Stephen D. J. McArthur

Multi-Agent Systems for Power Engineering Applications—Part I: Concepts, Approaches, and Technical Challenges

This is the first part of a two-part paper that has arisen from the work of the IEEE Power Engineering Societys Multi-Agent Systems (MAS) Working Group. Part I of this paper examines the potential value of MAS technology to the power industry. In terms of contribution, it describes fundamental concepts and approaches within the field of multi-agent systems that are appropriate to power engineering applications. As well as presenting a comprehensive review of the meaningful power engineering applications for which MAS are being investigated, it also defines the technical issues which must be addressed in order to accelerate and facilitate the uptake of the technology within the power and energy sector. Part II of this paper explores the decisions inherent in engineering multi-agent systems for applications in the power and energy sector and offers guidance and recommendations on how MAS can be designed and implemented.

Multi-Agent Systems for Power Engineering Applications—Part II: Technologies, Standards, and Tools for Building Multi-agent Systems

This is the second part of a two-part paper that has arisen from the work of the IEEE Power Engineering Societys Multi-Agent Systems (MAS) Working Group. Part I of this paper examined the potential value of MAS technology to the power industry, described fundamental concepts and approaches within the field of multi-agent systems that are appropriate to power engineering applications, and presented a comprehensive review of the power engineering applications for which MAS are being investigated. It also defined the technical issues which must be addressed in order to accelerate and facilitate the uptake of the technology within the power and energy sector. Part II of this paper explores the decisions inherent in engineering multi-agent systems for applications in the power and energy sector and offers guidance and recommendations on how MAS can be designed and implemented. Given the significant and growing interest in this field, it is imperative that the power engineering community considers the standards, tools, supporting technologies, and design methodologies available to those wishing to implement a MAS solution for a power engineering problem. This paper describes the various options available and makes recommendations on best practice. It also describes the problem of interoperability between different multi-agent systems and proposes how this may be tackled.

The design of a multi-agent transformer condition monitoring system

Online diagnostics and online condition monitoring are important functions within the operation and maintenance of power transformers. This paper describes how a multi-agent system (MAS) for transformer condition monitoring has been designed to employ the data generated by the ultra high frequency (UHF) monitoring of partial discharge activity. It describes the rationale behind the use of multi-agent techniques, and the problems overcome through this technology. Every aspect of the MAS design is discussed. In addition, the design and performance of the intelligent interpretation techniques are detailed.

A multiagent architecture for protection engineering diagnostic assistance

Protection engineers use data from a range of monitoring devices to perform post-fault disturbance diagnosis. In the past, heterogeneous intelligent systems have been developed to interpret the data and provide information to engineers to assist with the disturbance diagnosis task. The majority of these systems remain standalone due to the problems associated with systems integration. This paper proposes the use of multiagent systems for providing a flexible and scalable alternative to existing integration approaches. A novel multiagent system (MAS) has been developed entitled protection engineering diagnostic agents (PEDAs) which integrates a legacy SCADA interpretation system with new systems for digital fault recorder (DFR) record interpretation and for enhancing fault record retrieval from remote DFRs. The use of MAS technology provides a flexible and scalable architecture open to the introduction of new data interpretation systems. The paper discusses the benefits of a multiagent approach and the design and implementation of PEDA.

Distribution power flow management utilising an online Optimal Power Flow technique

This paper describes the current connection regime for distributed generation (DG) in the U.K. and presents a novel application of the optimal power flow (OPF) technique for automatic power flow management (PFM) to manage thermal constraints in distribution networks. OPF formulations have been used, in an offline mode, as a power system planning tool for several years. The novel implementation of OPF for “corrective” PFM in an online operational mode, for MV distribution networks, is presented and tested in this paper. The authors demonstrate, through simulations conducted on a commercially available substation computer, that such an application of OPF can represent first on, last off generator connection agreements that reflect the current principles of access in the U.K. Two case study networks, a 33 kV and an 11 kV, provide the basis for assessment of the OPF-based PFM algorithm in terms of computation time to arrive at a solution in the event of a network thermal excursion and the level of DG curtailment necessary to meet network thermal limits. Assessments are made and fully discussed of the suitability for an OPF-based approach for distribution network management within an online network control scheme including discussion of the important consideration of control robustness.

A Multi-Agent Fault Detection System for Wind Turbine Defect Recognition and Diagnosis

This paper describes the use of a combination of anomaly detection and data-trending techniques encapsulated in a multi-agent framework for the development of a fault detection system for wind turbines. Its purpose is to provide early error or degradation detection and diagnosis for the internal mechanical components of the turbine with the aim of minimising overall maintenance costs for wind farm owners. The software is to be distributed and run partly on an embedded microprocessor mounted physically on the turbine and on a PC offsite. The software will corroborate events detected from the data sources on both platforms and provide information regarding incipient faults to the user through a convenient and easy to use interface.

Automating power system fault diagnosis through multi-agent system technology

Fault diagnosis within electrical power systems is a time consuming and complex task. SCADA systems, digital fault recorders, travelling wave fault locators and other monitoring devices are drawn upon to inform the engineers of incidents, problems and faults. Extensive research by the authors has led to the conclusion that there are two issues which must be overcome. Firstly, the data capture and analysis activity is unmanageable in terms of time. Secondly, the data volume leads to engineers being overloaded with data to interpret. This paper describes how multi-agent system technology, combined with intelligent systems, can be used to automate the fault diagnosis activity. Within the multi-agent system, knowledge-based and model-based reasoning are employed to automatically interpret SCADA system data and fault records. These techniques and the design of the multi-agent system architecture that integrates them are described. Consequently, the use of engineering assistant agents as a means of providing engineers with decision support, in terms of timely and summarised diagnostic information tailored to meet their personal requirements, is discussed.

A generic knowledge-based approach to the analysis of partial discharge data

Partial discharge (PD) diagnosis is a recognized technique to detect defects within high voltage insulation in power system equipment. A variety of methods exist to capture the signals that are emitted during PD, and this paper focuses on the ultra high frequency (UHF) and IEC 60270 techniques. Phase-resolved patterns can be constructed from the PD data captured using either of these techniques and due to the individual signatures that different defects generate, experts can examine the phase-resolved pattern to classify the defect that created it. In recent years, knowledge regarding PD phenomena and phase-resolved patterns has increased, providing an opportunity to employ a knowledge-based system (KBS) to automate defect classification. Due to the consistent physical nature of PD across different high voltage apparatus and the ability to construct phase-resolved patterns from various sensors, the KBS offers a generic approach to the analysis of PD by taking the phase-resolved pattern as its input and identifying the physical PD processes associate with the pattern. This paper describes the advances of this KBS, highlighting its generic application through the use of several case studies, which present the diagnosis of defects captured through both the IEC 60270 and UHF techniques. This paper also demonstrates, in one of the case studies, how a limitation of previous pattern recognition techniques can be overcome by mimicking the approach of a PD expert when the pulses occur over the zero crossings of the voltage waveform of the phase-resolved pattern.

An agent-based anomaly detection architecture for condition monitoring

Online diagnostics and online condition monitoring are important functions within the operation and maintenance of a power plant. When there is knowledge of the relationships between the raw data and the underlying phenomena within the plant item, typical intelligent system-based interpretation algorithms can be implemented. Increasingly, health data is captured without any underlying knowledge concerning the link between the data and their relationship to physical and electrical phenomena within the plant item. This leads to the requirement for dynamic and learning condition monitoring systems that are able to determine the expected and normal plant behavior over time. This paper describes how multi-agent system technology can be used as the underpinning platform for such condition monitoring systems. This is demonstrated through a prototype multi-agent anomaly detection system applied to a 2.5-MW diesel engine driven alternator system.

A frequency-based RF partial discharge detector for low-power wireless sensing

Partial discharge (PD) monitoring has been the subject of significant research in recent years, which has given rise to a range of well-established PD detection and measurement techniques, such as acoustic and RF, on which condition monitoring systems for highvoltage equipment have been based. This paper presents a novel approach to partial discharge monitoring by using a low-cost, low-power RF detector. The detector employs a frequency-based technique that can distinguish between multiple partial discharge events and other impulsive noise sources within a substation, tracking defect severity over time and providing information pertaining to plant health. The detector is designed to operate as part of a wireless condition monitoring network, removing the need for additional wiring to be installed into substations whilst still gaining the benefits of the RF technique. This novel approach to PD detection not only provides a low-cost solution to on-line partial discharge monitoring, but also presents a means to deploy wide-scale RF monitoring without the associated costs of wide-band monitoring systems.