Natural Gas Load Research Articles

Short-term natural gas load forecasting based on EL-VMD-Transformer-ResLSTM

Due to changes in urban residents’ consumption habits and lifestyles, accurately predicting natural gas consumption has become increasingly important. To address this issue, this paper proposes a forecasting model that combines Ensemble Learning (EL), Variational Mode Decomposition (VMD), Transformer, and LSTM. First, XGBoost, CatBoost, and LightGBM are used as base learners in the ensemble learning framework, with the predictions generated by the ensemble model integrated into the original dataset. Next, the VMD method is employed to decompose the natural gas load sequence into several intrinsic mode functions (IMFs), effectively extracting the inherent features of the natural gas load sequence. Finally, the data is input into the Transformer-ResLSTM network for prediction. This network replaces the original Transformer decoder structure with an LSTM network and fully connected layers, creating a new decoder structure. Additionally, a residual connection mechanism is introduced in both the encoder of the Transformer network and the new decoder structure. Experimental results show that, compared to traditional models such as ARIMA, Transformer, GRU, and LSTM, the proposed hybrid model significantly improves prediction accuracy, reducing MSE by 92–98% and MAE by 74–83%. In summary, this method demonstrates significant potential and practical value in enhancing the accuracy of natural gas load forecasting.

Optimizing multi-energy systems with enhanced robust planning for cost-effective and reliable operation

This paper introduces a comprehensive and resilient multi-energy system (MES) designed for independent planning and real-time implementation. A robust daily coordinated planning model is proposed, incorporating adjustable optimization with fundamental operational and uncertainty constraints. The model integrates various energy sources and systems, including photovoltaics, wind turbines, combined heat and power (CHP) units, energy storage system (ESS), electric vehicle (EV), electric boilers, and power-to-gas (P2G) facilities, to manage electricity, natural gas, and heat demands. The objective is to minimize MES operational costs while meeting electricity and heat requirements, considering renewable energy uncertainties. It includes the development of a two-stage flexible robust optimization model that accounts for energy equilibrium, capacity constraints, and demand response mechanisms. The model incorporates price-based demand response with both switchable and interruptible loads, enhancing system controllability and flexibility. Additionally, a scenario generation and reduction technique based on the Kantorovich distance is employed to effectively manage forecast errors and uncertainties. A novel modified Slime Mold Algorithm (SMA) is utilized to solve the optimization problem, demonstrating superior convergence and computational efficiency compared to traditional meta-heuristics. The slime mold algorithm is further enhanced with chaos theory, using a sine map to introduce dynamic exploration capabilities. The findings indicate that the proposed multi-energy system model effectively balances electricity, natural gas, and heat loads while accommodating renewable energy fluctuations. The enhanced slime mold algorithm provides optimal solutions swiftly, ensuring reliable and cost-effective multi-energy system operation.

Daily natural gas load prediction method based on APSO optimization and Attention-BiLSTM.

As the economy continues to develop and technology advances, there is an increasing societal need for an environmentally friendly ecosystem. Consequently, natural gas, known for its minimal greenhouse gas emissions, has been widely adopted as a clean energy alternative. The accurate prediction of short-term natural gas demand poses a significant challenge within this context, as precise forecasts have important implications for gas dispatch and pipeline safety. The incorporation of intelligent algorithms into prediction methodologies has resulted in notable progress in recent times. Nevertheless, certain limitations persist. However, there exist certain limitations, including the tendency to easily fall into local optimization and inadequate search capability. To address the challenge of accurately predicting daily natural gas loads, we propose a novel methodology that integrates the adaptive particle swarm optimization algorithm, attention mechanism, and bidirectional long short-term memory (BiLSTM) neural networks. The initial step involves utilizing the BiLSTM network to conduct bidirectional data learning. Following this, the attention mechanism is employed to calculate the weights of the hidden layer in the BiLSTM, with a specific focus on weight distribution. Lastly, the adaptive particle swarm optimization algorithm is utilized to comprehensively optimize and design the network structure, initial learning rate, and learning rounds of the BiLSTM network model, thereby enhancing the accuracy of the model. The findings revealed that the combined model achieved a mean absolute percentage error (MAPE) of 0.90% and a coefficient of determination (R2) of 0.99. These results surpassed those of the other comparative models, demonstrating superior prediction accuracy, as well as exhibiting favorable generalization and prediction stability.

Short-term gas load prediction based on GRA-IPSO-LSTM

With the improvement of natural gas production, supply and marketing mechanism, the effective prediction of natural gas short-term load is of great significance for rational allocation of resources and solving urban energy security. Grey relation analysis (GRA) was used to determine the main controlling factors affecting the short-term load of natural gas. The inertia weight and acceleration factor of the particle swarm optimization (PSO) algorithm were improved by applying a nonlinear change strategy. The hyperparameters suitable for the LSTM model were found by using an optimization algorithm, and a combination model of GRA-IPSO-LSTM was formed. Other models are compared to verify the accuracy and reliability of the model. The results show that, according to the size of the grey correlation degree, the factors that have little influence on the daily load can be deleted step by step to reduce the complexity of the subsequent prediction model. The iteration speed, convergence accuracy, and optimization quality of the IPSO algorithm are improved, which reduces the limitation of the artificial selection of LSTM model hyperparameters. The MAPE, RMSE, and R of the GRA-IPSO-LSTM combined model are 5461.02 m3, 0.49%, and 0.99932, which significantly improve the prediction accuracy, proving that the combined model in this paper can be used for accurate prediction of short-term natural gas load.

RETRACTED: Optimum operation of energy hub by considering renewable resources by considering risk tolerance and risk taking with Teaching–learning-based optimization

Amidst growing concerns over climate change, the conventional energy landscape faces critical challenges associated with fossil fuel usage. In response, this study explores alternative approaches by investigating an energy hub system leveraging wind turbine-generated power. This hub integrates seamlessly with electricity and natural gas grids, offering a comprehensive energy supply encompassing electricity, natural gas, and thermal loads. The research strategy encompasses a multi-pronged approach. A Time-of-Use (TOU) load management program optimizes the distribution of electrical and thermal loads. To address the unpredictability of wind speed, the information gap decision theory (IGDT) is introduced to manage risk and deviations effectively. The central objective involves optimizing the energy hub's operations, focusing on minimizing operational costs and emissions. To address this intricate challenge, the study employs the Teaching–Learning-Based Optimization (TLBO) method. This advanced technique concurrently optimizes cost and environmental impact, exemplifying its efficacy in the energy hub context. The research culminates in demonstrating the TLBO algorithm's swift convergence, highlighting its aptitude for addressing complex cost and emission optimization dynamics. In sum, this study offers innovative insights into sustainable energy systems, where economic and environmental considerations converge harmoniously.

A multivariate natural gas load forecasting method based on residual recurrent neural network

AbstractCurrent natural gas load forecasting encounters with the conundrum of unsatisfying accuracy and interpretability. To address the challenge, a multi‐variate forecasting method is proposed, which contains three phases: First, an integrate history‐climate‐holiday factor set is established to provide multi‐perspective for a more explainable forecast; Second, factor fusion interaction between features and instances is carried out based on hierarchical contrastive learning, which contributes to inter‐intra factors potential relationships exploration. Third, a multivariate forecasting model named ResRNN is trained using fused target dataset. Due to its innovation in structure and loss, forecasting accuracy is further improved. Finally, the authors’ method's superiority is confirmed by several groups of comparative experiments and results demonstrate that it outperforms mainstream methods.

Pseudo-correlation problem and its solution for the transfer forecasting of short-term natural gas loads

Considering the information protection of users and system failure of natural gas enterprises, complete large-scale data are difficult to obtain, which is a critical issue for data-driven models applied to short-term load forecasting (STLF). Transfer forecasting has been widely used for STLF because it can significantly improve forecasting accuracy when using scarce data. Pseudo-correlation is a latent issue that significantly affects the accuracy of transfer forecasting and can even generate negative transfers. However, to the best of our knowledge, this phenomenon has not been investigated previously. In this paper, we first identify and define pseudo-correlation, and then propose a novel correlation coefficient algorithm to reduce the risk of negative transfer as a result of pseudo-correlation. We have implemented the proposed algorithm into the transfer forecasting of short-term loads within Greece's National Natural Gas Transmission System. Experimental results demonstrate that when negative transfer occurs, the probability of negative transfer being caused by pseudo-correlation is higher than 40%. Additionally, as the amount of missing data in the target domain increases, this probability also increases. The proposed method can effectively reduce the risk of negative transfers and improve the error in forecasting model by as much as 30%. Our insights into pseudo-correlation and its impact on transfer forecasting may provide forecasters of natural gas supply systems with a helpful method for achieving accurate STLF.

A cross-sectoral analysis of energy shortages in Pakistan: based on supply-driven input-output model

The impacts of energy shortages characterized by regular blackouts, natural gas, and electricity load shedding in Pakistan affected each economic sector, causing an energy-induced crisis and ecological sustainability issues. This study was conducted to reveal the benefits of renewable energy and describe the economic losses associated with electricity unavailability using supply-driven input-output as a price model across 34 sectors. The results revealed that exogenous shocks in electricity prices are responsible for bringing significant fluctuations across the business cycle in the country. Similarly, the overall output of Pakistan’s economy will decrease by 24.89 rupees due to a 1-kilowatt-hour reduction in electricity supply. Moreover, both forward and backward linkages of Pakistan’s economy revealed that higher electricity allocation coefficients pose significant output impacts on most sectors. We conclude that indirect output impacts require due consideration to avoid the underestimation problem due to total electricity shortages. It is recommended that the government provide a social and legal framework to boost the environmental sustainability and economic activities in the textile, oil refining, production of cement, and fertilizer sectors for sustainable economic growth.

Natural gas demand response strategy considering user satisfaction and load volatility under dynamic pricing

Under the background that natural gas is continuously consumed as a non-renewable energy source and the growing demand for natural gas in human society, the contradiction of supply and demand between natural gas utilization and social development has become increasingly prominent. Demand response (DR) in the system helps to address this issue. Currently, there is a lack of diverse DR for natural gas systems. However, DR not only maintains the balance between supply and demand in the gas system, but also relieve peak shaving pressure in natural gas systems and instruct users to save and reduce energy. Therefore, based on the price elasticity theory and user satisfaction, this study focuses on the purpose of natural gas users and gas suppliers to participate in DR, and constructs a natural gas DR model from the perspective of dynamic pricing. An effective natural gas DR strategy is proposed by classifying peak, plain and valley of natural gas load by K-means algorithm, and solving the DR model by multi-objective particle swarm optimization (MOPSO). The DR strategy proposed in this study is evaluated in terms of both non-heating and heating periods through actual examples. The results show that the DR strategy proposed in this study reduces the daily load demand of natural gas, reduces the maximum peak-to-valley difference of daily load, slows down the daily load volatility, improves user satisfaction, maximizes the interests of users and gas suppliers, and effectively balances the system demand.

Natural Gas Load forecasting based on the fusion of VMD-SE and CNN-BiLSTM-Attention

The rational dispatch and steady supply of natural gas resources can be effectively supported by accurate forecasting of the natural gas load. The accuracy of natural gas load forecasting is, however, low due to the fundamental characteristics of the non-stationary and non-linear natural gas load. Based on this, this paper proposes a new natural gas load forecasting model based on the fusion of VMD-SE and CNN-BiLSTM-Attention. First, the average instantaneous frequency method is used to determine the optimal K value of VMD, and then the sample entropy method is introduced to reconstruct the sub-sequence of VMD decomposition, which effectively reduces the computational overhead of the algorithm. Then, using CNN to mine the level information of multi-dimensional time series variables, using BiLSTM to mine the time series feature information, and introducing the Attention mechanism to give corresponding weight to different feature factors, highlighting the influence of key factors, the anticipated values of each reconstructed sub-series are superimposed to provide the final predicted value of the natural gas load. The model proposed in this paper has lower error than other forecasting models, can effectively improve the precision of natural gas load forecasting, and has a better forecasting effect, according to the results of establishing various forecasting models using the natural gas load data of one region of China as an example.

Multi-objective optimization of integrated energy systems based on demand response

ABSTRACT The implementation of demand response (DR) in the operation optimization of the integrated energy system has become one of the research hotspots worldwide with the rapid development of the energy network. Integrated gas-electricity system (IGES) operators can allocate different energy carriers more rationally and decrease energy cost and exergy input considering the DR scheme. However, DR was mainly applied to electric power systems in the past, while natural gas systems were less considered. In this paper, based on the theory of price-elasticity, and simultaneously with the consideration of the DR for end-user (EDU) of electricity and natural gas, the optimization model of the IGES is established, which includes two objective functions, the minimum operating cost of the integrated system and the maximum EDU satisfaction. The constraints include compressors and gas storages in the natural gas system, coal and gas generator units in the electric power system, Pow to gas units, and EDU gas/electric load changes. Subsequently, the proposed model is employed for an integrated 7-node natural gas system and 6-node power system with the sensitivity analysis for operating cost. The results demonstrate that the implementation of DR brings specific economic benefits to the operation of the entire system, the total operating cost is reduced by 16.6%, and the natural gas load is reduced by 89.9%. The implementation of DR balances the 24-hour load, reduces the fluctuation of the EDU load, increases the efficiency of the load shifting, and alleviates the instability of upstream production and transportation.

Optimal Operation of Integrated Energy Systems Based on Multi-Energy Coupling With Power-to-Gas Technology

Abstract Natural gas and renewable energy sources make up an increasingly large proportion of power generation due to their being environmentally friendly. Because of the intermittent and fluctuating output of renewable energy sources, the emerging technology of power-to-gas (P2G) units is of great significance to alleviate. This paper focuses on the coordinated optimization of the combined gas and electricity network (CGEN) system with bidirectional energy conversion. Gas-fired power generation (GPG) plants and P2G are considered as linkages between the two networks. A unified CGEN mathematical model is established with the minimum operation cost as the objective function. The injection and production process of underground natural gas storage (UNGS) is also taken into consideration that is not available in other literature. Variables such as the output of P2G and gas-fired power generation plants, the supply of UNGS, and the wind curtailment are optimized correspondingly. The improved 24-node power grid (PG) and Belgium 20-node natural gas pipeline network (NGPN) are adopted to test the validity and capability of the proposed model, and then we compare the results CGEN model with the single Belgium NGPN to analyze the impact on the NGPN. Moreover, we adopt a coupled operation system of a 6-node power system and a 7-node NGPN to further analyze the influence of P2G on the CGEN. The results show that compared with the system without P2G, the total operating cost of the system is reduced by 9.39%, the natural gas load shedding is reduced by 26.1%, and the wind curtailment is reduced from 326 MWh to zero.

Techniques for Creating Synthetic Combined Electric and Natural Gas Transmission Grids

This paper presents a methodology for the creation of a synthetic combined electric and natural gas transmission network, along with representative benchmark results. The systems do not contain actual, confidential network data, but are synthetic, meaning they are built to capture the behavior of a combined network that is geographically constrained. First, natural gas loads are placed in a selected area. Work already done in building synthetic electric grids aids in this process, where the natural gas-powered generators are modeled as loads in the natural gas system. Publicly available data is then used to place the remaining gas loads and the gathering plant. Next, a method is introduced to construct a pipeline network connecting the loads and processing plant, which acts as the source. The combined electric-gas system is then solved for the nodal pressures, pipeline flow rates, and electric state variables. A 51-node gas test case with 49 pipes, 23 loads, 2 compressor stations and a loop is constructed and solved in combination with a 173-bus electric system, designed to aid with developing and validating analysis techniques for combined electric-gas systems.

Prediction of fluctuation loads based on GARCH family-CatBoost-CNNLSTM

An accurate prediction on natural gas load is always a guarantee of a safe and reliable operation of the natural gas pipeline network system, however, natural gas daily load variations are instability and fluctuation. Therefore, accurate prediction fluctuation loads can be challenging. Concerning that many influencing factors of natural gas daily load are non-linear and time-varying, a combined prediction model combining GARCH family models, CatBoost algorithm, CNN and LSTM is proposed in this paper. The model combines two important techniques. The first technique is to visualize the fluctuation of the daily load of natural gas through the classical GARCH family model. and characterize the fluctuation through parameters. The second one is a new gradient boosting algorithm that can take into account factors such as the parameters of the GARCH family of models and the meteorological environment, and screen for suitable and important prediction features. It also combines CNN with LSTM to predict natural gas daily load with large fluctuations and calculates 95% confidence intervals. The experimental results show that the natural gas load prediction based on GARCH family-CatBoost-CNNLSTM is reduced by an average of 26.555%, 30.892%, and 26.283% in the three relative evaluation indicators of RMSE, MAE and MAPE, and an average increase of 0.914% in R2 compared with other single or combined control models such as LSTM, CNN and MLP. The model effectively combines the advantages of econometric methods, machine learning algorithms, deep learning algorithms and other techniques, as a result, it can be better applied to the prediction of fluctuation loads.

Economic-environmental convex network-constrained decision-making for integrated multi-energy distribution systems under electrified transportation fleets

Considering the high penetration rates of electrified transportation fleets, their impact on the integrated thermal/electrical/natural-gas multi-energy distribution systems (IMEDS) will be distinguishable. This study proposes a hybrid robust-stochastic convex optimization model for optimal scheduling of an IMEDS under the network constraints. Moreover, a high penetration level of smart plug-in hybrid electric vehicle (PHEV) fleets, as well as the renewable energy sources (RES) in the active electricity distribution system (AEDS) is regarded. A multi-objective optimization approach is taken to minimize the operation expenditures and the greenhouse gas emissions. The natural gas network’s (NGN) linepack storage capability along with the district heating network’s (DHN) thermal flexibility are formulated with the objective to enhance the flexibility and avoid overlapping in the peak demand of various energy forms under severe uncertainty condition (e.g., considering uncertain input parameters such as RES production, electrical loads, natural gas loads, drivers’ behaviour. To handle such uncertainty parameters, a scenario-based stochastic programming (SP) method is adopted, combined with robust optimization (RO) ambiguity sets, when dealing with volatilities of the market price. The network-constrained IMEDS was embodied by the standard IEEE 69-bus AEDS, 40-node NGN, 59-bus DHN systems. The proposed convex model is a second-order cone programming (SOCP) model, which was solved by the MOSEK solver. The functionality of the proposed method was confirmed through different case studies.

A new method to forecast multi-time scale load of natural gas based on augmentation data-machine learning model

Gas load forecasting is important for the economic and reliable operation of the city gas transmission and distribution system. In this paper, a nonlinear autoregressive model (NARX) with exogenous inputs, support vector machine (SVM), Gaussian process regression (GPR) and ensemble tree model (ETREE) were used to predict and compare the gas load based on the gas load data in a certain region for past 3 years. The results showed that the prediction errors for most of days were higher than 10%. Further, simulation data were generated by considering the gas load variation trend, which was then combined with historical data to form the augmentation data set to train the model. The test results indicated that the prediction error of daily gas load in one year reduced to below 7% with a machine learning prediction method based on augmentation data. In addition, the model based on augmentation data set still performed better than original data in predicting the monthly gas load in last year as well as daily gas load in last month and week. Therefore, the method based on augmentation data proposed in this paper is a potentially good tool to forecast natural gas load.

A Frequency–Pressure Cooperative Control Strategy of Multi-Microgrid with an Electric–Gas System Based on MADDPG

With the development of micro gas turbines (MT) and power-to-gas (P2G) technology, the electric–gas system plays an important role in maintaining the stable, economical, and flexible operation of the microgrid. When subjected to power load disturbance and natural gas load disturbance, the system controller needs to coordinately control the frequency of the microgrid and the gas pressure at the natural gas pipeline nodes. Additionally, the reliability and stability of a multi-microgrid system are much higher than that of a single microgrid, but its control technology is more complicated. Thus, a frequency–pressure cooperative control strategy of a multi-microgrid oriented to an electric–gas system is proposed in this paper. Firstly, based on the analysis of the operating characteristics of the natural gas network and the coupling equipment, the dynamic model of natural gas transmission is built. Secondly, a multi-microgrid load frequency control model including MT, P2G equipment, electric vehicles (EVs), distributed power sources and loads has been established. In addition, according to the three control objectives of microgrid frequency, node pressure and system coordination and stability, the structure of a Muti-Agent Deep Deterministic Policy Gradient (MADDPG) controller is designed, then the definition of space and reward functions are completed. Finally, different cases are set up in the multi-microgrid, and the simulation results are compared with PI control and fuzzy control. The simulation results show that, the proposed MADDPG controller can greatly suppress the frequency deviation caused by wind power and load disturbances and the air pressure fluctuations caused by natural gas network load fluctuations. Additionally, it can coordinate well the overall stability between the sub-microgrids of multi-microgrid.

A hybrid deep learning approach by integrating extreme gradient boosting‐long short‐term memory with generalized autoregressive conditional heteroscedasticity family models for natural gas load volatility prediction

AbstractNatural gas load forecasting provides decision‐making support for natural gas dispatch and management, pipeline network construction, pricing, and sustainable energy development. To explain the uncertainty and volatility in natural gas load forecasting, this study predicts the natural gas load volatility. As the natural gas load volatility has the time‐series features, along with long‐term memory, volatility aggregation, asymmetry, and nonnormality, this study proposes a natural gas load volatility prediction model by combining generalized autoregressive conditional heteroscedasticity (GARCH) family models, XGBoost algorithm, and long short‐term memory (LSTM) network. The model first takes the GARCH family models parameters of sliding estimation and meteorological factors as the influencing factors of volatility, and then it screens these influencing factors through the extreme gradient boosting (XGBoost) algorithm. Finally, the selected important features are input into the LSTM network to predict the volatility, and the 90% confidence interval of the volatility is calculated. Compared with a variety of single and combined models, the model proposed in this study has an average reduction of 45.404% in the evaluation index of mean squared error. The experimental results show that the model proposed in this study has a good performance and accuracy in predicting the volatility of natural gas load.

Dynamic stochastic joint expansion planning of power systems, natural gas networks, and electrical and natural gas storage

Over the last decades, electricity generation from natural gas has substantially increased, mostly driven by low natural gas prices due to fracturing and lower extraction costs. The geographic distance between natural gas resources and load centers calls for a holistic tool for joint expansion of power systems and natural gas networks. In this paper, a Dynamic Stochastic Joint Expansion Planning (DSJEP) of power systems and natural gas networks is proposed to minimize the investment and operational costs of power and natural gas systems. Electrical and natural gas storage (ENGS) are considered as an option for decision-makers in the DSJEP problem. The proposed approach takes into account long-term uncertainties in natural gas prices and electric and natural gas demands through scenario realizations. In dynamic planning, more scenario needs more time for computation; therefore, scenario reduction is implemented to eschew unnecessary scenarios. The proposed formulation is implemented on a four-bus electricity system with a five-node natural gas network. To demonstrate the efficiency and scalability of the proposed approach, it is also tested on the IEEE 118-bus system with a 14-node natural gas network. The numerical results demonstrate that ENGS can reduce the total investment cost, up to 52% in the test cases, and operational cost, up to 3%. In this paper, co-planning of power and natural gas systems considering natural gas and electrical storage is represented. Also, electrical and natural gas load growth uncertainties are taken into account to model the real situations. The purpose of the model is to minimize investing and operational costs.

Day-ahead city natural gas load forecasting based on decomposition-fusion technique and diversified ensemble learning model

Accompanying the trend of low-carbon energy consumption, natural gas has ushered in the energy transition era’s development. However, rapid growth has thrown off the balance of urban natural gas supply and demand, resulting in gas shortages in many Chinese cities for several consecutive years. This work proposes a novel model for short-term load forecasting that combined the decomposition-fusion technique with a replacement data function, feature selection, and a diversified Stacking ensemble learning model. First, fast ensemble empirical mode decomposition is used to disintegrate the original complex nonstationary time series data into several modes. To ensure accurate information and computational efficiency while preventing excessive decomposition, the Pearson coefficient is used to fuse highly correlated patterns further. Second, hybrid feature engineering is used to select high contribution candidate input variables. Finally, K-Flod cross-validation is performed in each base-learner to enhance generalization capability during the training process. The empirical results prove that the base-learners’ capabilities and discrepancy will significantly impact the model (MAE = 167.409, MAPE = 3.125, RMSE = 234.654). Even if different types of city data are used, the proposed model’s effectiveness and robustness in gas load forecasting is not weakened, and decomposition-fusion technology can boost the model’s effectiveness. However, it cannot play a decisive role; the ensemble learning approach can integrate the ascendancy of the single model while effectively reducing the risk of falling into a local minimum. The developed model has good application prospects in natural gas dispatch and control systems as it outperforms alternative models in prediction accuracy, adaptability, stability, and generalization ability.