Prediction of Natural Gas Consumption in Different Regions of China Using a Hybrid MVO‐NNGBM Model

In March 2020, a lockdown was imposed due to a global pandemic, which contributed to changes in the structure of the consumption of natural gas. Consumption in the industry and the power sector decreased while household consumption increased. There was also a noticeable decrease in natural gas consumption by commercial consumers. Based on collected data, such as temperature, wind strength, duration of weather events, and information about weather conditions on preceding days, models for forecasting gas consumption by commercial consumers (hotels, restaurants, and businesses) were designed, and the best model for determining the impact of the lockdown on gas consumption by the above-mentioned consumers was determined using the MAPE (mean absolute percentage error). The best model of artificial neural networks (ANN) gave a 2.17% MAPE error. The study found a significant decrease in gas consumption by commercial customers during the first lockdown period.

show abstract

“…Literature is abundant with literature reviews [65][66][67][68]. One can select core areas where gas consumption forecasts are drafted.…”

Section: Literature Reviewmentioning

confidence: 99%

Indirect Impact of the COVID-19 Pandemic on Natural Gas Consumption by Commercial Consumers in a Selected City in Poland

et al. 2022

View full text Add to dashboard Cite

show abstract

“…40 Furthermore, some researchers have tried to combine the gray forecasting model with other theories to forecast natural gas consumption. Wang et al 41 and Wu and Shen 42 established the least squares support vector machine model based on gray-related analysis, and design the weighted adaptive second-order particle swarm optimization algorithm to optimize the model's parameters. Lu et al 43 propose an improved kernel-based nonlinear extension of the Arps model optimized by the gray wolf optimization algorithm to predict natural gas consumption in the US.…”

Section: Introductionmentioning

confidence: 99%

Short‐term natural gas consumption prediction based on wavelet transform and bidirectional long short‐term memory optimized by Bayesian network

Liu²,

Qiao

2022

Energy Science & Engineering

View full text Add to dashboard Cite

In the energy structure, natural gas is an important clean energy, and its consumption forecast is of great significance for energy policy formulation, pipeline network planning design, and peak shaving capacity determination. In the field of forecasting, wavelet transform (WT) is widely used to process time series, especially natural gas consumption. However, in the application of the WT, the wavelet's orders and levels are randomly fixed. To solve this problem, this study proposes a hybrid model, which is based on bidirectional long short‐term memory (BiLSTM). In addition, Bayesian networks are used to optimize the hyperparameters of BiLSTM. And the different wavelets' orders and levels are utilized to deal with the daily natural gas consumption (DNLGSCN). When each level of Coiflets wavelets' four and five orders are used to process the DNLGSCN, the fifth level of Coiflets wavelets' four and five orders have the highest prediction accuracy, respectively, which is 0.3318 and 0.1773, taking U1 as an example. Using Symflets wavelet to decompose the DNLGSCN also gives the same result. Compared with the decomposition method (e.g., ensemble empirical mode decomposition), the prediction performance of the above four wavelet decomposition methods is better. The main conclusions are that decomposing the DNLGSCN with the fifth level of Coiflets wavelet's five orders has the best prediction performance.

show abstract

“…Li [37] proposed a grey model with the regression method, and proposed the GM-ARIMA model to predict the annual average new installed capacity of China's coal-fired growth in 2017e2026, which will reach 740 GW. Wang et al [38] used the MVO-MNGBM model to predict that natural gas consumption will reach 354.1 billion cubic meters by 2020 in different regions of China. The third type is the grey model optimized by an optimization algorithm.…”

Section: Introductionmentioning

confidence: 99%

A Novel Riccati Equation Grey Model And Its Application In Forecasting Clean Energy

Luo

Duan

2020

Energy

View full text Add to dashboard Cite

Objective: and accurate prediction of clean energy can supply an important reference for governments to formulate social and economic development policies. This paper begins with the logistic equation which is the whitening equation of the Verhulst model, introduces the Riccati equation with constant coefficients to optimize the whitening equation, and establishes a grey prediction model (CCRGM(1,1)) based on the Riccati equation. This model organically combines the characteristics of the grey model, and flexibly improves the modelling precision. Furthermore, the nonlinear term is optimized by the simulated annealing algorithm. To illustrate the validation of the new model, two kinds of clean energy consumption in the actual area are selected as the research objects. Compared with six other grey prediction models, CCRGM(1,1) model has the highest accuracy in simulation and prediction. Finally, this model is used to predict the nuclear and hydroelectricity energy consumption in North America from 2019 to 2028. The results predict that nuclear energy consumption will keep rising in the next decade, while hydroelectricity energy consumption will rise to a peak and subsequently fall back, which offers important information for the governments of North America to formulate energy measures.

show abstract

Prediction of Natural Gas Consumption in Different Regions of China Using a Hybrid MVO‐NNGBM Model

Cited by 10 publications

References 39 publications

Indirect Impact of the COVID-19 Pandemic on Natural Gas Consumption by Commercial Consumers in a Selected City in Poland

Indirect Impact of the COVID-19 Pandemic on Natural Gas Consumption by Commercial Consumers in a Selected City in Poland

Short‐term natural gas consumption prediction based on wavelet transform and bidirectional long short‐term memory optimized by Bayesian network

A Novel Riccati Equation Grey Model And Its Application In Forecasting Clean Energy

Contact Info

Product

Resources

About