Towards the Trusted Population-Based Optimization Systems

  • Sato Hiroshi
    Department of Computer Science, National Defense Academy
  • Kubo Masao
    Department of Computer Science, National Defense Academy

Description

Following the development of evolutionary computation, various population-based optimization methods have been proposed. In these systems, optimization is achieved through the interactions of many individuals/particles/agents. However, when the system is implemented in a distributed environment, reliability becomes an issue. In such an environment, it may not be possible to trust others. There are numerous cases which we cannot guarantee trust, such as malfunction of distributed parts or failure to synchronize. Therefore, we have to make trust between distributed individuals/particles/agents. The record of past actions is usually a good tool for generating trust. This paper introduces the blockchain mechanism into the population-based optimization system to make a trust management system. By using blockchain, we can implement it without a central authority. In the system, all interactions are reviewed and get feedback, and the feedback is used to calculate the trust score.

Journal

Details 詳細情報について

  • CRID
    1390854717504305536
  • DOI
    10.5954/icarob.2022.os23-2
  • ISSN
    21887829
  • Text Lang
    en
  • Data Source
    • JaLC
    • Crossref
  • Abstract License Flag
    Disallowed

Report a problem

Back to top