Cooee: An Artificial Intelligence Chatbot for Complex Energy Environments

Contemporary energy platforms are leveraging advanced data management and Artificial Intelligence (AI) capabilities in response to the increasing complexity of energy systems and grids. Despite these advances, it is a non-trivial and challenging task to support the decision-making needs of the human operators of such complex energy-related implementations. Conversational agents or chatbots are a potential emerging technology that can be utilized to address this challenge. Although there is a large body of literature on chatbots in general, they are not robust as they rely on predefined conversational pathways that are inadequate to efficiently address the complexities of dynamic data spaces in energy platforms. The capability of generating answers in real-time by communicating with the dynamic dataspace is crucial as energy management decisions are real-time and time sensitive. In this paper, we present the design and development of Cooee, a chatbot for conversational engagement with the dynamic data spaces of complex energy environments. Cooee leverages state-of-art language models along with rule-based language processing methods for a conversational interaction with dynamic data spaces, which consequently supports and enables decision-making by human experts. We have developed Cooee as a standalone application and then integrated into a real-world energy AI platform deployed within a multi-campus tertiary education institution setting. Cooee was empirically evaluated in this setting and compared with several state-of-the-art Q&A approaches.