Funmilade Faniyi

Architectural Aspects of Self-Aware and Self-Expressive Computing Systems: From Psychology to Engineering

Work on human self-awareness is the basis for a framework to develop computational systems that can adaptively manage complex dynamic tradeoffs at runtime. An architectural case study in cloud computing illustrates the frameworks potential benefits.

Architecting Self-Aware Software Systems

Contemporary software systems are becoming increasingly large, heterogeneous, and decentralised. They operate in dynamic environments and their architectures exhibit complex trade-offs across dimensions of goals, time, and interaction, which emerges internally from the systems and externally from their environment. This gives rise to the vision of self-aware architecture, where design decisions and execution strategies for these concerns are dynamically analysed and seamlessly managed at run-time. Drawing on the concept of self-awareness from psychology, this paper extends the foundation of software architecture styles for self-adaptive systems to arrive at a new principled approach for architecting self-aware systems. We demonstrate the added value and applicability of the approach in the context of service provisioning to cloud-reliant service-based applications.

EPiCS: Engineering Proprioception in Computing Systems

Modern compute systems continue to evolve towards increasingly complex, heterogeneous and distributed architectures. At the same time, functionality and performance are no longer the only aspects when developing applications for such systems, and additional concerns such as flexibility, power efficiency, resource usage, reliability and cost are becoming increasingly important. This does not only raise the question of how to efficiently develop applications for such systems, but also how to cope with dynamic changes in the application behaviour or the system environment. The EPiCS Project aims to address these aspects through exploring self-awareness and self-expression. Self-awareness allows systems and applications to gather and maintain information about their current state and environment, and reason about their behaviour. Self-expression enables systems to adapt their behaviour autonomously to changing conditions. Innovations in EPiCS are based on systematic integration of research in concepts and foundations, customisable hardware/software platforms and operating systems, and self-aware networking and middleware infrastructure. The developed technologies are validated in three application domains: computational finance, distributed smart cameras and interactive mobile media systems.

Evaluating Security Properties of Architectures in Unpredictable Environments: A Case for Cloud

The continuous evolution and unpredictability underlying service-based systems leads to difficulties in making exact QoS claims about the dependability of architectures interfacing with them. Hence, there is a growing need for new methods to evaluate the dependability of architectures interfacing with such environments. This paper presents a method for evaluating the security quality attribute of architectures in service-based systems. The proposed method combines some properties of the Architectural Tradeoff Analysis Method (ATAM) and security testing using Implied Scenario. In particular, the scenario elicitation process of ATAM is improved by utilising Implied Scenario technique to generate scenarios which may be undetected using plain ATAM. An industrial case study of a problem related to securing data at the Software-as-a-Service layer on Force.com Cloud platform is adopted to validate the new method. The results indicate that our method found four additional security scenarios beyond the plain ATAM, resulting in four new risks and two new tradeoff points.

A Systematic Review of Service Level Management in the Cloud

Cloud computing make it possible to flexibly procure, scale, and release computational resources on demand in response to workload changes. Stakeholders in business and academia are increasingly exploring cloud deployment options for their critical applications. One open problem is that service level agreements (SLAs) in the cloud ecosystem are yet to mature to a state where critical applications can be reliably deployed in clouds. This article systematically surveys the landscape of SLA-based cloud research to understand the state of the art and identify open problems. The survey is particularly aimed at the resource allocation phase of the SLA life cycle while highlighting implications on other phases. Results indicate that (i) minimal number of SLA parameters are accounted for in most studies; (ii) heuristics, policies, and optimisation are the most commonly used techniques for resource allocation; and (iii) the monitor-analysis-plan-execute (MAPE) architecture style is predominant in autonomic cloud systems. The results contribute to the fundamentals of engineering cloud SLA and their autonomic management, motivating further research and industrial-oriented solutions.

A Dynamic Data-Driven Simulation Approach for Preventing Service Level Agreement Violations in Cloud Federation

Abstract The new possibility of accessing an infinite pool of computational resources at a drastically reduced price has made cloud computing popular. With the increase in its adoption and unpredictability of workload, cloud providers are faced with the problem of meeting their service level agreement (SLA) claims as demonstrated by large vendors such as Amazon and Google. Therefore, users of cloud resources are embracing the more promising cloud federation model to ensure service guarantees. Here, users have the option of selecting between multiple cloud providers and subsequently switching to a more reliable one in the event of a providers inability to meet its SLA. In this paper, we propose a novel dynamic data-driven architecture capable of realising resource provision in a cloud federation with minimal SLA violations. We exemplify the approach with the aid of case studies to demonstrate its feasibility.

Engineering Proprioception in SLA Management for Cloud Architectures

With the wide adoption of the Cloud, there remains an open challenge to provide more dependable, transparent, and trustworthy provision of services. Service terms are typically defined in the Service Level Agreement (SLA) binding both service providers and users. For the service user, there is a need to ensure that s/he is enjoying the agreed level of service and any violations are reported accordingly. For the service provider, there is a need to manage a resilient infrastructure capable of meeting SLA terms and inform strategies for maximising profit and resource utilisation. The massive size, dynamism and unpredictability of Cloud architectures makes these goals difficult to accomplish using classic Service Level Management (SLM) approaches. In this paper, we motivate the need for novel dynamic and decentralised approaches for the design of SLM. Requirements and key design decisions for the new SLM are described. Also, a conceptual architecture for realising these requirements is presented. We roadmap and discuss research directions, which can benefit from the new SLM.

Self-managing SLA compliance in cloud architectures: a market-based approach

Service providers often use service level agreements (SLAs) to assure potential users of their services about the QoS to expect when they subscribe. In the cloud computing model, providers are required to continuously meet their SLA claims in the face of unanticipated failure of cloud resources. The dynamics of the cloud environment as attributed to its unpredictable mode of use and elasticity of its resources make human-driven solutions inefficient or sometimes infeasible. On the other hand, self-managed architectures have increasingly matured in their capacity to coordinate environments predominated by uncertainties. Thus making them a right fit for managing cloud-based systems. However, given the massive resource pool of the cloud, state-of-the-art centralised self-managed architectures are not scalable and are inherently brittle. Therefore, we propose a decentralised resource control mechanism which meets the unique robustness, scalability and resilience requirements of the cloud. The design of the mechanism gains inspiration from market control theory and a novel use of reputation metrics. In addition, an innovative self-managed cloud architecture has been designed based on the control mechanism. Early results from simulation studies show that the approach is feasible at reducing the SLA violations incurred by cloud providers.

Design Patterns and Primitives: Introduction of Components and Patterns for SACS

When faced with the task of designing and implementing self-aware and self-expressive computing systems, researchers and practitioners need guidelines on how to use the concepts and foundations of self-awareness. This chapter provides such guidelines on how to design self-aware and self-expressive computing systems in a principled way.We have documented different levels of self-awareness and proposed architectural patterns. We have also discussed common architectural primitives and attributes for architecting self-aware and self-expressive systems. Drawing on the knowledge obtained from the previous investigations, we discuss how the proposed patterns and primitives can be used in real software system projects.

Chapter 5 – Economics-Driven Software Architecting for Cloud

Many of the problems facing providers and users of Cloud-based systems, in terms of maximizing Quality-of-Service (QoS) satisfaction, can be studied using theories in microeconomics. Specifically, the concept of market-based control provides tools that can be used to design economically and computationally efficient Cloud software architectures. This chapter surveys both domains and presents some of the underlying problems and opportunities in the interesting crossbreed of economics and Cloud computing. The dynamic resource allocation problem is used as an example to demonstrate the added value of this approach. Observations from simulation studies reveal the usefulness of the posted offer market model as a viable mechanism for orchestrating the interaction of components in a Cloud software architecture. The chapter concludes with a reflection on open problems that need to be addressed to move the area forward.