Browsing by Author "Yang, Chen Wei"

Filter results by typing the first few letters
Now showing 1 - 4 of 4
  • Automatic Generation of Data centre Digital Twins for Virtual Commissioning of their Automation Systems
    (2023-01-05) Galkin, Nikolai; Ruchkin, Michail; Vyatkin, Valeriy; Yang, Chen Wei; Dubinin, Viktor
     A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä
    Data centres are becoming an increasingly important part of our society's infrastructure. The number of data centres is growing constantly, making growing the gross level of electrical energy consumption. At the same time, the rapid spread of sophisticated electrical devices as well as other automation systems in general produces an opportunity for making data centres an attractive player in the constantly designing energy market. But for this, new advanced technologies must be applied to solve the problems of complexity and heterogeneity in various types of data centre design. A new concept, which is based on the automated generation of a digital twin (DT) system, directly from its schematic representation is presented in this paper. A DT is a virtual version of an object or system, designed to aid decision-making and virtual commissioning through simulation, machine learning, and reasoning. In the scope of current work, the IEC 61850 standard is chosen as a starting point for a multi-step generation of the DT combining simulation model and decentralized control logic. As a result, the designed DT 'clone' of an electrical system consists of the SIMULINK model of the electrical system plus the automatically generated control application (based on the IEC 61499 standard).
  • Methods of data streaming from IEC 61499 applications to Cloud storages
    (2023) Lyu, Tuojian; Galkin, Nikolai; Liakh, Tatiana; Yang, Chen Wei; Vyatkin, Valeriy
     A4 Artikkeli konferenssijulkaisussa
    This paper presents and discusses two methods for collecting data from decentralised control applications designed in IEC 61499 architecture. The topic is justified by the growing use of Cloud-based storage and presentation services in the Internet-of-Things systems. Enabling IEC 61499 devices with the capabilities of storing data in the Cloud and using web-based data presentation and data analytics is of great practical importance. Moreover, what is the most elegant way to configure such data streaming in IEC 61499 is an open question, to solving which this paper aims to provide state-of-the-art information.
  • Towards Extension of Data Centre Modelling Toolbox with Parameters Estimation
    (2021-07) Berezovskaya, Yulia; Yang, Chen Wei; Vyatkin, Valeriy
     A4 Artikkeli konferenssijulkaisussa
    Modern data centres consume a significant amount of electricity. Therefore, they require techniques for improving energy efficiency and reducing energy waste. The promising energy-saving methods are those, which adapt the system energy use based on resource requirements at run-time. These techniques require testing their performance, reliability and effect on power consumption in data centres. Generally, real data centres cannot be used as a test site because of such experiments may violate safety and security protocols. Therefore, examining the performance of different energy-saving strategies requires a model, which can replace the real data centre. The model is expected to accurately estimate the energy consumption of data centre components depending on their utilisation. This work presents a toolbox for data centre modelling. The toolbox is a set of building blocks representing individual components of a typical data centre. The paper concentrates on parameter estimation methods, which use data, collected from a real data centre and adjust parameters of building blocks so that the model represents the data centre most accurately. The paper also demonstrates the results of parameters estimation on an example of EDGE module of SICS ICE data centre located in Luleå, Sweden.
  • Towards reinforcement learning approach to energy-efficient control of server fans in data centres
    (2021-11-30) Berezovskaya, Yulia; Yang, Chen Wei; Vyatkin, Valeriy
     A4 Artikkeli konferenssijulkaisussa
    Modern data centres require control, which aims to improve their energy efficiency and maintain their high availability. This work considers the implementation of a server fan agent, which is intended to minimise the power consumption of the corresponding server fan or group of fans. In the paper, the reinforcement learning approach to energy-efficient control of server fans is suggested. The reinforcement learning workflow is considered. The Simulink blocks simplifying the building of the environment for the reinforcement learning agent are developed. This work provides the framework for creating and training reinforcement learning agents of different types. As the paper is only a work-in-progress, possible type of agents and their training process is described, but training and deploying the agent is a work for the future.