Data centers as all complex systems are prone to faults, and cost of them can be very high. This paper is focused on detecting the faults in the cooling systems, in particular on local fans level. In the paper, a hybrid approach is proposed. In the approach a model is used as substitute of the real system to generate dataset containing records of both normal and fault cases. On the generated data, machine learning algorithm or ensemble of algorithms are selected and trained to detect the faults. To demonstrate the approach, the rack model of real data center is created, and reliability of the model is shown. Using the model, the dataset with normal as well as abnormal records of data is generated. To detect faults of local fans, simple classifiers are built for all pairs: a local fan – a processor unit. Classifiers are trained on one part of generated data (training data), and then their accuracy is estimated on another part of generated data (test data). A real-time fault detection system is built based on the classifiers. The rack model is used as the substitute of the real plant to check operability of the system.

Smart grid is a Cyber-Physical System with a high level of complexity due to its de-centralized infrastructure. IEC 61850 and IEC 61499 are two industrial standards which can address the challenges introduced by the Smart Grid on the substation automation level. Development of Smart Grid automation software is very time consuming process due to the need to address many requirements and high degree of customisation in every new substation. This limits the adoption of such smart grid technologies as digital substation. This paper aims at addressing this limitation by applying a semi-formal boilerplates model of functional requirements originally presented in informal natural language. The boilerplates are then modelled formally in an ontology for MDE model transformation. The contribution of this paper is the development of the semi-formal and formal boilerplate representation in the form of ontology to formulate Smart Grid requirements and demonstrating how functional requirements can be translated to IEC 61499 control codes using MDE to auto-generate an IEC 61499 PAC control system with structure and control flow. The MDE framework augmented with the requirements models is illustrated on a case study from CIGRE representing different stages of modelling in the proposed framework.

The benefits that arise from the adoption of a systems engineering approach to the design of engineered systems are well understood and documented. However, with software systems, different approaches are required given the changeability of requirements and the malleability of software. With the design of industrial cyber-physical systems, one is confronted with the challenge of designing engineered systems that have a significant software component. Furthermore, that software component must be able to seamlessly interact with both the enterprise’s business systems and industrial systems. In this paper, we present Janus, which together with the GORITE BDI agent framework, provides a methodology for the design of agent-based industrial cyber-physical systems. Central to the Janus approach is the development of a logical architecture as in traditional systems engineering and then the allocation of the logical requirements to a BDI (Belief Desire Intention) agent architecture which is derived from the physical architecture for the system. Janus has its origins in product manufacturing; in this paper, we apply it to the problem of Fault Location, Isolation and Service Restoration (FLISR) for power substations. 

This paper presents an automatic software generation method for energy distribution automation. The method uses the distribution network structure represented in SCL format of the IEC 61850 standard and generates complete executable applications compliant with the IEC 61499 standard. Each equipment element is based on the componentized MVC design pattern and can be executed on a distributed network of HMI and control devices. The challenges solved in this work include design and automatic generation of a library of substation equipment elements according to the MVC design pattern and secondly, automatic generation of SCADA HMI based on the IEC 61850 specification. The design process is demonstrated in a laboratory case study.

The so called Smart Grid is said to be enabled with bi-direction communication networks and energy flow. IEC 61850 is a substation communication standard which improves interoperability of the substation design. IEC 61499 is an automation standard which can be used for implementation of control in IEC 61850 models. This work is utilizing Model Driven Engineering techniques for substation automation systems, specifically using ontology models to automatically generate IEC 61499 distributed automation control systems. eSWRL is the proposed ontology transformation and it is necessary to develop an execution model for executing the transformation rules. This paper explores the use of several execution semantic models for eSWRL and illustrates the use of the most suitable execution model for the context of this work. In the case study, eSWRL rules are written using the execution models discussed in this paper to generate a distributed automation control library in IEC 61499.

This paper proposes a novel method of modelling requirements for smart grid automation systems that fits and complements the leading standards used for software development in smart grid: IEC 61850 and IEC 61499. Ontological representation is used to formally model the systems requirements and the integration of the requirement modelling to be used in conjunction with IEC 61850 specifications and IEC 61499 implementation. The proposed model is illustrated on a case study presented by the CIGRE working group where the system requirement in natural language was firstly modelled in ontology, then implemented in IEC 61499. Lastly, the resulting IEC 61499 control system was tested and validated against the system requirement by signal testing of the end control system.

This paper proposes a method for the automatic generation of smart-grid automation systems software from specifications that includes physical system layout and domain-specific functional “recipes.” The generated software has component organization and implements a decentralized approach to smart grid control, which reduces complexity of automation systems design and modification. The proposed method relies on synergies of two industrial standards IEC 61850 and IEC 61499, which are used to represent a part of the specification and the resulting software model, respectively. Then, the specification model is created in a form of ontology and the generation is based on ontology transformation. The proposed method requires an extension to the Semantic Web Rule Language (SWRL) to support the change of an ontology axioms set for the purpose of ontology transformation. The proposed transformation language, called extended SWRL, is introduced and illustrated in use. The result shows the viability of eSWRL as an ontology transformation language when demonstrated in a power distribution case study system.

In this paper, the aim of automatically generating a cyber-physical control system (more precisely, an IEC61499 control system) is discussed. The method is enabled by ontology models, specifically the source plant ontology model and the target control model for the CPS system implemented in the preferred programming language. The transforming of ontologies is enabled by an extension of SWRL (called eSWRL) and it is introduced here. There interpreter of eSWRL is developed using the Prolog language. A case study Baggage Handling System is used to demonstrate how the ontology models are transformed and the corresponding transforming rules that are developed