Skip to main content
SpringerLink
Log in

Data mining approach for energy efficiency improvements in a utilities supply on a petrochemical plant

  • Original Paper
  • Published:
Evolving Systems Aims and scope Submit manuscript

Abstract

Modeling energy systems is important to generate a range of insights and analyses to improve energy efficiency. However, some details are missing in most end‐use models for industrial systems, which has a profound effect on energy modeling for petrochemical plants. In an enterprise-wide optimization conducted in a petrochemical plant, the unit’s utility consumptions were modeled and some energy efficiency improvements were observed but with seasonality behaviors that were not appropriately represented and explained. The objective of this study was to obtain a relationship between energy efficiency gains with energy market cost (PLD), electricity demand, room temperature and plant load using the following methods: LRM, ARIMA, and Data Mining, comparing their performance in terms of accuracy and easy-of-use. LRM, despite being more used in the literature, was not applicable, ARIMA had a 67.9% goodness-of-fit, and Data Mining had the best results, with 82.8% and 98.8% goodness-of-fits using the M5P and RandomTree algorithms, respectively. In terms of data visualization, Data Mining is easy with the M5P algorithm, but the RandomTree algorithm has a very extensive regression tree, with 975 rows. The approach can support the organizations to empowerment these employees seeking to handle, store, and analyze all the data available on the company. At the end, the best approach to modelling and better understanding the energy efficiency improvements in a utilities supply on a petrochemical plant was stated as a M5P and its framework can be used to support the decision makers.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1

Source: Adapted from

Fig. 2

Source: The Author

Fig. 3

Source: The Author

Fig. 4

Source: The Author. Adapted from the application WEKA

Fig. 5

Source: The Author. Adapted from the application WEKA

Fig. 6

Source: The Author

Similar content being viewed by others

Data availability

The database used in the study results can be found at the Electronic Supplementary material.

Code availability

The codes of the algorithms used can be found at the Weka Software: https://www.cs.waikato.ac.nz/ml/weka/.

References

  • Abramowitz M, Stegun IA (1983) Handbook of mathematical functions with formulas, graphs, and mathematical tables. Applied Mathematics Series. 55 edn. Dover Publications, New York

  • Biscarri F, Monedero I, León C, Guerrero JI, González R, Pérez-Lombard L (2012) A decision support system for consumption optimization in a naphtha reforming plant. Comput Chem Eng 44:1–10

    Article  Google Scholar 

  • Boroojeni KG, Amini MH, Bahrami S, Iyengar S, Sarwat AI, Karabasoglu O (2017) A novel multi-time-scale modeling for electric power demand forecasting: from short-term to medium-term horizon. Electr Power Syst Res 142:58–73

    Article  Google Scholar 

  • Boyd GA, Pang JX (2000) Estimating the linkage between energy efficiency and productivity. Energy Policy 28(5):289–296

    Article  Google Scholar 

  • Contreras J, Espinola R, Nogales FJ, Conejo AJ (2003) ARIMA models to predict next-day electricity prices. IEEE Trans Power Syst 18(3):1014–1020

    Article  Google Scholar 

  • Croonenbroeck C, Hüttel S (2017) Quantifying the economic efficiency impact of inaccurate renewable energy price forecasts. Energy 134:767–774

    Article  Google Scholar 

  • Cuaresma JC, Hlouskova J, Kossmeier S, Obersteiner M (2004) Forecasting electricity spot-prices using linear univariate time-series models. Appl Energy 77(1):87–106

    Article  Google Scholar 

  • D’Oca S, Hong T (2015) Occupancy schedules learning process through a data mining framework. Energy Build 88:395–408

    Article  Google Scholar 

  • de Santana DM, Lourenço SR, Cassiano DA (2017) Enterprise-wide optimization in a petrochemical plant: a MILP approach to energy efficiency improvement. Appl Petrochem Res 7(2):151–160

    Article  Google Scholar 

  • Dubey R, Samantaray SR, Panigrahi BK, Venkoparao VG (2016) Data-mining model based adaptive protection scheme to enhance distance relay performance during power swing. Int J Electr Power Energy Syst 81:361–370

    Article  Google Scholar 

  • Fayyad U, Piatetsky-Shapiro G, Smyth P (1996) From data mining to knowledge discovery in databases. AI Mag 17(3):37–37

    Google Scholar 

  • Fonseca MAG, Faria LS, Lourenço SR (2019) Selection of energy efficiency industrial projects using Topsis method. Int J Dev Res 9:26719–26724

    Google Scholar 

  • Gao Y, Tumwesigye E, Cahill B, Menzel K (2010) Using data mining in optimisation of building energy consumption and thermal comfort management. In Gao TEY, Cahill B, Menzel K (eds), 2010 2nd International Conference on Software Engineering and Data Mining (SEDM) (pp. 434–439). Piscataway: IEEE Xplore

  • Gill SS, Tuli S, Xu M, Singh I, Singh KV, Lindsay D et al (2019) Transformative effects of IoT, blockchain and artificial intelligence on cloud computing: evolution, vision, trends and open challenges. Int Things 8:100118

    Article  Google Scholar 

  • Hand DJ (1998) Data mining: statistics and more? Am Stat 52(2):112–118

    Google Scholar 

  • Henke N, Bughin J, Chui M, Manyika J, Saleh T, Wiseman B et al (2016) The age of analytics: competing in a data-driven world. McKinsey Glob Inst 30:1–28

    Google Scholar 

  • Jonhson NL, Kotz S, Balakrishnan N (1994) Chi-squared distributions including Chi and Rayleigh. Continuous univariate distributions, 2nd edn. Willey

    Google Scholar 

  • Kelechi AH, Alsharif MH, Bameyi OJ, Ezra PJ, Joseph IK, Atayero A-A et al (2020) Artificial Intelligence: an energy efficiency tool for enhanced high performance computing. Symmetry 12(6):1029

    Article  Google Scholar 

  • Maciejowska K, Nowotarski J, Weron R (2016) Probabilistic forecasting of electricity spot prices using factor quantile regression averaging. Int J Forecast 32(3):957–965

    Article  Google Scholar 

  • Martin C, Leurent H (2017) Technology and innovation for the future of production: accelerating value creation. World Economic Forum, Geneva

    Google Scholar 

  • Monedero I, Biscarri F, León C, Guerrero JI, González R, Pérez-Lombard L (2012) Decision system based on neural networks to optimize the energy efficiency of a petrochemical plant. Expert Syst Appl 39(10):9860–9867

    Article  Google Scholar 

  • Mood A, Graybill FA, Boes DC (1974) Introduction to the theory of statistics, 3rd edn. McGraw-Hill

    MATH  Google Scholar 

  • NIST (2006) Engineering statistics handbook—chi-squared distribution. NIST, US Department f Commerce

  • Peral J, Maté A, Marco M (2017) Application of data mining techniques to identify relevant key performance indicators. Comput Stand Interfaces 54:76–85

    Article  Google Scholar 

  • Pfenninger S, Hawkes A, Keirstead J (2014) Energy systems modeling for twenty-first century energy challenges. Renew Sustain Energy Rev 33:74–86

    Article  Google Scholar 

  • Shearer C (2000) The CRISP-DM model: the new blueprint for data mining. J Data Warehous 5(4):13–22

    Google Scholar 

  • Singh MK (2016) Effective big data management and opportunities for implementation. IGI Global, Hershey

    Book  Google Scholar 

  • Tapscott D, Tapscott A (2016) Blockchain revolution: How the technology behind bitcoin is changing money, business, and the world. Penguin Publishing Group, London

    Google Scholar 

  • Velázquez D, González-Falcón R, Pérez-Lombard L, Gallego LM, Monedero I, Biscarri F (2013) Development of an energy management system for a naphtha reforming plant: a data mining approach. Energy Convers Manag 67:217–225

    Article  Google Scholar 

  • Witten IH, Frank E, Hall MA (2011) Data mining: practical machine learning tools and techniques. Morgan Kaufmann, Burlington

    Google Scholar 

  • Yoo I, Alafaireet P, Marinov M, Pena-Hernandez K, Gopidi R, Chang JF et al (2012) Data mining in healthcare and biomedicine: a survey of the literature. J Med Syst 36(4):2431–2448

    Article  Google Scholar 

  • Yu Z, Haghighat F, Fung BC, Yoshino H (2010) A decision tree method for building energy demand modeling. Energy Build 42(10):1637–1646

    Article  Google Scholar 

  • Yu Z, Fung BCM, Haghighat F (2013) Extracting knowledge from building-related data—a data mining framework. Build Simul 6(2):207–222

    Article  Google Scholar 

  • Zhou N, Fridley D, Khanna NZ, Ke J, McNeil M, Levine M (2013) China’s energy and emissions outlook to 2050: perspectives from bottom-up energy end-use model. Energy Policy 53:51–62

    Article  Google Scholar 

Download references

Acknowledgements

None.

Funding

None.

Author information

Authors and Affiliations

  1. Programa de Pós-Graduação em Engenharia Industrial (PEI) and Centro Interdisciplinar em Energia e Ambiente (CIENAM), Federal University of Bahia, Bahia, Brazil

    Delano Mendes de Santana

  2. Department of Engineering, Modeling and Applied Social Sciences, Federal University of ABC, São Paulo, Brazil

    Sérgio Ricardo Lourenço & Douglas Alves Cassiano

Authors
  1. Delano Mendes de Santana
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Sérgio Ricardo Lourenço
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Douglas Alves Cassiano
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

DMS designed the study, performed the experiments and wrote the manuscript; DAC review the manuscript and advise the study; SRL was the co-advisor.

Corresponding author

Correspondence to Delano Mendes de Santana.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (XLSX 528 KB)

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

de Santana, D.M., Lourenço, S.R. & Cassiano, D.A. Data mining approach for energy efficiency improvements in a utilities supply on a petrochemical plant. Evolving Systems 14, 1071–1081 (2023). https://doi.org/10.1007/s12530-023-09515-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12530-023-09515-y

Keywords

Search

Navigation