An improved forecasting model of short-term electric load of papermaking enterprises for production line optimization

Changzhi Lai, Yu Wang, Kai Fan, Qilin Cai, Qing Ye, Haoqiang Pang and Xi Wu

Energy, 2022, vol. 245, issue C

Abstract: The load forecasting is generally based on historical data extrapolation in most forecasting models, resulting in a poor correlation with the production information and significant application limitations. To improve this, the production information-based backpropagation neural network (BPNN) combined with genetic algorithm (GA) and particle swarm optimization (PSO) hybrid forecasting model was established for a papermaking enterprise with the three-level electric data collected. Based on this, shift electric consumption quotas and air compressor transformation energy-saving predictions were proposed. The results show that when the production management information is included, the average mean absolute percent error (MAPE) of the six forecasting results can be 1.2%, an improvement of 18.3% on average, indicating the high accuracy of our proposed model. The unit energy consumption of paper products can be reduced by 3.26% through management optimization using the proposed shift electric consumption quotas. Under the guidance of energy-saving predictions, the overall power saving rate of the production line after the enterprise reforms the air compressor is 3%. The proposed load-forecasting model and energy optimization methods have high accuracy and practical applicability.

Keywords: Papermaking enterprise; Data acquisition; Short-term electric load forecasting; Hybrid BP neural Network; Energy-saving transformation guidance (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (3)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544222001281
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:245:y:2022:i:c:s0360544222001281

DOI: 10.1016/j.energy.2022.123225

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().