Mid-term energy consumption predicting model for natural gas pipeline considering the effects of operating strategy

• Published in: Energy conversion and management 2022-12, Vol.274, p.116429, Article 116429
• Main Authors: Shui, Chongyuan, Zhou, Dengji, Hao, Jiarui, Zhang, Na, Wang, Chen, Bu, Xiangqi, Shao, Tiemin
• Format: Article
• Language: English
• Subjects: administrative management; Compressor station; Energy consumption prediction; energy conversion; natural gas; Natural gas pipeline; oil and gas industry; Operating strategy; prediction
• ISSN: 0196-8904
• DOI: 10.1016/j.enconman.2022.116429

•A mid-term energy consumption predicting model for natural gas pipeline was proposed.•Annual cost can be accurately predicted with monthly transmission plan as the sole input.•Operating strategy and scheme were defined and introduced to obtain high accuracy.•Seasonal correction method was validated the best to train the model from historical data. Natural gas transmission with pipeline takes a large part of energy consumption in the natural gas industry, whose energy consumption prediction plays a vital role in its planning and management. Currently used energy consumption prediction methods are usually based merely on energy consumption data and experience. However, lacking the support of mechanism, especially the operating scheme, these plausible methods can yield large error if the gas transmission plan varies drastically. Towards this concern, this work proposed an energy consumption predicting model based on the operating strategy and the subsequent working mechanism of compressor stations. Strategies to ascertain appropriate operating scheme for prediction were proposed based on historical working data. With proper training, the model can render future annual energy consumption accurately, with monthly gas transmission plan as the sole input. Considering the different operating strategies and working status, validations and analyses were presented based on the proposed model, which revealed the influential factors for the energy consumption predicting.