Natural Gas Consumption Research Articles

The general conformable fractional grey system model and its applications

As a mathematical instrument, the fractional order grey system model can be employed to characterize uncertain real-world data. This paper presents new definitions for the generalized conformable fractional accumulation (GCFA) and the generalized conformable fractional difference (GCFD). For the first time, complex network theory explains the modelling mechanisms of accumulation. Then a novel generalized conformable fractional grey model (GCFGM(1,1)) is proposed based on the GCFA and GCFD, and the particle swarm optimizer (PSO) method is employed to optimize its fractional order. In this study, the proposed model is applied to the prediction of China’s overall energy consumption, natural gas consumption, and gross domestic product. Our research reveals that our proposed model achieves mean absolute percentage error (MAPE) values of less than 5% on real datasets from 9 different regions, outperforming other comparative models. These key empirical findings demonstrate the superiority of our model in accurately predicting relevant variables.

Assessment of the impact of setting the heating curve on reducing gas consumption in a residential building while ensuring thermal comfort

Due to the large share of the residential building sector in CO2 emissions, it is necessary to look for quick-to-implement and cost-free solutions for heating systems aimed at increasing their efficiency and reducing fuel consumption. The aim of the study is a multi-aspect assessment of the proper setting of the heating curve in the weather controller of a low-temperature floor heating system with a condensing gas boiler, and an analysis of the impact of the heating curve slope on the natural gas consumption, the emission of gaseous and dust pollutants and on maintaining appropriate indoor air parameters: air temperature, operative temperature and PMV and PPD. A wide range of simulation tests were carried out using the TRNSYS software for an existing energy-efficient single-family residential building, with mechanical ventilation with heat recovery, located in north-eastern Poland in Bialystok. Changing the heating curve slope by 0.1 can reduce gas consumption and pollutant emissions by 1.6–10.3 %. Low heating curve slopes may result in failure to reach the temperature set by users (difference between the set and achieved indoor temperature up to 1.9 K), while maintaining standard thermal comfort parameters (−0.5<PMV<+0.5; PPD<10 %). Reducing the indoor air temperature by 2 K can contribute to reducing gas consumption by 11 % while maintaining standard thermal comfort parameters. Changing the heating curve slope is one of the effective methods of reducing fuel consumption in the building. Results are useful for users of buildings equipped with low-temperature heating systems with floor heating and installers of these systems.

Modeling, prediction and analysis of natural gas consumption in China using a novel dynamic nonlinear multivariable grey delay model

Accurately predicting natural gas consumption is essential for developing a clean, low-carbon, safe, and efficient energy system. Therefore, this paper integrates the idea of the extended logistic model into multivariable grey prediction theory. Considering the delay effect and nonlinear characteristics of the system, a novel dynamic nonlinear multivariate grey delay prediction model is constructed. Meanwhile, the algorithmic framework for solving the parameters of the new model is provided to identify and optimize the parameters of the time-delay effect of the model. The genetic algorithm was identified as the best matching optimization algorithm for the new model. Furthermore, the new model is applied to fitting and forecasting China's natural gas consumption, and the validity of the model is fully verified. Compared with other forecasting models, the new model has a lower average relative error in the fitting and forecasting stage, and, in particular, achieves a better forecasting effect with the lowest MAPEpre value (0.001 % for one-step ahead, 0.005 % for two-step ahead, and 0.746 % for three-step ahead). Moreover, the model is employed to forecast China's natural gas consumption for the next five years, providing a robust foundation for government policies related to the supply of natural gas.

Can we see differences between the 14C activities of urban (Zagreb) and rural (Cvetković) sites (central Croatia)?

Radiocarbon (Δ14C) was measured for four years (2019–2022) in Zagreb (Croatia) and in Cvetković village near Jastrebarsko (Zagreb County, Croatia) to see whether there are differences between the city site and the rural one because of the fossil fuel combustion. The δ13CCO2 was measured as grab samples once in a month in period December 2020–November 2022. The bomb-produced 14C has been globally distributed across the planet, but the combustion of fossil fuels that do not contain 14C causes a local effect of lowering Δ14C. Zagreb is considered to be a location with heavy fossil fuel combustion as compared to the Cvetković (rural site). Monthly 14C activity at Zagreb is constantly below the 14C activity at Cvetković. Mean 14C activity at Zagreb (Δ14CZagreb = −18.4 ± 2.6 ‰) is lower than that in Cvetković (Δ14CCve = −2.9 ± 2.1 ‰) due to fossil fuel combustion in the city of Zagreb. This is especially pronounced during winter when the mean value in Zagreb is Δ14CZagreb = −26.0 ± 4.3 ‰ and in Cvetković Δ14CCve = −5.9 ± 3.4 ‰.Natural gas consumption was used as the proxy for fossil fuel combustion, and it shows better correlation with Δ14C in Zagreb than in Cvetković. The Δ14C difference, Δ14CCve ‒ Δ14CZagreb, becomes statistically negligible when natural gas consumption is small.No difference is observed on δ13CCO2; in Zagreb mean δ13CCO2 is −11.0 ± 1.3 ‰, and in Cvetković −11.4 ± 1.4 ‰. Lower δ13CCO2 values are observed in winter (Zagreb −11.9 ± 1.1 ‰, −12.2 ± 1.5 ‰ Cvetković) than in summer (−10.1 ± 0.8 ‰ vs. −10.4 ± 1.0 ‰) at both locations. Together with higher Δ14C in Cvetković, it indicates that at the area of Cvetković biogenic samples of modern origin (biomass, wood) as energy source for heating is more pronounced.

Development and implementation of technological measures to extend the campaign of blast furnace No. 5 of PJSC Severstal

The work presents generalized experience in the development and implementation at PJSC Severstal of technological measures to extend the campaign of blast furnace No. 5. The authors carried out an analysis, identified and described the problem areas, generalized the principles for ensuring the safety of the shaft lining, boshes and metal receiver of the blast furnace. The results of a study of the working space of blast furnace No. 5 in 2006 are also presented. The identified technological factors ensure an increase in duration of the unit campaign. Technolo­gical measures are given for: washing the blast furnace hearth, reducing chemical erosion of the carbon blocks of the hearth and flange, forming a protective skull in the blast furnace shaft, special methods for loading solid coke substitutes, and organizing an effective structure of the charge column in the blast furnace. It is necessary to use digital models integrated into the blast furnace expert system for operational control of blast furnace technology. The results of the current blast furnace campaign were compared with previous ones. It was proven that the systematic use of all elements of the developed technology makes it possible to achieve high economic indicators while exceeding the standard duration of the campaign by 1.75 times. Experience in technology development made it possible to increase the furnace campaign duration to 17.46 years, achieve a reduction in specific coke consumption by 15.9 %, and increase the specific consumption of natural gas for cast iron smelting by 46.4 %; reduce the specific carbon consumption for cast iron smelting by 6.3 %.

Optimal scheduling of regional integrated energy systems with hot dry rock enhanced geothermal system based on information gap decision theory

AbstractHot dry rock (HDR) is regarded as a promising resource of geothermal energy and becomes an important field for future geothermal development due to its advantages of high temperature, wide distribution and huge reserves. At present, HDR research is mainly focused on the modeling and efficiency evaluation of power generation cycle, but its relationship with the source side of the system has not been considered in the field of integrated energy systems. Therefore, this paper proposes a day‐ahead scheduling method for regional integrated energy systems (RIES) with HDR based on information gap decision theory (IGDT). First, the heat transfer system model of HDR is established according to the energy flow model and basic structure of the HDR enhanced geothermal system (EGS). Second, a comprehensive geothermal energy system scheduling model is established from HDR based on the energy hub modeling structure. Then, the IGDT is introduced to analyze the renewable energy output uncertainty in the model. Finally, through a real RIES analysis, the simulation results verified the correctness and effectiveness of the proposed model. The scheduling cost was ¥47,073 when EGS participated in the scheduling. Access to EGS reduced the system's total 24‐h energy purchase by 8305 kW, natural gas consumption by 3051.9 m3, and total carbon emissions by 742.28 kg. The latter emphasized that the proposed model achieves the purpose of reducing the system cost, saving energy and reducing emissions.

The Dynamics of Energy-Related Carbon Emissions and Their Influencing Factors in the Yangtze River Delta, China

Chinese cities are pursuing an energy transition to decouple energy-related carbon emissions (ERCEs) from economic growth. Despite numerous studies focusing on the factors influencing carbon emissions, few have quantitatively analyzed their respective contribution rates, thus leaving a gap in effectively guiding policies. This study took 16 cities in the Yangtze River Delta (YRD) as the study area. The decoupling between ERCEs and economic growth was analyzed during 2000–2020, and the contribution rates of different factors were explored. The results showed that the total ERCEs increased from 413.40 million to 1265.86 million tons during 2000–2020, increasing by over three times. Coal and oil were the dominant energy sources in most cities, but natural gas consumption increased from 0.15% to 5.96%. Moreover, 14 cities showed a decoupling status, indicating a certain win–win situation between economic growth and ERCE reduction. Economic growth greatly increased ERCEs, with its contribution rate ranging from 114.65% to 493.27% during 2000–2020. On the contrary, energy structure and energy intensity both contributed to reducing ERCEs in most cities, and their maximum contribution rates reached −32.29% and −449.13%, respectively, which were the main forces for the win–win situation. Finally, carbon reduction proposals are put forward, which provide theoretical support for achieving the “Double Carbon” goal in the YRD.

CALCULATING THE CARBON FOOTPRINT FOR ENVIRONMENTAL SUSTAINABILITY: THE CASE OF TED DİYARBAKIR COLLEGE (TÜRKİYE

It is crucial to promote awareness, particularly throughout society, regarding a topic that holds significant importance for our environment. This study was undertaken with the intention of making a contribution to research on carbon footprint, driven by this motive. In this study, the carbon footprint calculation of TED Diyarbakır (Türkiye) College was made using the IPCC Tier approach. The carbon footprint of 3 different capabilities, namely scope 1 (Natural gas, gasoline, diesel, fire extinguishers), scope 2 (electric) and scope 3 (Water consumption, services), were calculated. When Scope 1, Scope 2 and Scope 3 are evaluated together, it is seen that the amount of carbon footprint originating from Scope 1 is higher. Sources of emissions from Scope 1 include natural gas consumption, diesel and gasoline fuel consumption, as well as fire extinguishers. When the emission sources in the college were compared, it was determined that the highest carbon footprint was due to natural gas consumption within scope 1 (97.98%). Subsequently, it was determined that the carbon footprint was caused by existing vehicle shuttle within scope 3 (1.917%). Finally, it has been determined that the carbon footprint is caused by the existing electricity consumption within scope 2 (0.1%). It is stated that there are 2 reasons for the low carbon footprint caused by electricity consumption. The first is that the equipment used in lighting is LED, and the second is that there is no need for lighting fixtures due to the long lighting time of the day in our geography

Review about evaluation methods of recoverable reserves of deep water drive gas reservoirs in China

It has been widely accepted that China is one of the biggest natural gas consumers. Related to the imports of LNG, China stands in a very uncomfortable situation. Most domestic gas reservoirs fall within deep water drive gas reservoirs inordinately, which has entered the production depletion stage. Accurate estimation of SEC recoverable reserves of deep water drive gas reservoirs is of great significance for gas consumption planning and peak shaving. The existing calculation methods of recoverable reserves mainly consist of static methods and dynamic methods. In the early stage of exploration and development, the volumetric method has often been utilized to calculate the recoverable reserves. With the continuous development of gas reservoirs, the main methods for evaluation are dynamic methods, including the successive subtraction of production method, water drive curve method, prediction model method, attenuation curve method, improved virtual curve method, and material balance method for deep gas reservoirs.

Energy-saving technology of silicate pressed material with use of micro-porous silica-earth raw materials

Purpose. Research on the possibility of producing a silicate material that hardens under reduced parameters of autoclave processing, due to the introduction of natural zeolite into the raw material mixture. The methods. To solve the problems set in the work, following methods were used:generalization and analysis of theoretical and experimental data of domestic and foreign authors; analytical studies of raw materials (chemical, mechanical and physical-mechanical methods); laboratory experiment using physical and mechanical tests. The study of the properties of raw materials was carried out according to standardized methods. Findings. It has been proven that natural zeolite is an effective component of silicate pressed materials for reducing heat energy consumption during their autoclaving. It was established that with a low zeolite content, the compressive strength of lime-zeolite stone practically does not differ from the strength of limestone-sandstone. A study of the influence of the autoclave treatment regime on the strength of silicate pressed concrete, which was made using a lime-zeolite binder, was carried out. It has been experimentally confirmed that the strength-to-strength ratio of pressed silicate material on a lime-zeolite binder (compared to a similar pressed silicate material on a lime-sand binder) depends to a lesser extent on the water vapor pressure during autoclaving. The originality. The dependences of the compressive strength limit of samples-beams made of lime-zeolite binder at different mass ratios of lime:siliceous component, as well as the dependence of the compressive strength limit of silicate pressed materials on a lime-zeolite binder on water vapor pressure during autoclave processing. Practical implementation. The results of the research can be used at enterprises of the building materials industry in the production of silicate bricks. Replacing natural quartz sand with natural zeolite reduces the production cost of lime-zeolite binder, and the reduction of water vapor pressure during autoclaving of silicate pressed material on lime-zeolite binder reduces the consumption of high-value natural gas.

Can China's carbon generalized system of preferences reduce urban residents' carbon emissions? Evidence from a quasi-natural experiment

The carbon generalized system of preferences (CGSP) is an innovative incentive mechanism implemented by the Chinese government, which has also become an important part of carbon emission reduction at the living end, and it is of great significance to study whether the Pilot Policy can reduce the carbon emissions of residents. This study firstly accounts for the total carbon emissions and per capita carbon emissions of the residents of 284 cities in China, and on this basis, adopts the SCM method to quantitatively study and analyze the overall and local implementation effects of CGSP in China by taking the first batch of CGSP pilots in China as an example, and further applies the mediation effect model to test the pathways of the role of CGSP. The main findings of the study are as follows: (1) During the period of 2010–2020, the total carbon emissions from urban residents' living in China showed a yearly growth trend, from 36,623.98 ×10−2Mt in 2010–85,241.20 ×10−2Mt in 2020, an increase of 8.83%. Total carbon emissions present a structural difference of "electricity consumption > central heating > private transport > gas (oil, natural gas) consumption". (2) Overall, the implementation of the CGSP had a robust positive impact on the overall carbon emission reduction in the pilot cities, with an average annual emission reduction effect value of 36.53 ×10−2Mt. Locally, the annual net policy effect values of Dongguan, Zhongshan, Heyuan, and Guangzhou are 6169.79 ×10−2, 26,600.17 ×10−2, 17,081.34 ×10−2 and 9393.36 ×10−2Mt respectively. (3) CGSP has a good carbon emission reduction effect by suppressing the impact on residents' carbon emissions through enhancing the city's innovation capacity and promoting electricity saving and consumption reduction, while the mediating effect played by the promotion of green and low-carbon travel in the pilot policy is not significant. Finally, based on the research findings, relevant suggestions are targeted.

Ray-Tracing modeling for urban photovoltaic energy planning and management

The traditional Radiative Transfer Modelling solutions for Solar Energy monitoring and forecasting often provide outputs for a single point location or an area location. However, for high resolution representation of areas these solutions suffer due to low simulation speeds. This approach makes it difficult for decision-makers to accurately estimate the solar potential of the administrative area and plan installations accordingly. In this direction, the study introduces three-dimensional Ray-Tracing based radiative modeling which is a high-speed area-based solution for solar energy monitoring. The three-dimensional ray-tracing was simulated by using advanced graphic creation platforms and cloud computing in conjunction with satellite data of the clouds, aerosols, building shadows effects and three-dimensional representations of the city using Cesium 3D tiles and Unreal Engine ®. The entire system was developed in a hybrid model to be exploited by urban planners for solar PV installations and by electricity distribution system operators for energy management and efficient incorporation of the produced energy into the regular and smart grids. This study implements and analyses this Ray-Tracing model for solar photovoltaic energy potential estimation at a rooftop level for the city of Athens, Greece. The total rooftop exploitable area in Athens was found to be close to 34 km2, which is able to massively host distributed PVs followed by almost 4.3 TWh of annually produced energy, whilst Penteli (a Municipality in Athens) possessed a potential of 96.8 GWh with an exploitable area of just 0.8 km2. This amount of energy, in a hypothetical full coverage scenario, is able to provide for 48.7% of Athens’s total energy requirement. Similar year-long simulations were conducted using the EU’s largest rooftop solar installation at Stavros Niarchos Foundation Cultural Center and randomly selected rooftops having solar installations in different municipalities in Athens. With these estimated solar potential values, the gross savings in natural gas consumption and hence the CO2 equivalent emissions can be computed. With the current estimated solar potential of Athens, the analyzed savings accounted of nearly 2.43 billion euros and 18 MT CO2 equivalent emissions. These computed annual savings are capable of covering installation costs for nearly 100,000 new solar installations. The end-product of this study is the development of a solar cadastre web tool which will support the decision-makers in the energy transition policies and the solar PV penetration into the urban environment and eventually drive the effort into renewable energy transition across the globe.

FMM-VMD-Transformer: A hybrid deep learning model for predicting natural gas consumption

The rapid advancement of energy digitization and intelligence has engendered an escalating demand for accurate and timely prediction of natural gas consumption across diverse temporal scales. This exigency finds solutions in the swift development of intelligent algorithms. Most of the current short-term prediction algorithms are season-dependent and can achieve high prediction accuracy in temperate regions. However, in tropical and subtropical regions where seasonal patterns are not obvious, the prediction accuracy of related studies tends to decrease significantly. To address this challenge, we propose a natural gas hybrid prediction model that is applicable to temperate, subtropical, and tropical regions. This model integrates mode decomposition, feature selection and prediction. Specifically, the Feature Matching Maximization (FMM) optimization algorithm and Variational Mode Decomposition (VMD) are proposed to decompose the natural gas consumption into three sub-series: trend component, feature component, and residue component, thereby enhancing the feature representation capability for complex nonlinear characteristics. Furthermore, the Transformer model based on multi-head attention is enhanced to predict the temporal data of each sub-series. This augmentation capitalizes on the Transformer model’s robust long-term dependence modeling capability, enabling it to extract valuable information from historical data. The hybrid model is experimentally validated on the natural gas consumption dataset of Xiamen, a subtropical region. Compared to other decomposition-based prediction algorithms, our findings possess superior feature extraction capabilities and higher prediction accuracy, especially in the case of nonlinear and non-stationary data. Finally, the robustness of the model is validated using datasets from multiple cities and different time spans.

Reassessing determinants of urban energy intensity in China: insights from controllable and uncontrollable factors.

This study adopts a new approach to reassess the factors influencing urban energy intensity in China. Initially, the factors impacting energy intensity are classified into controllable and uncontrollable categories. Subsequently, employing a single-factor multi-stage method combined with the Adaboost method, 289 Chinese cities are categorized based on uncontrollable factors to eliminate the influence of inherent differences on energy intensity. Finally, panel data regression analyses are conducted using data from 289 Chinese cities between 2005 and 2016, individually for each city type, to evaluate the extent to which controllable factors contribute to energy intensity. The findings indicate that (1) heightened energy prices, an increased share of electricity consumption, and a greater proportion of centralized heating significantly influence the reduction of energy intensity across all city types; (2) to optimize energy consumption, each city type should adopt specific strategies. For instance, cities located in resource-rich heating regions with low economic outputs can reduce their energy intensity by increasing electricity consumption, while cities with high economic outputs can decrease their energy intensity by increasing natural gas consumption. The findings of this study carry substantial implications for the Chinese government in shaping targeted energy policies tailored to different city types.

Theoretical and experimental study on total heat recovery of condensing gas boiler flue gas by gas engine-driven compression heat pump

How to improve the utilization efficiency of natural gas and achieve the goal of carbon reduction has gradually become the focus of people’s attention. The exhaust temperature of the condensing gas boiler is between 50℃ and 80℃, which still contains some heat that is not used, so it is necessary to recover this part of the heat. This paper mainly studies the total heat recovery and utilization of waste heat from low-temperature flue gas of condensing gas boiler. In the research field of gas boiler flue gas waste heat recovery, the use of gas compression heat pump to recover gas boiler flue gas waste heat is still very few. Based on the principle of reducing the cold source temperature, a low-temperature flue gas recovery scheme of a gas engine-driven compression heat pump coupled condensing gas boiler is proposed. The low-temperature chilled water produced by gas engine-driven compression heat pump is used to recover flue gas waste heat from condensing gas boiler and gas engine, which can improve the utilization efficiency of natural gas and eliminate the “white smoke phenomenon” simultaneously. In addition, the waste heat of flue gas is used as the low-temperature heat source of gas engine-driven compression heat pump to ensure the stable operation of the heat pump in the low-temperature environment. The flue gas waste heat recovery technology has been improved compared with other flue gas waste heat recovery technologies in terms of primary energy utilization efficiency, system stability, corrosion resistance of flue gas heat exchangers, and investment recovery cycle. The experimental results show that when the water inlet temperature of the flue gas heat exchanger is 15℃, the overall power of the unit can reach 645 kW, and the final exhaust temperature is below 25℃. The overall primary energy utilization rate of the GEHP&CB can reach 110 %, which is 10 %∼20 % higher than that of the condensing gas boiler. The payback period of the increased initial investment is 1.4 heating seasons. Due to the improvement of natural gas utilization efficiency significantly reduces natural gas consumption and pollutant discharge.

Evaluation of fault-sealing: a case study on Xiangguosi underground gas storage, SW China

China vigorously implements the dual carbon strategy, and natural gas consumption continues to grow rapidly. It is urgent to improve the natural gas “production, supply, storage, and sales” system and accelerate the construction of underground gas storage (UGS). UGS requires “storage, injection, and extraction”. Faults are the primary factor of “storage”, the evaluation of fault-sealing is crucial for the safe construction and operation of UGS. Existing researches start from the perspective of the hydrocarbon reservoir, develop an evaluation of the basic characteristics of faults, lithological configuration of the fault’s two blocks, analysis of production performance, Shale Smear Factor (SSF), Shale Gouge Ratio (SGR), properties of fault-filling materials, 3D tectonic model, normal pressure on the fault plane, fault shear index, and fault plugging coefficient. This paper systematically analyzes the adaptability of existing methods and proposes an index to evaluate the fault-sealing capability of UGS. Taking the first UGS in SW China—Xiangguosi UGS as a case, using this workflow to evaluate the fault-sealing capability of 5 major faults. It is believed that the evaluation of fault-sealing on Xiangguosi UGS is good. This conclusion supports the design of construction key indicators and is the important basis point of the construction of the “signpost” UGS. It is of guiding significance and provides a reference for the evaluation of fault-sealing for the rebuilding of depleted gas reservoirs to UGSs.

Integrating geothermal energy in Hungary: A case study on sustainable urban heating and emissions mitigation through the district heating infrastructure

Hungary boasts exceptional geothermal capabilities, with an Earth's crust thermal gradient nearly double the global average. However, the current utilization of these resources is often one-sided and lacks careful consideration. This comprehensive study offers updated insights into Hungary's geothermal potential and its current energy utilization. By presenting a practical example and employing scenario-based analyses, this study demonstrates how basic calculations can guide investment decisions in geothermal infrastructure. The aim is to address the prevailing issue of cities and towns prioritizing fossil fuel-based energy sources, thereby overshadowing renewable energy alternatives, despite advancing technology. Notably, in the case of Székesfehérvár, it was determined that annual natural gas consumption could be reduced by an impressive 40–50%, leading to a substantial reduction of 5,000–9,200 tons of CO2 emissions, depending on the specific scenarios examined.

Damping accumulative NDAGM(1,N, α) power model and its applications

PurposeIn this essay, a new NDAGM(1,N,α) power model is recommended to resolve the hassle of the distinction between old and new information, and the complicated nonlinear traits between sequences in real behavior systems.Design/methodology/approachFirstly, the correlation aspect sequence is screened via a grey integrated correlation degree, and the damped cumulative generating operator and power index are introduced to define the new model. Then the non-structural parameters are optimized through the genetic algorithm. Finally, the pattern is utilized for the prediction of China’s natural gas consumption, and in contrast with other models.FindingsBy altering the unknown parameters of the model, theoretical deduction has been carried out on the newly constructed model. It has been discovered that the new model can be interchanged with the traditional grey model, indicating that the model proposed in this article possesses strong compatibility. In the case study, the NDAGM(1,N,α) power model demonstrates superior integrated performance compared to the benchmark models, which indirectly reflects the model’s heightened sensitivity to disparities between new and old information, as well as its ability to handle complex linear issues.Practical implicationsThis paper provides a scientifically valid forecast model for predicting natural gas consumption. The forecast results can offer a theoretical foundation for the formulation of national strategies and related policies regarding natural gas import and export.Originality/valueThe primary contribution of this article is the proposition of a grey multivariate prediction model, which accommodates both new and historical information and is applicable to complex nonlinear scenarios. In addition, the predictive performance of the model has been enhanced by employing a genetic algorithm to search for the optimal power exponent.

Analysis and Forecasting of Energy Data and GDP Based on Pearson Correlation Analysis-Random Forest Algorithm

The relationship between energy data and GDP is an important economic issue because energy is the foundation that supports modern economic development. This paper examines the relationship between energy data and GDP and uses Pearson correlation analysis to calculate the relationship between each variable in energy data and annual GDP for 52 regions. The results show that total electricity consumption is the factor with the highest degree of influence on GDP, followed by natural gas consumption, biomass consumption, hydroelectricity consumption, LPG consumption and geothermal energy consumption. This indicates that there is an extremely strong correlation between local energy data and GDP. To further explore this correlation, this paper attempts to predict the GDP of the locality based on the local energy data using a machine learning approach.The Random Forest algorithm is chosen as the machine learning model, and the training, validation and test sets are divided according to the ratio of 6:2:2. By using MSE, RMSE, MAE, MAPE and R to evaluate the model, it is found that the random forest machine learning algorithm can predict the local GDP well.The predicted value of GDP and the actual value of GDP are very close to each other, meanwhile, the value of MSE is 62.779.These findings show that the local energy data are closely related to economic development. The impact of energy factors on the economy should be taken into account when formulating economic policies. In addition, machine learning algorithms can provide strong support for economic forecasting and provide more accurate information for decision makers.

Predicting Liquid Natural Gas Consumption via the Multilayer Perceptron Algorithm Using Bayesian Hyperparameter Autotuning

Reductions in energy consumption and greenhouse gas emissions are required globally. Under this background, the Multilayer Perceptron machine-learning algorithm was used to predict liquid natural gas consumption to improve energy consumption efficiency. Setting hyperparameters remains challenging in machine-learning-based prediction. Here, to improve prediction efficiency, hyperparameter autotuning via Bayesian optimization was used to identify the optimal combination of the eight key hyperparameters. The autotuned model was validated by comparing its predictive performance with that of a base model (with all hyperparameters set to the default values) using the coefficient of variation of root-mean-square error (CvRMSE) and coefficient of determination (R2) based on the Measurement and Verification Guideline evaluation metrics. To confirm the model’s industrial applicability, its predictions were compared with values measured at a small-to-medium-sized food factory. The optimized model performed better than the base model, achieving a CvRMSE of 12.30% and an R2 of 0.94, and achieving a predictive accuracy of 91.49%. By predicting energy consumption, these findings are expected to promote the efficient operation and management of energy in the food industry.