The objective of this research is development of an Intelligent Distributed Control System (IDCS) for a large-scale power plant. The complex network of sensor/actuators and distributed systems inherent in modern large-scale power plants immediately suggests a Multi-Agent System (MAS) as a viable solution. To operate a large-scale power plant, the monitoring and control systems are distributed and automated for each subsystem in the power plant. The approach is to use MAS, which allows implementation of significantly more sophisticated measures to compensate for the unsecure and nonrobust properties plaguing traditional control systems.
The intellectual merit of this research is that MAS is well suited for distributed control of power plants since the resulting cooperative and negotiated solutions provide the ability for distributed autonomy, robust control, and flexible auto configuration. Current power plants use only centralized or loosely decentralized control schemes and require continuous intervention by the operator, while MAS can manage the power plant operation by itself.
The broader impact of this research includes creation of a powerful unified tool for monitoring and control of power plants; an operational environment that is secure, fuel efficient, and provides practical and realistic infrastructure; and application in a broad range of engineering problems including nuclear plants, fuel cell plants, and power grids. With over 32.4% of current generation coming from coal alone, it is important to burn these fuels as efficiently and cleanly as possible. MAS paints a coherent picture for operators and will be useful as a training tool for workforces in energy systems. The MAS-IDCS facility will be utilized in developing courses in Power Systems Control and Computational Intelligence, and will be attractive in recruiting diversified groups of students.
OUTCOME REPORT This research seeks to develop an Intelligent Distributed Control System (IDCS) for a large-scale industrial system, namely, the power plant. Large scale systems pose significant technical challenges when solving optimization problems and seeking to satisfy multiple objectives, especially when trying to achieve robust performance in a dynamic environment. The complex network of sensor/actuators and distributed subsystems inherent in modern large-scale power plants immediately suggests a Multi-Agent System (MAS) as a viable solution technique. The fundamental principle of the MAS is improvement of the interaction between agents, which are autonomous, robust, and flexible software monitoring and control programs. In order to operate a large-scale power plant, the monitoring and control systems are distributed and automated for each subsystem in the power plant. State-of-the-art architectures of the MAS are used to develop monitoring and control systems to provide not only stable and maneuverable operation, but also more autonomous, efficient, and optimal operation of the power plant. The control systems will consist of a reference governor, intelligent identification system, modified predictive optimal control system, and learning and adaptation functions. Finally, the configuration of the MAS-based IDCS will be developed to allow the dynamic reorganization of subsystems for better global and local performance. The primary intellectual merit of the proposed research is that MAS is well suited for distributed control of power plants since the resulting cooperative and negotiated solutions provide the ability for distributed autonomy, robust control, and flexible auto configuration. In addition, a powerful level of abstraction is provided to make the problem more tractable. Current power plants use only strictly centralized or loosely decentralized control schemes. The MAS can manage the power plant operation by itself, while an operator’s intervention is continuously needed for adequate operation of the conventional control systems. In an emergency, the MAS monitoring and control systems can handle many problems a human operator is not quick enough to react to, and then quickly employ self-healing mechanisms that eliminates the problem or provides enough time for the operator to resolve the issue. Although different MAS architectures are introduced in various applications, the proposed architectures for the single agents and MAS are unique to the application of modular systems. Not only can a single agent pursue a task proactively, but clustered agents can solve problems together, so that the intelligence functions become more powerful. The proposed dynamic organization makes it possible to reconfigure agents ad hoc for optimal plant operation. Additionally, MAS can employ modern security advancements and firewalls to protect critical information, while current SCADA systems are highly vulnerable to attack. The Broader Impact of the proposed research is widespread. Since the MAS provides a unified and powerful tool for monitoring and control of power plants, the research communities and utility industries will be presented with a new foundation for the operation of power plants. Moreover, the project includes contributions to the fields of control and software engineering through the proposed distributed designs. The outcome of this interdisciplinary research effort will be reflected in the graduate EE curriculum by a proposed graduate course in intelligent control, thereby allowing the training of highly skilled human resources for the power industry. The proposed MAS promises to offer an optimal operational environment in power plants that is secure, fuel efficient, and will provide practical and realistic infrastructure. Moreover, the concept of MAS has potential applications in a broad range of engineering problems including nuclear plants, fuel cell plants, shipboard power plants, space power stations, smart grids, oil refineries and chemical plants. Society stands to benefit in multiple ways from this research. Perhaps the most important use of this technology will be its implementation in fossil fuel generators, where optimization can be used to concurrently reduce pollution, increase efficiency, and extend component lifetime. With over 13 GW of planned additional generating capacity from coal, gas and petroleum in the next 4 years, and 32.4% of current generation coming from coal alone, it is important to burn these fuels as efficiently and cleanly as possible. Enhanced operation should also decrease the maintenance costs of the plant while improving efficiency. A final benefit of the MAS system is the coherent picture it paints for operators and its use as a training tool. Because many power system problems are caused by lack of information or improper training of the human operators, this broader impact is of singular importance.
