Parameter Variation & the Components of Natural Gas Price Volatility

Distributed peak-shaving heat pump technology is to use a heat pump to adjust the heat on the secondary network in a substation, with features of low initial investment, flexible adjustment, and high operating cost. The paper takes an example for the system that uses two 9F class gas turbines (back pressure steam) as the basic heat source and a distributed heat pump in the substation as the peak-shaving heat source. The peak-shaving ratio is defined as the ratio of the designed peak-shaving heat load and the designed total heat load. The economic annual cost is taken as a goal, and the optimal peak-shaving ratio of the system is investigated. The influence of natural gas price, electricity price, and transportation distance are also analyzed. It can provide the reference for the optimized design and operation of the system.

Download Full-text

Guidance needed on use of natural gas price escalator clauses

10.2172/6714845 ◽

1980 ◽

Author(s):

E. Staats

Keyword(s):

Natural Gas ◽

Gas Price

Download Full-text

News-Based Research on Forecast of International Natural Gas Price Trend

Fuzzy Systems and Data Mining VI - Frontiers in Artificial Intelligence and Applications ◽

10.3233/faia200699 ◽

2020 ◽

Author(s):

Tianxiang Li ◽

Xiaosong Han ◽

Aoqing Wang ◽

Hui Li ◽

Guosheng Liu ◽

...

Keyword(s):

Time Series ◽

Deep Learning ◽

Natural Gas ◽

Predictive Accuracy ◽

Price Trend ◽

Learning Network ◽

Natural Gas Prices ◽

Deep Learning Network ◽

Sentiment Score ◽

Gas Price

In this paper, we build a deep learning network to predict the trends of natural gas prices. Given a time series, for each day, the gas price trend is classified as “up” and “down” according to the price compared to the last day. Meanwhile, we collect news articles as experimental materials from some natural gas related websites. Every article was then embedded into vectors by word2vec, weighted with its sentiment score, and labeled with corresponding day’s price trend. A CNN and LSTM fused network was then trained to predict price trend by these news vectors. Finally, the model’s predictive accuracy reached 62.3%, which outperformed most of other traditional classifiers.

Download Full-text