# Improving the Energy Efficiency of Industrial Refrigeration Systems by Means of Data-Driven Load Management

^{*}

## Abstract

**:**

## 1. Introduction

## 2. System Description and Problems Addressed

#### Challenges Improving Compressors Performance by Means of Load Management

## 3. Overall Load Management Methodology

#### 3.1. Load Disaggregation

#### 3.2. Load Management

## 4. Experimental Results

## 5. Conclusions and Discussion

## Author Contributions

## Funding

## Acknowledgments

## Conflicts of Interest

## Abbreviations

Symbol | Description |

Agg | Aggregated signal |

B | Number of available evaporators |

C | Compressor |

CBC | COIN-OR branch and cut |

COP | Coefficient of performance |

ETP | Equivalent thermal parameter |

G | Number of switched ON evaporators |

$h$ | Threshold for the optimization algorithm |

I | Number of minutes of a day |

L | Lower boundary of optimization algorithm |

MLP | Multi-layer perceptron |

MPC | Model predictive control |

N | Number of spaces to refrigerate |

NILM | Non-intrusive load monitoring |

p | Pressure |

PID | Proportional-integral-derivative controller |

PLC | Programmable logic controller |

PLR | Partial load ratio |

PCM | Phase change material |

$Q$ | Cooling capacity |

$Q{}^{\prime}$ | Estimated aggregated cooling capacity |

$\widehat{Q}$ | Estimated cooling capacity consumed by an evaporator |

U | Upper boundary of optimization algorithm |

R717 | Ammonia |

S | Space to refrigerate |

$s{p}_{}$ | Suction pressure |

T | Temperature |

${t}_{C}^{ON}$ | Number of minutes with the compressor switched ON per day |

${t}_{C}^{>90}$ | Number of minutes with the compressor above 90% of PLR per day |

TES | Thermal energy storage |

$TSP$ | Temperature set point |

$\Delta T$ | Temperature difference |

${\epsilon}_{T}$ | Temperature error |

${\rho}_{day}$ | Percentage of time that a compressor is above 90% of PLR |

$\tau $ | Number of timesteps elapsed since the evaporator was switched ON |

$\phi $ | Number of timesteps elapsed since the evaporator was switched OFF |

${w}_{}$ | Neural network weighs |

${\lambda}_{}$ | Space to refrigerate status |

${x}_{}$ | Neural network inputs |

## References

- Abdelaziz, E.; Saidur, R.; Mekhilef, S. A review on energy saving strategies in industrial sector. Renew. Sustain. Energy Rev.
**2011**, 15, 150–168. [Google Scholar] [CrossRef] - Antonakakis, N.; Chatziantoniou, I.; Filis, G. Energy consumption, CO 2 emissions, and economic growth: An ethical dilemma. Renew. Sustain. Energy Rev.
**2017**, 68, 808–824. [Google Scholar] [CrossRef][Green Version] - Banjo, S.; Bolaji, B.; Osagie, I.; Fayomi, O.; Fakehinde, O.; Olayiwola, P.; Oyedepo, S.; Udoye, N.E. Experimental analysis of the performance characteristic of an eco-friendly HC600a as a retrofitting refrigerant in a thermal system. J. Physics: Conf. Ser.
**2019**, 1378, 042033. [Google Scholar] [CrossRef] - Oruç, V.; Devecioğlu, A.G. Retrofitting an air-conditioning device to utilize R1234yf and R1234ze(E) refrigerants as alternatives to R22. J. Braz. Soc. Mech. Sci. Eng.
**2018**, 40, 226. [Google Scholar] [CrossRef] - Kojok, F.; Fardoun, F.; Younes, R.; Outbib, R. Hybrid cooling systems: A review and an optimized selection scheme. Renew. Sustain. Energy Rev.
**2016**, 65, 57–80. [Google Scholar] [CrossRef] - Qian, X.; Yang, Y.; Lee, S.W.; Caballes, M.J.L.; Alamu, O.S. Cooling Performance Analysis of the Lab-Scale Hybrid Oyster Refrigeration System. Process.
**2020**, 8, 899. [Google Scholar] [CrossRef] - Li, J.-B.; Xu, S.; Liu, F.-S. Influence of driving speed on absorption/compression hybrid refrigerant cycle. Jilin Daxue Xuebao (Gongxueban)/J. Jilin Univ. (Eng. Technol. Ed.)
**2013**, 43, 291–297. [Google Scholar] - Chen, S.; Liu, X.; Fu, H. Design of Energy-saving Optimized Remote Control System of Chiller Based on Improved Particle Swarm Optimization. In Proceedings of the 2018 5th IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS), Nanjing, China, 23–25 November 2018; pp. 299–304. [Google Scholar]
- Jabari, F.; Mohammadpourfard, M.; Mohammadi-Ivatloo, B. Energy efficient hourly scheduling of multi-chiller systems using imperialistic competitive algorithm. Comput. Electr. Eng.
**2020**, 82, 106550. [Google Scholar] [CrossRef] - Vu, H.D.; Chai, K.S.; Keating, B.; Tursynbek, N.; Xu, B.; Yang, K.; Yang, X.; Zhang, Z. Data Driven Chiller Plant Energy Optimization with Domain Knowledge. In Proceedings of the 2017 ACM on International Symposium on Symbolic and Algebraic Computation, Kaiserslautern, Germany, 25–28 July 2017; pp. 1309–1317. [Google Scholar] [CrossRef][Green Version]
- Sohrabi, F.; Nazari-Heris, M.; Mohammadi-Ivatloo, B.; Asadi, S. Optimal chiller loading for saving energy by exchange market algorithm. Energy Build.
**2018**, 169, 245–253. [Google Scholar] [CrossRef] - Lu, A.; Ding, Q.; Jiang, A. Research on Optimization of Chiller Based on Adaptive Weight Particle Swarm Algorithm. In Proceedings of the 2018 International Conference on Control, Automation and Information Sciences (ICCAIS), Hangzhou, China, 24–27 October 2018; pp. 428–433. [Google Scholar] [CrossRef]
- Afram, A.; Janabi-Sharifi, F. Theory and applications of HVAC control systems – A review of model predictive control (MPC). Build. Environ.
**2014**, 72, 343–355. [Google Scholar] [CrossRef] - Chen, C.; Wang, J.; Heo, Y.; Kishore, S. MPC-Based Appliance Scheduling for Residential Building Energy Management Controller. IEEE Trans. Smart Grid
**2013**, 4, 1401–1410. [Google Scholar] [CrossRef] - Avci, M.; Erkoc, M.; Rahmani, A.; Asfour, S. Model predictive HVAC load control in buildings using real-time electricity pricing. Energy Build.
**2013**, 60, 199–209. [Google Scholar] [CrossRef] - Shoreh, M.H.; Siano, P.; Shafie-Khah, M.; Loia, V.; Catalão, J.P. A survey of industrial applications of Demand Response. Electr. Power Syst. Res.
**2016**, 141, 31–49. [Google Scholar] [CrossRef] - Liang, M.; Meng, Y.; Lu, N.; Lubkeman, D.; Kling, A. HVAC load Disaggregation using Low-resolution Smart Meter Data. In Proceedings of the 2019 IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT), Washington, DC, USA, 18–21 February 2019. [Google Scholar]
- Sala, E.; Kampouropoulos, K.; Delgado-Prieto, M.; Romeral, L. Disaggregation of HVAC load profiles for the monitoring of individual equipment. In Proceedings of the 2016 IEEE 21st International Conference on Emerging Technologies and Factory Automation (ETFA), Berlin, Germany, 6–9 September 2016; pp. 1–6. [Google Scholar] [CrossRef]
- Lin, X.; Tian, Z.; Lu, Y.; Zhang, H.; Niu, J. Short-term forecast model of cooling load using load component disaggregation. Appl. Therm. Eng.
**2019**, 157, 113630. [Google Scholar] [CrossRef] - Xiao, Z.; Yuan, J.; Gang, W.; Zhang, C.; Xu, X. A NILM method for cooling load disaggregation based on artificial neural network. E3S Web Conf.
**2019**, 111. [Google Scholar] [CrossRef][Green Version] - Hovgaard, T.G.; Larsen, L.F.; Edlund, K.; Jørgensen, J.B. Model predictive control technologies for efficient and flexible power consumption in refrigeration systems. Energy
**2012**, 44, 105–116. [Google Scholar] [CrossRef] - Song, M.; Niu, F.; Mao, N.; Hu, Y.; Deng, S.S. Review on building energy performance improvement using phase change materials. Energy Build.
**2018**, 158, 776–793. [Google Scholar] [CrossRef] - Radaideh, A.; Vaidya, U.; Ajjarapu, V. Sequential Set-Point Control for Heterogeneous Thermostatically Controlled Loads Through an Extended Markov Chain Abstraction. IEEE Trans. Smart Grid
**2017**, 10, 116–127. [Google Scholar] [CrossRef] - Mirakhorli, A.; Dong, B. Occupancy behavior based model predictive control for building indoor climate—A critical review. Energy Build.
**2016**, 129, 499–513. [Google Scholar] [CrossRef] - Cirera, J.; Carino, J.A.; Zurita, D.; Ortega, J.A. Semisupervised refrigeration plant cooling disaggregation by means of deep neural network ensemble. In Proceedings of the 2019 IEEE 28th International Symposium on Industrial Electronics (ISIE), Vancouver, BC, Canada, 12–14 June 2019; pp. 1761–1766. [Google Scholar] [CrossRef]
- Azmi, W.H.; Sharif, M.Z.; Yusof, T.M.; Mamat, R.; Redhwan, A.A.M. Potential of nanorefrigerant and nanolubricant on energy saving in refrigeration system—A review. Renew. Sustain. Energy Rev.
**2017**, 69, 415–428. [Google Scholar] - Widell, K.; Eikevik, T. Reducing power consumption in multi-compressor refrigeration systems. Int. J. Refrig.
**2010**, 33, 88–94. [Google Scholar] [CrossRef][Green Version] - Stoecker, W.F. Industrial Refrigeration Handbook; McGraw-Hill Education: New York, NY, USA, 1998. [Google Scholar]
- Huang, P.; Huang, G.; Augenbroe, G.; Li, S. Optimal configuration of multiple-chiller plants under cooling load uncertainty for different climate effects and building types. Energy Build.
**2018**, 158, 684–697. [Google Scholar] [CrossRef] - Sadurni, A.; Oliet, C.; Rigola, J.; Oliva, A. Detailed Unsteady Simulation of Liquid Overfeed Refrigerating Systems. In Proceedings of the 2008 International Refrigeration and Air Conditioning Conference, West Lafayette, IN, USA, 14–17 July 2008; pp. 1–8. [Google Scholar]
- Josep Cirera i Balcells, Miquel Pujal i Curià, Jordi Brull i Noval, Albert Vendrell i Ribera. Industrial overfeed refrigeration system. IEEE Dataport
**2020**. [Google Scholar] [CrossRef] - Blázquez, J.L.F.; Maestre, I.R.; Gallero, F.J.G.; Baladés, J.D.M. Reduction of computation time in building energy performance simulation programs by applying tearing techniques. Energy Build.
**2016**, 130, 667–675. [Google Scholar] [CrossRef] - Mitchell, S.; O’Sullivan, M.; Dunning, I. PuLP: A Linear Programming Toolkit for Python; The University of Auckland: Auckland, New Zealand, 2011. [Google Scholar]
- Cirera, J.; Carino, J.A.; Zurita, D.; Ortega, J.A. Data Analytics for Performance Evaluation Under Uncertainties Applied to an Industrial Refrigeration Plant. IEEE Access
**2019**, 7, 64127–64135. [Google Scholar] [CrossRef] - Cirera, J.; Carino, J.A.; Zurita, D.; Ortega, J.A. A Data-Driven-Based Industrial Refrigeration Optimization Method Considering Demand Forecasting. Processes
**2020**, 8, 617. [Google Scholar] [CrossRef]

**Figure 1.**(

**a**) Refrigeration system scheme. (

**b**) Distribution and area of the spaces to refrigerated in the facilities.

**Figure 3.**Simplified communication diagram of the refrigeration system. The data-driven load management block represents the proposed solution to manage the cooling loads.

**Figure 4.**Example of the performance of two screw compressors C1 and C2 working in parallel to supply the cooling demand.

**Figure 9.**Detail of a specific S temperature with its corresponding assessment in each situation. The green area of the temperature plot represents the permissible temperature range.

**Figure 10.**Simultaneity results. (

**a**) Simultaneity of the proposed method compared with the reference. (

**b**) Minutes saved with the proposed method vs. reference. (

**c**) Percentage of simultaneity that it supposes.

**Figure 11.**Compressor efficiency results. Comparison of percentage of time in high efficiency partial load ratio (PLR).

**Figure 12.**Electrical consumption results. (

**a**) Electrical energy consumption of the proposed method compared with the reference. (

**b**) Energy saved with the proposed method vs. reference. (

**c**) Percentage of energy that it supposes.

**Figure 13.**Temperature error in regard to its set point of the different spaces to refrigerate. (

**a**–

**g**) Error in each space.

Id | Type of Organic Load | N° Evaporators | T Set Point (°C) | Average Working Time Per Day (h) | Area (m^{2}) |
---|---|---|---|---|---|

S1 | Chicken tunnel | 3 | −0.5 | 19 | 1164 |

S2 | Chicken tunnel | 3 | −0.5 | 19 | 1407 |

S3 | Pig tunnel/chamber | 5 | −2/−10 | 14 | 1246 |

S4 | Meat chamber | 4 | 0 | 24 | 270 |

S5 | Meat chamber | 4 | 0 | 24 | 575 |

S6 | Turkey tunnel/chamber | 4 | −2/1 | 19 | 754 |

S7 | Chicken tunnel | 6 | −0.8 | 19 | 684 |

S8 | Quail tunnel | 1 | −0.3 | 3 | 418 |

Feature | Unit | Description |
---|---|---|

${T}_{n,t}$ | °C | Temperature of the spaces at the current timestep t. |

${T}_{n,t-1}$ | °C | Temperature of the space s at time t-1. |

${T}_{n,t-2}$ | °C | Temperature of the space s at time t-2. |

${T}_{n,t-3}$ | °C | Temperature of the space s at time t-3. |

${\mathsf{\tau}}_{n,t}^{\mathrm{g}}$ | Timesteps | Number of timesteps elapsed since the evaporator g of the space s was switched ON at the current timestep t. |

${\mathsf{\phi}}_{n,t}^{\mathrm{g}}$ | Timesteps | Number of timesteps elapsed since the evaporator g of the space s was switched OFF at the current timestep t. |

${G}_{n,t}$ | Units | Number of evaporators switched ON at the space s at the current timestep t. |

$s{p}_{t}$ | Bar | Suction pressure |

${S}_{status}$ | ON/OFF | Evaporator status of each S. If multiple evaporators a logical OR is applied |

${\mathit{h}}^{1}$ | ${\mathit{h}}^{2}$ | ${\mathit{h}}^{3}$ | ${\mathit{h}}^{4}$ | ${\mathit{h}}^{5}$ | ${\mathit{h}}^{6}$ | |
---|---|---|---|---|---|---|

S1 | −1.5 | −0.5 | 0 | 0.4 | −0.2 | 0 |

S2 | −1.5 | −0.5 | 0 | 0.4 | −0.2 | 0 |

S3 | −1.5 | −0.5 | 0 | 0.4 | −0.2 | 0 |

S4 | −2 | −0.5 | 0 | 0.4 | −1.2 | 0 |

S5 | −2 | −0.5 | 0 | 0.4 | −1.2 | 0 |

S6 | −1.5 | −0.2 | 0 | 0.4 | −0.2 | 0 |

S8 | −1.5 | −0.5 | 0 | 0.4 | −0.2 | 0 |

Proposed | Reference | ||||||
---|---|---|---|---|---|---|---|

Date | $\mathit{Q}$ (kWh) | Suction p (bar) | Discharge p (bar) | Date | $\mathit{Q}$ (kWh) | Suction p (bar) | Discharge p (bar) |

2020-04-06 | 29,518 | 1.70 | 8.01 | 2020-01-21 | 28,673 | 1.70 | 8.03 |

2020-04-07 | 28,101 | 1.69 | 8.02 | 2020-01-21 | 28,673 | 1.70 | 8.03 |

2020-04-08 | 30,066 | 1.69 | 8.03 | 2019-10-17 | 30,270 | 1.72 | 8.09 |

2020-04-09 | 23,099 | 1.78 | 8.00 | 2019-12-27 | 23,263 | 1.71 | 8.00 |

2020-04-14 | 35,380 | 1.70 | 8.32 | 2019-06-19 | 31,580 | 1.67 | 8.76 |

2020-04-15 | 31,948 | 1.71 | 8.35 | 2019-10-17 | 30,270 | 1.72 | 8.09 |

2020-04-16 | 33,575 | 1.70 | 8.63 | 2019-06-19 | 31,580 | 1.67 | 8.76 |

2020-04-17 | 30,264 | 1.70 | 8.59 | 2019-08-13 | 30,175 | 1.70 | 8.70 |

© 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Cirera, J.; Carino, J.A.; Zurita, D.; Ortega, J.A.
Improving the Energy Efficiency of Industrial Refrigeration Systems by Means of Data-Driven Load Management. *Processes* **2020**, *8*, 1106.
https://doi.org/10.3390/pr8091106

**AMA Style**

Cirera J, Carino JA, Zurita D, Ortega JA.
Improving the Energy Efficiency of Industrial Refrigeration Systems by Means of Data-Driven Load Management. *Processes*. 2020; 8(9):1106.
https://doi.org/10.3390/pr8091106

**Chicago/Turabian Style**

Cirera, Josep, Jesus A. Carino, Daniel Zurita, and Juan A. Ortega.
2020. "Improving the Energy Efficiency of Industrial Refrigeration Systems by Means of Data-Driven Load Management" *Processes* 8, no. 9: 1106.
https://doi.org/10.3390/pr8091106