The need for a dynamic and scalable expansion of the grid infrastructure and resources and other scalability issues in terms of execution efficiency and fault tolerance present centralized management techniques with numerous difficulties. This chapter presents the case for biologically inspired grid resource management techniques that are decentralized and self organized in nature. To achieve the desired de-centralized resource management, these techniques model the self-organization observed in many natural complex adaptive systems. Using a few representative techniques, the authors review the literature on Bio-inspired Grid Resource Management. Based on this review the authors conclude that many such techniques have been successfully applied to resource discovery, service placement, scheduling and load balancing.
The universe is full of systems that are complex and constantly adapting to their environment. Examples of these systems include human economies, the ecosystem and the weather system. These, so called complex adaptive systems (CAS), are characterised by the absence of a centralised control, dynamism and large scales. The components (or agents) of these complex adaptive systems interact with each other according to some simple local rules. These simple interactions, however, result in self-organisation and complex behaviors.
The Grid As A Complex Adaptive System
A grid computing system can also be seen as a CAS. It is by nature a complex combination of hardware, software and network components. Geographically distributed nature of resources that make up the grid infrastructure, along with their heterogeneity and different control policies in different domains, make the availability of these resources dynamic and conditional upon local constraints. The consumers of the resources are the users who have specific requirements which are expressed in terms of CPU speed, storage capacity, network bandwidth, etc. To achieve the desired de-centralized resource management the self-organization observed in many natural CAS systems can be modeled in the context of grid computing.
Key Terms in this Chapter
Ant Colony Optimization: Ant Colony Optimization or ACO is a Swarm Intelligence technique inspired by the ability of real ant colonies to efficiently organize the foraging behavior of the colony using chemical pheromone trails as a means of communication between the ants.
Complex Adaptive Systems: They are complex in that they are diverse and made up of multiple interconnected elements and adaptive in that they have the capacity to change and learn from experience.
Agent-Based Systems: These are composed of multiple independent / autonomous agents which are collectively capable of achieving goals difficult for an individual agent or a monolithic system.
Self-Organization: It is a process in which the internal organization of a system, normally an open system, increases in complexity without being guided or managed by an outside source. Self-organizing systems typically exhibit emergent behavior.
Grid Resource Management: Efficient and effective deployment of Grid resources when they are needed.
Heuristic Methods: These methods, found through discovery and observation, are known to produce incorrect or inexact results at times but likely to produce correct or sufficiently exact results when applied in commonly occurring conditions.
Emergent Behavior: Emergence refers to the way complex systems and patterns arise out of a multiplicity of relatively simple interactions.
Swarm Intelligence: Emergent behavior, observed in numerous natural entities, is modeled to explore collective (or distributed) problem solving without centralized control or the provision of a global model. These models are collectively called Swarm Intelligence models and are characterized by their decentralized and self-organizing nature.