A distributed problem solving system for short-term load forecasting

• Published in: Electric power systems research 1993-04, Vol.26 (3), p.219-224
• Main Authors: Chen, Jiann-Liang, Tsai, Ronlon, Liang, Sheau-Shing
• Format: Article
• Language: English
• Subjects: Applied sciences; blackboard system; distributed problem solving system; Electrical engineering. Electrical power engineering; Electrical power engineering; Exact sciences and technology; knowledge sources; Operation. Load control. Reliability; Power networks and lines; short-term load forecasting
• ISSN: 0378-7796; 1873-2046
• DOI: 10.1016/0378-7796(93)90016-8

Based on the attractive features of both distributed artificial intelligence and existing load forecasting techniques, a distributed problem solving system for short-term load forecasting is proposed. Such a distributed paradigm is a multi-agent system, each processing agent of which can compute autonomously and cooperate with other agents to reason an accurate and satisfactory solution for load forecasting. The designed load forecasting system solves problems using three basic modules: a blackboard module, knowledge sources, and a control mechanism. In addition, to achieve a high degree of accuracy in load forecasting, the existing techniques are embedded in the domain knowledge source and the root mean square error is referred to as the key driven by the constraint knowledge source. This system has been implemented by the expert system tool CLIPS in a SUN network environment and tested with practical data. It was found that the developed distributed system is a valuable tool for system operators for short-term load forecasting.