AI applications in power systems operation

Despite the high degree of satisfaction reported by the electric utilities which pioneered the implementation of expert systems in their control centres, the number of actual implementations of such systems in control centres remains quite small compared to the number of systems successfully demonstrated in prototype form. This discrepancy suggests that these companies have unanswered concerns about the cost and difficulty of integrating expert systems into their energy management system (EMS). These concerns must be addressed before this technology finds wider acceptance in power system operation. This paper begins by analyzing the reasons why integrating an expert system in an EMS is more complex and costly than adding a conventional advanced application program. Based on this analysis, the interfaces which must be provided to achieve an effective integration are defined. It is then argued that artificial intelligence applications should not be integrated directly into the EMS but should be "plugged" in an "AI environment" supporting the necessary interfaces with the EMS and providing common services to the applications.