Cohesive Hybrid Intelligent Multi-Agent Systems for Power Restoration Planning

The paper develops an approach to solving practical problems by modeling teams of specialists with hybrid intelligent multi-agent systems. The paper discusses the phenomenon of cohesion, which occurs in long-term teams of specialists that jointly solve practical problems, as well as approaches to its multiagent computer modeling based on the exchange of information about agent's interests, knowledge, experience, development and coordination of common goals, values, norms, means and methods of activity. These mechanisms will simplify the process of integrating heterogeneous intelligent agents into a single system, which is especially important when they are created by independent development teams. The paper proposes the functional structure of the cohesive hybrid intelligent multi-agent system, the architectures of its agents, which are necessary for the implementation of the above mechanisms, and also considers the use of the system to solve the problem of planning the restoration of power supply after large-scale accidents.