Remediating critical cause-effect situations with an extended BDI architecture

Remediation actions are performed in scenarios in which consequences of a problem should be promptly mitigated when its cause takes too long to be addressed or is unknown. Such scenarios are recurrent in the real world, including in the context of computer science. Existing approaches that address these scenarios are application-specific. Nevertheless, the reasoning about remediation actions as well as cause identification and resolution, in order to address problems permanently, can be abstracted in such a way that they can be incorporated to autonomous software components, often referred to as agents. They can thus autonomously deal with these scenarios, which we refer to as critical cause-effect situations. In this paper, we propose a domain-independent extension to the belief-desire-intention (BDI) architecture that provides such agents with this automated reasoning. Our work provides an extensible solution to this recurrent problem-solving strategy and allows agents to flexibly deal with resource-constrained scenarios. This solution removes the need for manually implementing the coordination of actions performed by agents, using causal models to capture the knowledge required to carry out this task. Therefore, it not only allows the development of systems with remediative behaviour, but also enables the reduction of development effort by means of a reusable infrastructure that can be used in several different domains. Our approach was evaluated based on an existing solution in the network resilience domain, which showed that our extended agent can autonomously address a network challenge, with a reduction in the development effort and no impact in agent performance.