Development of Analysis Tools for Energy Efficiency Increase of Existing Data Centres

Challenge of analysis and optimization method selection for data centre energy efficiency improvement has been addressed based on several pilot site data centres. Typically energy efficiency has been presented by single performance factor – power usage effectiveness. Full cycle of workflow and methods covering data collection, system modelling and complexity layer definition, data analysis and user feedback and visualization approaches have been discussed and proposed for in-depth analysis and impact on power usage effectiveness examination. Experimental plan is created and higher resolution sensors are selected to analyse thermodynamic behaviour of system and its elements, which will enable AI-based algorithm development for automated analysis, cooling regime optimisation and system behaviour prediction.

[1]  Anatolijs Zabasta,et al.  Development of IoT based Monitoring and Control System for Small Industrial Greenhouses , 2021, 2021 10th Mediterranean Conference on Embedded Computing (MECO).

[2]  Math H.J. Bollen,et al.  Reliability Analysis of Internal Power Supply Architecture of Data Centers in Terms of Power Losses , 2021 .

[3]  Insup Lee,et al.  Stacked LSTM based deep recurrent neural network with kalman smoothing for blood glucose prediction , 2021, BMC Medical Informatics and Decision Making.

[4]  Matteo Sangiorgio,et al.  Robustness of LSTM neural networks for multi-step forecasting of chaotic time series , 2020 .

[5]  Michael Ohadi,et al.  Energy Audit of Data Centers and Server Rooms on an Academic Campus: Impact of Energy Conservation Measures , 2020, 2020 19th IEEE Intersociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems (ITherm).

[6]  Pedro S. Moura,et al.  A review on energy efficiency and demand response with focus on small and medium data centers , 2018, Energy Efficiency.

[7]  Ansis Avotins,et al.  Electrical Power Measurement Method Comparison Using Statistical Analysis , 2018, 2018 IEEE 59th International Scientific Conference on Power and Electrical Engineering of Riga Technical University (RTUCON).

[8]  S. Hochreiter,et al.  Long Short-Term Memory , 1997, Neural Computation.

[9]  Yoshua Bengio,et al.  Learning long-term dependencies with gradient descent is difficult , 1994, IEEE Trans. Neural Networks.

[10]  Gregory D. Hager,et al.  Deep learning: RNNs and LSTM , 2020 .

[11]  P. Apse-Apsitis,et al.  Development and testing results of IoT based air temperature and humidity measurement system for industrial greenhouse , 2018 .