A review on Artificial Intelligence Control System on Chiller Plant
Introduction.
What is Artificial Intelligence Control System.
Real-time data collected from the central control and monitoring system of a district cooling plant on the operation of chillers, cooling towers, water pumps would help optimize the operation of the system and identify energy saving opportunities. This is made possible by the machine learning capability of AI.
AI system can predict and forecast the chiller plant power consumption and cooling demand.
Optimal operational setting can be determined using an optimisation model for real-time chiller plant control, including staging, sequencing, chilled water supply temperature set-point
Efficiency
The just-in-demand design reduces capital cost of the building and free up fund for continuous energy measurement and improving energy efficiency of chiller plant.
Environment (Energy Saving)
Cost (Operational Cost, Life Cycle)
Type of AI Control System
White Box
White box is based on traditional mathematical modelling of heat, mass, energy, and momentum transfer balances in building HVAC system
Black Box
Black box employs data-driven artificial intelligence to understand and model the behaviour of HVAC systems
Grey Box (Hybrid Prediction Control)
Combines black and white box capabilities for improved performance
Power prediction models are built to predict chiller performance.
AI can be employed as the data mining algorithm, with big data analysis based on the actual acquired voluminous operation data by fully considering the characteristics of chiller plants without additional installation of large-sized and high-priced equipment
An optimization algorithm searches for the parameters with the lowest power
prediction
Predictive control strategy was first validated by comparing the predicted outdoor temperature and building cooling load demand with recorded values
– International Standard
Sciencetific Gap
Conclusion
Ref. list must be within Year 2019 – 2024
[1] Loreggia, A., Faccio, F., Mussolin, D., & Zambonin, M. (2022). Simulating Floating Head Pressure Control With Artificial Intelligence. IEEE Access, 10, 125963–125971. https://doi.org/10.1109/ACCESS.2022.3225976
[2] Chan, K. C., Wong, V. T. T., Yow, A. K. F., Yuen, P. L., & Chao, C. Y. H. (2022). Development and performance evaluation of a chiller plant predictive operational control strategy by artificial intelligence. Energy and Buildings, 262, 112017-. https://doi.org/10.1016/j.enbuild.2022.112017
[3] Suen, A. T. Y., Ying, D. T. W., & Choy, C. T. L. (2022). Application of artificial intelligence (AI) control system on chiller plant at MTR station. HKIE Transactions, 29(2), 90–97. https://doi.org/10.33430/v29n2thie-2021-0032
[4] Chan, K. C., Wong, V. T. T., Yow, A. K. F., Yuen, P. L., & Chao, C. Y. H. (2022). Development and performance evaluation of a chiller plant predictive operational control strategy by artificial intelligence. Energy and Buildings, 262, 112017-. https://doi.org/10.1016/j.enbuild.2022.112017
[5] Lee, D., Lin, C.-J., Lai, C.-W., & Huang, T. (2021). Smart-valve-assisted model-free predictive control system for chiller plants. Energy and Buildings, 234, 110708-. https://doi.org/10.1016/j.enbuild.2020.110708
[6] Teimourzadeh, H., Jabari, F., & Mohammadi-Ivatloo, B. (2020). An augmented group search optimization algorithm for optimal cooling-load dispatch in multi-chiller plants. Computers & Electrical Engineering, 85, 106434–12. https://doi.org/10.1016/j.compeleceng.2019.07.020
[7] Danxu Zhang, Luh, P. B., Junqiang Fan, & Gupta, S. (2018). Chiller Plant Operation Optimization With Minimum Up/Down Time Constraints. IEEE Robotics and Automation Letters, 3(1), 9–15. https://doi.org/10.1109/LRA.2017.2723467
[8] Vu, H. D., Chai, K. S., Keating, B., Tursynbek, N., Xu, B., Yang, K., Yang, X., & Zhang, Z. (2018). Data Driven Chiller Plant Energy Optimization with Domain Knowledge. https://doi.org/10.48550/arxiv.1812.00679
[9] Adelekan, D. S., Ohunakin, O. S., & Paul, B. S. (2022). Artificial intelligence models for refrigeration, air conditioning and heat pump systems. Energy Reports, 8, 8451–8466. https://doi.org/10.1016/j.egyr.2022.06.062
[10] Zhang, D., Mittal, K., Wilson, J., Luh, P. B., Fan, J., & Gupta, S. (2019). Efficiency and Reliability Joint Optimization of Chiller Plants Based on a Hybrid Model. IEEE Robotics and Automation Letters, 4(4), 3224–3231. https://doi.org/10.1109/LRA.2019.2924126
[11] Yu, Y. (2020). AI Chiller: An Open IoT Cloud Based Machine Learning Framework for the Energy Saving of Building HVAC System via Big Data Analytics on the Fusion of BMS and Environmental Data. arXiv.Org. https://doi.org/10.48550/arxiv.2011.01047
[12] Yang, C., Gunay, B., Shi, Z., & Shen, W. (2021). Machine Learning-Based Prognostics for Central Heating and Cooling Plant Equipment Health Monitoring. IEEE Transactions on Automation Science and Engineering, 18(1), 346–355. https://doi.org/10.1109/TASE.2020.2998586
[13] Ramaraj, S. (2020). A Hybrid Network Flow Algorithm for the Optimal Control of Large-Scale Distributed Energy Systems. ProQuest Dissertations Publishing.
[14] F. Al Qahtani and M. Muaafa, “Chiller Plant Management Optimization By Artificial Intelligence,” 2022 Saudi Arabia Smart Grid (SASG), Riyadh, Saudi Arabia, 2022, pp. 1-2, doi: 10.1109/SASG57022.2022.10199765.
