for Safety Analysis of Cyber-Physical Systems
Figures
Figures - uploaded by Sara Tucci-Piergiovanni
Author content
All figure content in this area was uploaded by Sara Tucci-Piergiovanni
Content may be subject to copyright.
... Observing one or more agent communities operating in IoT and CPS scenarios can unveil an apparently unlimited potential. For example, the application domains that received notable contributions are healthcare [52,54,11,24], smart environments (e.g., office, home city [4,44,6,32]), smart cities (e.g., mobility [24,32], urban safety [52], water distribution [4,33], transportation [11], and energy [41,52,11]), industrial scenarios (e.g., manufacturing [4], workflow and process management [52,11]), assisted living [15,16,44,6], and telerehabilitation [17]. ...
... Observing one or more agent communities operating in IoT and CPS scenarios can unveil an apparently unlimited potential. For example, the application domains that received notable contributions are healthcare [52,54,11,24], smart environments (e.g., office, home city [4,44,6,32]), smart cities (e.g., mobility [24,32], urban safety [52], water distribution [4,33], transportation [11], and energy [41,52,11]), industrial scenarios (e.g., manufacturing [4], workflow and process management [52,11]), assisted living [15,16,44,6], and telerehabilitation [17]. ...
Techniques originating from the Internet of Things (IoT) and Cyber-Physical Systems (CPS) areas have extensively been applied to develop intelligent and pervasive systems such as assistive monitoring, feedback in telerehabilitation, energy management, and negotiation. Those application domains particularly include three major characteristics: intelligence, autonomy and real-time behavior. Multi-Agent Systems (MAS) are one of the major technological paradigms that are used to implement such systems. However, they mainly address the first two characteristics, but miss to comply with strict timing constraints. The timing compliance is crucial for safety-critical applications operating in domains such as healthcare and automotive. The main reasons for this lack of real-time satisfiability in MAS originate from current theories, standards, and technological implementations. In particular, internal agent schedulers, communication middlewares, and negotiation protocols have been identified as co-factors inhibiting the real-time compliance. This paper provides an analysis of such MAS components and pave the road for achieving the MAS compliance with strict timing constraints, thus fostering reliability and predictability.
... Observing one or more agent communities operating in IoT and CPS scenarios can unveil an apparently unlimited potential. For example, the application domains that received more contributions are healthcare [25,27,31,52,61,62], smart environments (e.g., office, home city [4,6,44,58]), smart cities (e.g., mobility [32,44], urban safety [73], water distribution [4, 45], transportation [13], and energy [13,54,73]), industrial scenarios (e.g., manufacturing [4], workflow and process management [13,73]) and assisted living [6,20,21,58]. See [70] for a recent survey of MAS applications. ...
Since its dawn as a discipline, Artificial Intelligence (AI) has focused on mimicking the human mental processes. As AI applications matured, the interest for employing them into real-world complex systems (i.e., coupling AI with Cyber-Physical Systems—CPS) kept increasing. In the last decades, the multi-agent systems (MAS) paradigm has been among the most relevant approaches fostering the development of intelligent systems. In numerous scenarios, MAS boosted distributed autonomous reasoning and behaviors. However, many real-world applications (e.g., CPS) demand the respect of strict timing constraints. Unfortunately, current AI/MAS theories and applications only reason “about time” and are incapable of acting “in time” guaranteeing any timing predictability. This paper analyzes the MAS compliance with strict timing constraints (real-time compliance)—crucial for safety-critical applications such as healthcare, industry 4.0, and automotive. Moreover, it elicits the main reasons for the lack of real-time satisfiability in MAS (originated from current theories, standards, and implementations). In particular, traditional internal agent schedulers (general-purpose-like), communication middlewares, and negotiation protocols have been identified as co-factors inhibiting real-time compliance. To pave the road towards reliable and predictable MAS, this paper postulates a formal definition and mathematical model of real-time multi-agent systems (RT-MAS). Furthermore, this paper presents the results obtained by testing the dynamics characterizing the RT-MAS model within the simulator MAXIM-GPRT. Thus, it has been possible to analyze the deadline miss ratio between the algorithms employed in the most popular frameworks and the proposed ones. Finally, discussing the obtained results, the ongoing and future steps are outlined.
... Figure 5 shows an example of FMEA and FMECA table generated within Sophia. In addition, we enrich the FMEA module with an adaptive multi-agent optimization method to provide an optimal set of recommended actions, in order to get a trade-off between system safety criticality and cost constraints [35]. ...
Support Vector Machines (SVM) have been in the forefront of machine learning research for many years now. They have very nice theoretical properties and have proven to be efficient in many real life applications but the design of SVM training algorithms often gives rise to challenging optimization issues. We propose here to review the basics of support vector machine learning from a multi-agent optimization perspective. Multi-agents systems break down complex optimization problems into elementary ”oracle” tasks and perform a collaborative solving process resulting in a self-organized solution of the complex problems. We show how the SVM training problem can also be ”tackled” from this point of view and provide several perspectives for binary classification, hyperparameters selection, multiclass learning as well as unsupervised learning. This conceptual work is illustrated through simple examples in order to convey the ideas and understand the behaviour of agent cooperation. The proposed models provide simple formulations of complex learning tasks that are sometimes very difficult to solve with classical optimization strategies. The ideas that are discussed open up perspectives for the design of new distributed cooperative learning systems.
MultiDisciplinary Optimization (MDO) problems represent one of the hardest and broadest domains of continuous optimization. By involving both the models and criteria of different disciplines, MDO problems are often too complex to be tackled by classical optimization methods. We propose an approach which takes into account this complexity using a new representation (NDMO - Natural Domain Modeling for Optimization) and a self-adaptive multi-agent algorithm. Our method agentifies the different elements of the problem (such as the variables, the models, the objectives). Each agent is in charge of a small part of the problem and cooperates with others to find equilibrium on conflicting values. Despite the fact that no agent of the system has a complete view of the entire problem, the mechanisms we provide allow the emergence of a coherent solution. Evaluations on several academic and industrial test cases are provided.
Robotic systems (RSs) are often used for performing critical tasks with little or no human intervention. Such RSs must satisfy certain dependability requirements including reliability, availability, security and safety. In this paper, we focus on the safety aspect and propose a methodology and associated framework for safety assessment of RSs in the early phases of development. The methodology relies upon model-driven engineering approach and describes a preliminary safety assessment of safety-critical RSs using fault tree (FT) analysis (FTA). The framework supports a domain specific language for RSs called RobotML and includes facilities (i) to automatically generate or manually construct FTs and perform both qualitative and quantitative FTA, (ii) to make semantic connections with formal verification and FTA tools, (iii) to represent FTA results in the RobotML modeling environment. In the case study, we illustrate the proposed methodology and framework by considering a mobile robot developed in the scope of the Proteus project.
A complex product is generally a system composed of numerous interdependent components, each one representing specific disciplines and developed using associated expertise. When analysing the problem from another point of view, we can see that for each design domain, a generally huge set of real already designed elements exists. Thus, when constructing a new element, it is interesting to use this already known and acquired knowledge. This knowledge does not only contain the discipline's information but also the engineers' experience. Considering this point of view, the design of complex products defines a new generic class of complex problems. In this paper, we address this class of problems using the Self-Adaptive Population Based Reasoning (SAPBR) generic approach. It is based on the Adaptive Multi-Agent System (AMAS) theory that takes advantage from cooperation to design robust and open multi-agent systems. In SAPBR, agents use cooperative self-tuning principles in order to estimate and discover new characteristic values for the design of new elements. The obtained system is compared to the Self-Organising Map (SOM) and the Multilayer Perceptron (MP) algorithms that address similar problems.
There are many challenges which face designers of complex system architectures, particularly safety–critical or real-time systems. The introduction of Architecture Description Languages (ADLs) has helped to meet these challenges by consolidating information about a system and providing a platform for modelling and analysis capabilities. However, managing this wealth of information can still be problematic, and evaluation of potential design decisions is still often performed manually. Automatic architectural optimisation can be used to assist this decision process, enabling designers to rapidly explore many different options and evaluate them according to specific criteria. In this paper, we present a multi-objective optimisation approach based on EAST-ADL, an ADL in the automotive domain, with the goal of combining the advantages of ADLs and architectural optimisation. The approach is designed to be extensible and leverages the capabilities of EAST-ADL to provide support for evaluation according to different factors, including dependability, timing/performance, and cost. The technique is applied to an illustrative example system featuring both hardware and software perspectives, demonstrating the potential benefits of this concept to the design of embedded system architectures.
Nowadays aircrafts require more electrical systems. Functions usually carried out by mechanical, hydraulics or pneumatics systems are now carried out by electrical systems. Thus there is a densification of electrical systems. An aircraft electrical system is made of several electrical harnesses which are assemblies of cables and connective devices. A cable may contain one or several wires in a common covering. Thus wiring may be seen as a system of systems. In parallel, a link connects (functionally) equipments through harnesses.
Modeling and Analysis of Real-Time and Embedded Systems with UML and MARTE explains how to apply the complex MARTE standard in practical situations. This approachable reference provides a handy user guide, illustrating with numerous examples how you can use MARTE to design and develop real-time and embedded systems and software. Expert co-authors Bran Selic and SA©bastien GA©rard lead the team that drafted and maintain the standard and give you the tools you need apply MARTE to overcome the limitations of cyber-physical systems. The functional sophistication required of modern cyber-physical systems has reached a point where traditional code-centric development methods are proving less and less capable of delivering a reliable product in a timely manner. In Modeling and Analysis of Real-Time and Embedded Systems with UML and MARTE, you will learn how to take advantage of modern model-based engineering methods and corresponding industry standards to overcome these limitations. These methods take full advantage of computer-supported automation allowing timely detection of design flaws to reduce engineering risk, leading thereby to better overall product quality and greater productivity.
The benefits and importance of self managed, stable and dependable systems, and IT services, are discussed. With the increase in number of hardware and software components to be managed increases, and as the dependencies between user-perceived services and the underlying networks and systems are ever more complex and dynamic, management systems have become increasingly complex. Researchers have experimented with alternative methods to organize and structure systems and services differently to better facilitate their management. It is necessary to have a strongly distributed management solutions where management decisions are highly decentralized and performed autonomously by network devices and systems. The management community is moving to self management, which is raising huge interest in the distributed systems, and software engineering. Biological and sociological phenomena also serves as inspirations and guidelines for the design of self organization systems.