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

Abstract

A common denominator in the vast majority of processes in the food industry is refrigeration. Such systems guarantee the quality and the requisites of the final product at the expense of high amounts of energy. In this regard, the new Industry 4.0 framework provides the required data to develop new data-based methodologies to reduce such energy expenditure concern. Focusing in this issue, this paper proposes a data-driven methodology which improves the efficiency of the refrigeration systems acting on the load side. The solution approaches the problem with a novel load management methodology that considers the estimation of the individual load consumption and the necessary robustness to be applicable in highly variable industrial environments. Thus, the refrigeration system efficiency can be enhanced while maintaining the product in the desired conditions. The experimental results of the methodology demonstrate the ability to reduce the electrical consumption of the compressors by 17% as well as a 77% reduction in the operation time of two compressors working in parallel, a fact that enlarges the machines life. Furthermore, these promising savings are obtained without compromising the temperature requirements of each load.

Grey Box Modelling of Supermarket Refrigeration Room

“…A promising approach to data-driven modeling and optimization of refrigeration systems is with neural networks and predictive control presented in [3] to increase the efficiency of the compressor in a refrigeration system. This is later shown in [4], where an energy reduction of 17% was achieved.…”

A Systematic Literature Review on Data-Driven Residential and Industrial Energy Management Systems

“…In industrial EMSs, Cirera et al [60] propose a data-driven methodology that improves the refrigeration systems' efficiency on the load side. They validate the NILM approach with a MATLAB simulation.…”

“…Choobineh and Mohaghehghi [73] distinguish between direct load control, where the utility directly shuts down the load remotely, and indirect load control, where the customer receives an optional request from the utility. Both Cirera et al [60] and Wang et al [71] increase flexibility by exploiting the users' indifference to minor temperature changes, considering the modification of a refrigerator within desired temperature bounds [60] and heating, ventilation, and air conditioneing [71]. In addition, material buffers are integrated [66,67] to increase industrial flexibility.…”

“…Advanced industrial EMSs are equipped with sensors to measure physical and electrical quantities, including voltages, power flows, and environmental conditions such as temperature, humidity, or vibration [73], frequencies, and heat flows [60]. Cirera et al [60] operate a refrigeration system, employing the pressure sensors WIKA S20 (WIKA Alexander Wiegand SE, Klingenberg, Germany), the temperature sensors WIKA T15.H (WIKA Alexander Wiegand SE, Klingenberg, Germany), or valve positioning reeds, and integrate the controllers 319-3 (Siemens, Munich, Germany) and S7-200 (Siemens, Munich, Germany) to communicate with a relational MySQL database.…”

“…In addition, industrial EMSs include hydrogen production [65]. While residential EMSs include occupancy detection [25,34], presence detectors [50], and indoor temperature [50] for environmental data, industrial EMSs also consider pressure sensors [60], temperature sensors [60], humidity and vibration [73]. Only residential EMSs consider user data, namely consumers' preferences and priorities for various applications [53], consumers' comfort levels [23,43,50], and consumers' location [50].…”