Demand Forecast Model Research Articles

Research on the security of natural gas supply and demand in China under the dual carbon target.

The security of natural gas supply is not only an important part of China's energy security, it also serves as a basic guarantee for China to achieve its dual carbon target and energy transition. Therefore, it is very important to conduct research on the security of China's natural gas supply and demand in the context of the dual carbon target. This paper develops a system dynamics (SD) model for natural gas demand forecasting and a generalized Weng's model for production forecasting to predict China's natural gas demand and production under different scenarios during 2022-2060, and then analyzes China's natural gas supply and demand situation and potential import and external dependence based on the forecast results. The simulation results show that (1) under the two demand scenarios D1 and D2, China's natural gas demand will peak at 766.02 billion m3 in 2046 and 708.07 billion m3 in 2036 and decline to 521.65 billion m3 and 278.99 billion m3 in 2060 respectively; (2) under the two production scenarios S1 and S2, China's natural gas production will peak at 344.581 billion m3 in 2042 and 366.341 billion m3 in 2043 and decrease to about 250 billion m3 in 2060; (3) before 2035, the security of natural gas supply in China will face a challenging situation, the total volume of potential gas imports will gradually increase to about 350 billion m3, and China's dependence on natural gas imports will exceed 50%; after 2035, the progress of China's energy transition will improve the security of its natural gas supply. This paper proposes four recommendations for expanding gas demand in the near to medium term, promoting conventional and unconventional gas production, diversifying import channels and building emergency reserves to ensure China's gas supply security and enable gas to play a "bridging" role in the energy transition.

Performance of TANN, NARX, and GMDHT Models for Urban Water Demand Forecasting: A Case Study in a Residential Complex in Qom, Iran

To keep the balance between demand and supply, methods based on the average per capita consumption were usually applied to predict water demand. More complicated models such as linear regression and time series models were developed for this purpose. However, after the introduction of artificial neural networks (ANNs), different applications of this method were used in the field of water supply management, especially for urban water demand prediction. In this study, multiple types of ANNs were studied to understand their suitability for a residential complex water demand prediction in the city of Qom, Iran. The results indicated that time series ANN (TANN), nonlinear autoregressive network with exogenous inputs (NARX), group method of data handling time series (GMDHT), and their wavelet counterparts (i.e., w-TANN and w-NARX) exhibited varying degrees of performance. Among the aforementioned models, w-NARX performed the best (based on the average overall error) with the test set root mean squared error (MSE) of 49.5 (m3 /h) and R of 0.93, followed by the GMDHT model with the test set MSE of 104 (m3 /h) and R of 0.97 and w-TANN with the test set MSE of 68.8 (m3 /h) and R of 0.91. In addition, the feedback connection in NARX compared to TANN demonstrated overall performance improvement.

Forecasting Urban Peak Water Demand Based on Climate Indices and Demographic Trends

Austria’s water utilities are facing new challenges due to advancing climate change. In recent years, changes in water demand have been observed. Water demand forecast models are required to assess these changes and react to them in a sustainable way. In this study, an existing modeling approach was extended with new climate indices. The multiple linear regression model was applied to different study sites. The model was trained with a training dataset and validated with a test dataset. The performance of the model was assessed using common parameters, such as the mean absolute percentage error. In a further step, the modeling approach was applied to climate projections to estimate the change in water demand for three different representative concentration pathways (RCPs). The change in water demand due to population growth was then considered and combined with the change due to climate change. RCP2.6 shows an average 14% increase in water demand for the period 2051–2070, with climate change (average increase of 0.7%) playing a negligible role. For RCP4.5, an increase of 16% is predicted, while the highest increase of 19% is observed in RCP8.5. Population growth is responsible for most of the increase.

Monte Carlo-based Charging Demand Forecasting Model and Market Space Study

With the rapid development of China's new energy vehicle industry, charging infrastructure has gradually become a key factor affecting the further development of the new energy vehicle industry. Scientific and reasonable forecasts of the future development scale of the domestic charging infrastructure market have become an important element supporting the business planning of various related parties such as vehicle enterprises, charging pile enterprises, and the energy industry. Based on the distribution data of electric vehicle traveling and charging characteristics obtained from the industry research, this study proposes a set of charging infrastructure prediction model based on the principle of energy supply-demand balance, predicts the development scale of charging infrastructure in the country and key cities, and further analyzes the market competition and future market margin of the key cities, and evaluates the difficulty of future market entry in the key cities, which provides a basis for further development of the charging infrastructure industry. The difficulty of entering the future market in each key city is assessed, providing business decision support for industry participants. In the future, the charging infrastructure development scale prediction results proposed by this study can be used as the input parameters of the charging pile layout planning model to enhance the scientific nature of the charging infrastructure layout and help the industry to develop in a high-quality manner.

PAG-TSN: Ridership Demand Forecasting Model for Shared Travel Services of Smart Transportation

With the increasing popularity of cab services such as Didi and Uber, cities are faced with the challenge of high carbon emissions and traffic congestion. Ride-sharing services, as a novel green mode of transportation, have emerged as a key technology in smart transportation for addressing these problems. The implementation of ride-sharing is predicated on an accurate ridership demand forecasting model, which can effectively prevent vehicle resource waste, alleviate traffic congestion, and reduce carbon emissions. In this paper, a periodic attentional graph convolutional spatio-temporal network model (PAG-TSN) is proposed to predict regional ridership demand. Specifically, the model is trained using a large amount of GPS data and user demand data collected by the travel service provider. PAG-TSN consists of two parts: the bicomponent attention graph convolution model (BAT-GCN) and the periodic attentional gated recurrent unit model (PA-GRU). The former uses GCN to extract spatial features from pointwise and edgewise graphs; the latter uses the spatial feature vectors extracted from the former with external information as input, and uses GRU to extract temporal features from feature data of different periods, and finally uses attention mechanism and POI requirement correlation to integrate the extracted spatio-temporal information to derive prediction results. Extensive experiments and evaluations on the CD2Date and XA2Date datasets show that PAG-TSN outperforms other baseline models in accurately predicting regional ridership demand, with MAPE and RMSE values of 0.1147 and 5.56, respectively.

Impact of a systematic framework for anticipatory compounding on medication waste reduction in a mid-size community hospital.

In current hospital pharmacy practice, the need to compound medications ahead of patient orders often results in an increase in medication waste. The purpose of this study was to implement a strategic approach for anticipatory sterile compounding and evaluate its effect on the reduction of expired medication waste. This was a pre-/post-intervention quasi-experimental study with 3 weeks of data collection for both arms and a 1-week washout period to implement process changes. A par log was placed on the medication storage refrigerator used for anticipatory compounding, with minimum and maximum levels determined by the demand-forecasting model. The primary outcome was the percentage of observations associated with waste. The secondary outcomes were the overall percentage of sterile compounding spending attributable to waste, median wasted dollars per sterile compounded product, and median dollars spent per sterile product compounded as anticipatory stock. Descriptive statistics were calculated using Minitab version 20, with the α level set to 0.05. A total of 4,619 observations were included in the analysis: 2,433 in the preintervention group and 2,186 in the postintervention group. Despite the median price being higher in the postintervention group than in the preintervention group, both the primary and secondary outcomes indicated that waste was reduced following the intervention. Overall, implementation of the framework reduced sterile products waste at our institution. More research is needed to evaluate the effects of this framework at institutions of different sizes and with different patient populations. Further research on probabilistic models for sterile compounded products is also needed.

Enhancing supply chain efficiency: a holistic examination of hybrid forecasting models employing mode and PERT technique as deterministic factors

ABSTRACT Inaccurate forecasts can cause severe financial consequences and disrupt supply chain operations for organisations. This study focuses on the pharmaceutical industry, renowned for its complex supply chain and diverse data attributes. It proposes a novel approach to identify the optimal combination of demand forecasting models that enhance accuracy by leveraging deterministic factors using Mode and PERT. By refining model selection in the pharmaceutical industry, this research aims to improve both forecasting precision and supply chain efficiency. A four-level framework based on deterministic factors is proposed to evaluate the extent of hybrid modelling in demand forecasting, empowering practitioners to make informed decisions even in challenging circumstances. The findings offer decision-makers flexibility in selecting suitable forecasting models and assist in tailoring methods to specific conditions. Furthermore, this research highlights the industry's ability to leverage digital technologies and transform existing forecasting methodologies, ensuring uninterrupted business operations during disruptions such as the COVID-19 pandemic.

Leveraging online reviews for hotel demand forecasting: A deep learning approach

The use of online reviews for forecasting hotel demand has gained increasing interest in recent years. However, prior studies have primarily focused on sentiment information and do not capture sufficient signals for accurate hotel demand forecasting. Furthermore, the complex feature interactions within multivariate time series complicate hotel demand forecasting. Guided by systematic functional linguistics (SFL) theory, this study proposes an analytic framework consisting of ideational, textual, and interpersonal functions to extract signals from online reviews. Besides, we propose a novel long short-term memory interaction-based convolutional neural network (LICNN) model for hotel demand forecasting. The results indicate that incorporating online review features reduces root mean squared error (RMSE) by at least 2.2 % and at most 46.6 %, mean absolute error (MAE) by at least 3.2 % and at most 44.8 %, and mean absolute percentage error (MAPE) by at least 3.5 % and at most 44.6 %. Moreover, compared with baseline models, our proposed LICNN model achieves the lowest RMSE (at least 15.8 % and at most 53.1 % improvements), MAE (at least 8.1 % and at most 56.1 % improvements), and MAPE (at least 12.9 % and at most 44.8 % improvements). The ablation study highlights the value of extracting feature interactions in demand forecasting.

Managing Healthcare Product Demand Effectively in The Post-Covid-19 Environment: Navigating Demand Variability and Forecasting Complexities

Managing the demand for healthcare products is a complex problem requiring in-depth knowledge of epidemiological trends, supply chain dynamics, and regulatory considerations. The intricate management of healthcare product demand in the post-COVID-19 era is thoroughly explored in this study. It is divided into nine sections exploring various facets of this critical field, emphasizing the persistent demand variations and difficulty in forecasting in the healthcare industry. It underscores the necessity for efficient demand management techniques in the changing healthcare environment. The significance of historical demand trends and provides examples of how studying historical data is essential for comprehending and forecasting the demand for healthcare products. Identifying seasonal fluctuations, forecasting disease outbreaks, and improving inventory management are emphasized. Investigating the difficulties in predicting the need for healthcare products, deals with problems caused by epidemiological ambiguity, supply chain breakdowns, patient demographics, regulatory adjustments, and technological advancements. The importance of data availability and quality in accurate demand forecasting is emphasized in this section. It encompasses scenario planning, resource allocation, technology adoption, supplier diversity, flexible manufacturing, collaborative and information sharing, data-driven decision-making, demand forecasting models, and strategic stockpiling. "Data Analytics and Predictive Modeling in Demand Forecasting," emphasize the function of these techniques in comprehending and forecasting demand trends. All covered are time series analysis, machine learning algorithms, epidemic predictive modeling, supply chain integration, scenario planning, optimization, risk assessment, in-the-moment monitoring, and feedback loops. "Supply Chain Resilience and Demand Response" explains why it's crucial to create robust supply chains and successfully adapt to demand changes. Supplier diversity, strategic stockpiling, agile production, real-time visibility, teamwork, data-driven decision-making, scenario planning, and regulatory flexibility are all covered

Online Ride-hailing Demand Prediction Model Based on GRU & LSTM

While online car-hailing provides fast and convenient services, it has the same problems in the process of ‘seeking customers’ as traditional taxis. With the research goal of the demand for online ride-hailing, an online ride-hailing demand forecast model based on G & LSTM is proposed. Firstly, grey relational degree analysis and other methods are used to analyze which and how the relevant factors affect the demand for online car-hailing. Secondly, the demand prediction model of online car-hailing based on GRU&LSTM is trained an adjusted. Through the adjustment and comparison experiment, the values of each parameter in the model are properly adjusted. Finally, based on the running data of Chengdu, the model proposed is verified and evaluated. The experimental results show that the GRU&LSTM prediction model has good prediction effect. By comparing the prediction effect of weighting data and unweighting data, it can be seen that weighted data has better prediction effect.

A Strep A vaccine global demand and return on investment forecast to inform industry research and development prioritization

Investment in Strep A vaccine R&D is disproportionately low relative to the large burden of Strep A diseases globally. This study presents a novel Strep A vaccine global demand and financial forecast model with estimates of potential global demand and associated revenue and profits for a hypothetical Strep A vaccine as well as a net present value (NPV) analysis of return on capital investments required to develop the vaccine. A positive NPV was calculated for a variety of developer scenarios and target populations, including the global rollout of the vaccine in private and public markets by a multinational pharmaceutical corporation and a staged rollout by a developing country vaccine manufacturer for both infant and child populations. The results suggest there is a viable commercial market for a Strep A vaccine. It is hoped that this study will help to inform industry decision-making and drive increased prioritization of, and investment in, Strep A vaccine research and development.

A new key performance indicator model for demand forecasting in inventory management considering supply chain reliability and seasonality

Forecasting demand and determining safety stocks are key aspects of supply chain planning. Demand forecasting involves predicting future demand for a product or service using historical data and other external and internal drivers. Stockouts and excess production can be reduced by accurately forecasting demand. This allows companies to plan production, inventory, and logistics more effectively. Companies maintain safety stocks in their inventory to protect against unexpected changes in demand or supply. A company must find the appropriate safety stock level to meet customer demands while avoiding excess inventory and carrying costs. Forecasting demand and determining safety stocks work together to help companies reduce costs, improve customer service, and optimize inventory levels. Key Performance Indicators (KPIs) are commonly used to measure model performance. Classical forecasting models mostly concern themselves with minimizing forecast errors. However, the impact on inventory costs is not directly considered. In this paper, we introduce a Key Performance Indicator to be used in the demand forecasting process that produces more efficient results in terms of inventory costs. We also propose a novel approach to determining the best level for safety stock. This approach considers logistic network supply reliability and seasonality indices identified within historical demand patterns. We use real-life data and show that the proposed method can improve efficiency in forecasting and safety stock levels by reducing the risk of stockouts and excess inventory.

Demand forecasting using a hybrid model based on artificial neural networks: A study case on electrical products

Purpose: This work aims to evaluate demand forecasting models to determine if using exogenous factors and machine learning techniques helps improve performance compared to univariate statistical models, allowing manufacturing companies to manage demand better.Design/methodology/approach: We implemented a multivariate Auto-Regressive Moving Average with eXogenous input (ARMAX) statistical model and a Neural Network-ARMAX (NN-ARMAX) hybrid model for forecasting. Later, we compared both to a standard univariate statistical model to forecast the demand for electrical products in a Colombian manufacturing company.Findings: The outcomes demonstrated that the NN-ARMAX model outperformed the other two. Indeed, demand management improved with the reduction of overstock and out-of-stock products.Research limitations/implications: The findings and conclusions in this work are limited to Colombian manufacturing companies that sell electrical products to the construction industry. Moreover, the experts from the company that provided us with the data also selected the external factors based on their own experiences, i.e., we might have disregarded potential factors.Practical implications: This work suggests that a model using neural networks and including exogenous variables can improve demand forecasting accuracy, promoting this approach in manufacturing companies dealing with demand planning issues.Originality/value: The findings in this work demonstrate the convenience of using the proposed hybrid model to improve demand forecasting accuracy and thus provide a reliable basis for its implementation in supply chain planning for the electrical/construction sector in Colombian manufacturing companies.

Supply Chain Demand Forecasting and Price Optimisation Models with Substitution Effect

Determining the optimal price of products is essential, as it plays a critical role in improving a company’s profitability and market competitiveness. This requires the ability to calculate customers’ demand in the Fast Moving Consumer Goods (FMCG) industry as various effects exist between multiple products within a product category. The substitution effect is one of the challenging effects at retail stores, as it requires investigating an exponential number of combinations of price changes and the availability of other products. This paper suggests a systematic price decision support tool for demand prediction and price optimise in online and stationary retailers considering the substitution effect. Two procedures reflecting the product price changes and the demand correlation structure are introduced for demand prediction and price optimisation models. First, the developed demand prediction procedure is carried out considering the combination of price changes of all products reflecting the effect of substitution. Time series and different well-known machine learning approaches with hyperparameter tuning and rolling forecasting methods are utilised to select each product’s best demand forecast. Demand forecast results are used as input in the price optimisation model. Second, the developed price optimisation procedure is a constraint programming problem based on a week time frame and a product category level aggregation and is capable of maximising profit out of the many price combinations. The results using real-world transaction data with 12 products and 4 discount rates demonstrate that including some business rules as constraints in the proposed price optimisation model reduces the number of price combinations from 11,274,924 to 19,440 and execution time from 129.59 to 25.831 min. The utilisation of the presented price optimisation support tool enables the supply chain managers to identify the optimal discount rate for individual products in a timely manner, resulting in a net profit increase.

Natural Gas Demand Forecasting Model Based on LASSO and Polynomial Models and Its Application: A Case Study of China

China aims to reduce carbon dioxide emissions and achieve peak carbon and carbon neutrality goals. Natural gas, as a high-quality fossil fuel energy, is an important transition resource for China in the process of carbon reduction, so it is necessary to predict China’s natural gas demand. In this paper, a novel natural gas demand combination forecasting model is constructed to accurately predict the future natural gas demand. The Lasso model and the polynomial model are used to build a combinatorial model, which overcomes the shortcomings of traditional models, which have low data dimensions and poor prediction abilities. In the modeling process, the cross-validation method is used to adjust the modeling parameters. By comparing the performance of the combinatorial forecasting model, the single forecasting model and other commonly used forecasting models, the results show that the error (2.99%) of the combinatorial forecasting model is the smallest, which verifies the high accuracy and good stability advantages of the combinatorial forecasting model. Finally, the paper analyzes the relevant data from 1999 to 2022 and predicts China’s natural gas demand in the next 10 years. The results show that the annual growth rate of China’s natural gas demand in the next 10 years will reach 13.33%, at 8.3 × 1011 m3 in 2033, which proves that China urgently needs to rapidly develop the gas supply capacity of gas supply enterprises. This study integrates the impact of multiple factors on the natural gas demand, predicts China’s natural gas demand from 2023 to 2033, and provides decision-making support for China’s energy structure adjustment and natural gas import trade.

Attention mechanism-based transfer learning model for day-ahead energy demand forecasting of shopping mall buildings

The forecasting performance of data-driven models decreases rapidly with a limited training dataset. Herein, we sought to solve this problem by developing an attention mechanism-based transfer learning model and comparing its predictive ability in day-ahead energy consumption with those of three direct learning models: artificial neural networks with auto-regression (AR-ANN), random forest with auto-regression (AR-RF), and long short-term memory neural network (LSTM). Our target building was a large-scale shopping mall in Harbin, with 2 years of monitored data. The 2-months to 1-year data selected from the first year and all data from the second year were used as the training and testing sets, respectively. These models predicted the target building's peak electricity demand (PED) and total energy consumption (TEC). The results showed that the proposed transfer learning model outperformed the three direct learning models when data were insufficient in the training set. Specifically, the direct prediction models' lowest PED and TEC prediction errors were 34.34% and 26.32%, respectively, with 2-month training data available. In comparison, the corresponding prediction errors of the proposed model were only 12.48% and 10.78%, respectively. This study demonstrated the excellent performance of the proposed model with limited data.

Research and application of load forecasting method for park integrated energy system based on XGBoost algorithm

Load forecasting is the basis of energy management and optimal dispatching of the park-integrated energy system, and its forecasting accuracy directly affects the overall operation performance of the system. Therefore, this paper proposes a load forecasting method for the park-integrated energy system based on the XGBoost algorithm. This paper first establishes the simulation analysis model of photovoltaic power generation and electric vehicle charging and discharging in the park and then carries out the supply and demand forecast and load characteristic modeling of the park’s energy system. Finally, this paper constructs the power prediction optimization control flow based on the XGBoost prediction model and uses the mean absolute percentage error (MAPE) and root mean square error (RMSE) as two evaluation indicators. The validity of the proposed method is verified by the data of the actual micro energy system in the park.

베트남 의료관광 수요 결정요인에 관한 연구

Purpose – The purpose of this study is to identify the predictive factors of medical tourism in Vietnam by analyzing the variables that lead to the annual visitor number. Design/methodology/approach – This study collected data from Vietnamese with experience in domestic and international medical tourism, and focused on Hanoi, Vietnam. In this study, the variable of medical tourism preferences was applied independently. Factors that impacted the number of annual visitors were estimated by the truncated Poisson model. Findings – The results of the TP model analysis of demand for medical tourism are as follows. Among the variables related to socio-economic characteristics, age, marital status, and occupation had a significantly positive effect on the number of annual medical visits. These results imply that it is important to understand socio-economic characteristics to expand demand for medical tourism in Vietnam, which shows high growth potential. The top three variables that gave a significant positive effect on the number of annual medical visitors are the level of medical technology, waiting time, and price, as well as medical service experience. Research implications – The results indicate the need to develop medical tourism products tailored to consumer tastes by subdividing medical technology levels, waiting for time and price, medical experience services, and so on. Thus, the results presented by this study create a starting point for the development of demand forecasting models for the domestic, international, and Vietnamese medical tourism markets in the future.

A Quasi-moment-method Modelling of Energy Demand Forecasting

This paper presents a novel approach to the modelling of electrical energy demand forecasting, based on the Quasi-Moment-Method (QMM). The technique, using historical energy consumption/demand data, essentially calibrates nominated ‘base’ models (in this case, nominal Harvey and Autoregressive models) to provide significantly better performing models. In addition to the novelty of the use of QMM, the paper identifies hitherto unreported singularities of the generic Harvey / logistic model, through which a simple, but remarkably pivotal modification is proposed, prior to the model’s use as base model in QMM calibration schemes. The treatment of the ‘Harvey singularities’ informed a similar and equally significant modification of the Autoregressive model utilized in the paper. For the purposes of validation and performance evaluation, computational results due to the QMM models are compared with corresponding results reported in three different journal publications, which utilized the Harvey and Autoregressive models in conventional regression schemes. And in terms of the usual model performance metrics (including Mean Absolute Percentage Error (MAPE) and Root Mean Square Percentage Error (RMSPE)), the results very clearly demonstrate the superiority of the QMM models for both energy demand prediction and forecasting. As representative examples, a QMM-calibrated Harvey model recorded an RMSE value of 495.45dB for total energy consumption prediction, as against 618.60dB obtained for the corresponding nominal Harvey model: and for the Autoregressive case, RMSE was obtained as 131.35dB for QMM model’s prediction of peak load demand, compared with the 173.40dB due to the nominal model.

Smart BRT Management System

Bus Rapid Transit (BRT) has increasingly become an attractive urban transit alternative in many developing cities due to its cost-effective and flexible implementation. However, it still seems difficult to introduce BRT to these cities because almost all their city structures have been built solely under a road transport development city plan which causes many problems, such as urban sprawl, traffic congestion, and air pollution. This system introduced several strategies to support BRT implementation in developing cities. These proposed strategies were evaluated by applying demand forecasting and emission models to the BRT project plan. It was demonstrated that the proposed strategies could effectively improve BRT ridership, traffic conditions, and air pollution emissions of the entire system. This study could be further extended to include strategy recommendations if a BRT system was introduced to other developing cities