Reconfigurable service-oriented architecture for autonomic computing

Almost a decade has passed since the objectives and benefits of autonomic computing were stated, yet even the latest system designs and deployments exhibit only limited and isolated elements of autonomic functionality. In previous work, we identified several of the key challenges behind this delay in the adoption of autonomic solutions, and proposed a generic framework for the development of autonomic computing systems that overcomes these challenges. In this article, we describe how existing technologies and standards can be used to realise our autonomic computing framework, and present its implementation as a service-oriented architecture. We show how this implementation employs a combination of automated code generation, model-based and object-oriented development techniques to ensure that the framework can be used to add autonomic capabilities to systems whose characteristics are unknown until runtime. We then use our framework to develop two autonomic solutions for the allocation of server capacity to services of different priorities and variable workloads, thus illustrating its application in the context of a typical data-centre resource management problem.

General-purpose autonomic computing

The success of mainstream computing is largely due to the widespread availability of general-purpose architectures and of generic approaches that can be used to solve real-world problems cost-effectively and across a broad range of application domains. In this chapter, we propose that a similar generic framework is used to make the development of autonomic solutions cost effective, and to establish autonomic computing as a major approach to managing the complexity of today’s large-scale systems and systems of systems. To demonstrate the feasibility of general-purpose autonomic computing, we introduce a generic autonomic computing framework comprising a policy-based autonomic architecture and a novel four-step method for the effective development of self-managing systems. A prototype implementation of the reconfigurable policy engine at the core of our architecture is then used to develop autonomic solutions for case studies from several application domains. Looking into the future, we describe a methodology for the engineering of self-managing systems that extends and generalises our autonomic computing framework further.

Resource-definition policies for autonomic computing

The paper introduces a framework for the formal specification of autonomic computing policies, and uses it to define a new type of autonomic computing policy termed a resource-definition policy. We describe the semantics of resource-definition policies, explain how they can be used as a basis for the development of autonomic system of systems, and present a sample data-centre application built using the new policy type.

Towards a generic autonomic architecture for legacy resource management

Half a decade has passed since the objectives and benefits of autonomic computing were stated, yet even the latest system designs and deployments exhibit only limited and isolated elements of autonomic functionality. From an autonomic computing standpoint, all computing systems – old, new or under development – are legacy systems, and will continue to be so for some time to come. In this paper, we propose a generic architecture for developing fully-fledged autonomic systems out of legacy, non-autonomic components, and we investigate how existing technologies can be used to implement this architecture.

Run-time connector synthesis for autonomic systems of systems

A key objective of autonomic computing is to reduce the cost and expertise required for the management of complex IT systems. As a growing number of these systems are implemented as hierarchies or federations of lower-level systems, techniques that support the development of autonomic systems of systems are required. This article introduces one such technique, which involves the run-time synthesis of autonomic system connectors. These connectors are specified by means of a new type of autonomic computing policy termed a resource definition policy, and enable the dynamic realisation of collections of collaborating autonomic systems, as envisaged by the original vision of autonomic computing. We propose a framework for the formal specification of autonomic computing policies, and use it to define the new policy type and to describe its application to the development of autonomic system of systems. To validate the approach, we present a sample data-centre application that was built using connectors synthesised from resource-definition policies.

Formal methods for the development and verification of autonomic IT systems

This chapter explores ways in which rigorous mathematical techniques, termed formal methods, can be employed to improve the predictability and dependability of autonomic computing. Model checking, formal specification, and quantitative verification are presented in the contexts of conflict detection in autonomic computing policies, and of implementation of goal and utility-function policies in autonomic IT systems, respectively. Each of these techniques is illustrated using a detailed case study, and analysed to establish its merits and limitations. The analysis is then used as a basis for discussing the challenges and opportunities of this endeavour to transition the development of autonomic IT systems from the current practice of using ad-hoc methods and heuristic towards a more principled approach. © 2012, IGI Global.

Methodology for the model-driven development of self-managing systems

Based on recent advances in autonomic computing, we propose a methodology for the cost-effective development of self-managing systems starting from a model of the resources to be managed and using a general-purpose autonomic architecture.

Revisiting goal-oriented models for self-aware systems-of-systems

Systems-of-systems (SoS) are systems resulted from the interaction among other independent constituent systems that collaborate to offer new functionalities towards accomplishing global missions. Each of these constituent systems accomplishes its individual missions and is able to contribute to the achievement of the global missions of the SoS, both being viewed as a set of associated goals. In the perspective of self-aware systems, SoS need to exhibit goal-awareness, i.e., They need to be aware of their own goals and of how their constituent systems contribute to their accomplishment. In this paper, we revisit goal-oriented concepts aiming at identifying and modeling goals at both SoS level and the constituent systems level. Moreover, we take advantage of such goal-oriented models to express the relationship among goals at these levels as well as to define how each constituent system can contribute to the accomplishment of global goals of an SoS. In addition, we shed light on important issues related to goal modeling in self-aware SoS to be addressed in future research.

Preface to Models@run.time 2016

The complexity of adapting software during runtime has spawned interest in how models can be used to validate, monitor and adapt runtime behaviour. The use of models during runtime extends the use of modeling techniques beyond the design and implementation phases. The goal of this workshop is to look at issues related to developing appropriate modeldriven approaches to managing and monitoring the execution of systems and, also, to allow the system to reason about itself. We aim to continue the discussion of research ideas and proposals from researchers who work in relevant areas such as MDE, software architectures, reflection, and autonomic and self-adaptive systems, and provide a 'state-of-the-art' research assessment expressed in terms of challenges and achievements.

CloudMPL:a domain specific language for describing management policies for an autonomic cloud infrastructure

To benefit from the advantages that Cloud Computing brings to the IT industry, management policies must be implemented as a part of the operation of the Cloud. Among others, for example, the specification of policies can be used for the management of energy to reduce the cost of running the IT system or also for security policies while handling privacy issues of users. As cloud platforms are large, manual enforcement of policies is not scalable. Hence, autonomic approaches for management policies have recently received a considerable attention. These approaches allow specification of rules that are executed via rule-engines. The process of rules creation starts by the interpretation of the policies drafted by high-rank managers. Then, technical IT staff translate such policies to operational activities to implement them. Such process can start from a textual declarative description and after numerous steps terminates in a set of rules to be executed on a rule engine. To simplify the steps and to bridge the considerable gap between the declarative policies and executable rules, we propose a domain-specific language called CloudMPL. We also design a method of automated transformation of the rules captured in CloudMPL to the popular rule-engine Drools. As the policies are changed over time, code generation will reduce the time required for the implementation of the policies. In addition, using a declarative language for writing the specifications is expected to make the authoring of rules easier. We demonstrate the use of the CloudMPL language into a running example extracted from a management energy consumption case study.