Analysis of the factors influencing the electricity consumption in a confectionery plant

被引:0
作者
Abourriche, Youness [1 ,2 ]
Tighazoui, Ayoub [1 ]
Zint, Virginie [1 ]
Rose, Bertrand [1 ]
Boudes, Jean-Francois [3 ]
Mauer, Daniel [3 ]
Waldburger, Patrick [3 ]
机构
[1] Univ Strasbourg, ICube Lab, CNRS 7357, Strasbourg, France
[2] INSA Ctr Val Loire, Blois, France
[3] CPK CARAMBAR & CO, Strasbourg, France
关键词
Electricity forecasting; Energy optimization; Multiple regression; Confectionery plant; Significant energy uses; ENERGY-CONSUMPTION; LINEAR-REGRESSION; OPTIMIZATION; EFFICIENCY; DEMAND; DESIGN;
D O I
10.1007/s12053-025-10313-5
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
With growing environmental concerns, the management of energy consumption has become a key focus for production firms. Consequently, increased attention has been directed by decision-makers and academic researchers toward modeling and forecasting energy consumption. However, only a limited number of studies have specifically examined electricity consumption modeling for industrial cases. To address this gap, an analysis was conducted to identify the factors influencing electricity consumption in a specific case from the confectionery industry in France. Multiple linear regression and multiple exponential regression techniques were utilized to establish an equation correlating consumption with various influencing factors. By examining a comprehensive set of factors, including production volume, operating hours, ambient temperature, and water flow of air handling units, a thorough understanding of the relationship between these factors and electricity consumption in significant energy uses was achieved. The analysis of data collected from a representative confectionery plant revealed significant correlations between the influencing factors and electricity consumption. Based on the derived equation, a model was proposed to estimate electricity consumption using the values of these influencing factors. Additionally, a user-friendly interface was designed, enabling plant operators to apply the model with ease. The findings of this study motivated the company to explore decarbonization initiatives, leading to notable energy savings and a positive financial impact. These insights contribute to a deeper understanding of the drivers of electricity consumption in the confectionery industry and offer valuable guidance for developing strategies to optimize energy usage and enhance sustainability in this sector.
引用
收藏
页数:24
相关论文
共 42 条
  • [1] Modelling and forecasting hourly electricity demand in West African countries
    Adeoye, Omotola
    Spataru, Catalina
    [J]. APPLIED ENERGY, 2019, 242 : 311 - 333
  • [2] Al-Ghandoor A, 2009, JORDAN J MECH IND EN, V3, P69
  • [3] Arjun N. N., 2014, 2014 International Conference on Data Science & Engineering (ICDSE), P171, DOI 10.1109/ICDSE.2014.6974632
  • [4] Balac Natasha, 2013, 2013 IEEE International Conference on Big Data, P657, DOI 10.1109/BigData.2013.6691635
  • [5] Electricity consumption forecasting in Italy using linear regression models
    Bianco, Vincenzo
    Manca, Oronzio
    Nardini, Sergio
    [J]. ENERGY, 2009, 34 (09) : 1413 - 1421
  • [6] Integrating energy efficiency performance in production management - gap analysis between industrial needs and scientific literature
    Bunse, Katharina
    Vodicka, Matthias
    Schoensleben, Paul
    Bruelhart, Marc
    Ernst, Frank O.
    [J]. JOURNAL OF CLEANER PRODUCTION, 2011, 19 (6-7) : 667 - 679
  • [7] Electricity load dynamics, temperature and seasonality Nexus in Algeria
    Chabouni, Naima
    Belarbi, Yacine
    Benhassine, Wassim
    [J]. ENERGY, 2020, 200 (200)
  • [8] Optimal modeling of combined cooling, heating, and power systems using developed African Vulture Optimization: a case study in watersport complex
    Chen, Liang
    Huang, Huan
    Tang, Panyu
    Yao, Dong
    Yang, Haonan
    Ghadimi, Noradin
    [J]. ENERGY SOURCES PART A-RECOVERY UTILIZATION AND ENVIRONMENTAL EFFECTS, 2022, 44 (02) : 4296 - 4317
  • [9] The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation
    Chicco, Davide
    Warrens, Matthijs J.
    Jurman, Giuseppe
    [J]. PEERJ COMPUTER SCIENCE, 2021,
  • [10] Building energy performance forecasting: A multiple linear regression approach
    Ciulla, G.
    D'Amico, A.
    [J]. APPLIED ENERGY, 2019, 253