Pervasive systems require flexible and efficient resource management policies to accommodate heterogeneous infrastructures and evolving application demands. This paper presents a policy-specification formalism, building on previous work, that addresses key limitations in how policies are defined and evaluated. The new approach introduces a clear categorization of policies into mandatory and optional sets, enabling fail-fast decisions when critical conditions fail while still supporting opportunistic usage. These features reduce evaluation costs——often down to O(1) in the best case——and facilitate parallel evaluations in large-scale environments. The proposed formalism offers a practical way to define opportunistic resource usage for collaborative, multi-organizational scenarios, demonstrating improved adaptability, reduced overhead, and effective integration of organizational knowledge in resource management. Simulations confirm superior performance compared to previous approach, validating the formalism’s capacity to address complex and dynamic system requirements.

错误:搜索内容不能为空,请输入英文关键词
错误:关键词超出字数限制,请精简
高级检索

An Enhanced Formalism for Resource Management Policies Specification and Fast Evaluation in Pervasive Systems

  • David Beserra,
  • Jean Araujo

摘要

Pervasive systems require flexible and efficient resource management policies to accommodate heterogeneous infrastructures and evolving application demands. This paper presents a policy-specification formalism, building on previous work, that addresses key limitations in how policies are defined and evaluated. The new approach introduces a clear categorization of policies into mandatory and optional sets, enabling fail-fast decisions when critical conditions fail while still supporting opportunistic usage. These features reduce evaluation costs——often down to O(1) in the best case——and facilitate parallel evaluations in large-scale environments. The proposed formalism offers a practical way to define opportunistic resource usage for collaborative, multi-organizational scenarios, demonstrating improved adaptability, reduced overhead, and effective integration of organizational knowledge in resource management. Simulations confirm superior performance compared to previous approach, validating the formalism’s capacity to address complex and dynamic system requirements.