chapter  19
40 Pages

A Biologically Inspired QoS-Aware Architecture for Scalable, Adaptive, and Survivable Network Systems . . . . . . . . . . . . . . . . . . . . . . . . . . . PASKORN CHAMPRASERT AND JUNICHI SUZUKI

Contents 19.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 482 19.2 Design Principles in SymbioticSphere . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 484 19.3 SymbioticSphere . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 487

19.3.1 Agents . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 487 19.3.2 Platforms . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 487 19.3.3 Behavior Policies . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 489

19.3.3.1 Agent Behavior Policies . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 489 19.3.3.2 Platform Behavior Policies . . . . . . . . . . . . . . . . . . . . . . . . . . . 490

19.3.4 Energy Exchange . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 491 19.3.5 Constraint-Aware Evolution . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 492

19.4 Evaluation. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 495 19.4.1 Simulation Configurations. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 496 19.4.2 Evaluation of Energy Exchange . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 500 19.4.3 Evaluation of Adaptability . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 500 19.4.4 Evaluation of Scalability . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 509 19.4.5 Evaluation of Survivability . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 514

19.5 Related Work . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 517 19.6 Concluding Remarks . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 518 References . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 519

Large-scale network systems, such as grid/cloud computing systems, are increasingly expected to be autonomous, scalable, adaptive to dynamic network environments, survivable against partial system failures, and simple to implement and maintain. Based on the observation that various biological systems have overcome these requirements, the proposed architecture, SymbioticSphere, applies biological principles and mechanisms to design network systems (i.e., application services and middleware platforms). SymbioticSphere follows key biological principles such as decentralization, evolution, emergence, diversity, and symbiosis. Each application service and middleware platform is modeled as a biological entity, analogous to an individual bee in a bee colony, and implements biological mechanisms such as energy exchange, migration, replication, reproduction, and death. Each agent/platform possesses behavior policies, as genes, each of which determines when and how to invoke a particular behavior. Agents and platforms are designed to evolve and adjust their genes (behavior policies) through generations and autonomously improve their scalability, adaptability, and survivability. Through this evolution process, agents/platforms strive to satisfy given constraints for quality of service (QoS) such as response time, throughput, and workload distribution. This chapter describes the design of SymbioticSphere and evaluates how the biologically inspired mechanisms in SymbioticSphere impact the autonomy, adaptability, scalability, survivability, and simplicity of network systems.