A Study on an Extensive Hierarchical Model for Demand Forecasting of Automobile Components

Demand forecasting and big data analytics in supply chain management are gaining interest.This is attributed to the wide range of big data analytics in supply chain management,in addition to demand forecasting,and behavioral analysis.In this article,we studied the application of big data analytics forecasting in supply chain demand forecasting in the automotive parts industry to propose classifications of these applications,identify gaps,and provide ideas for future research.Algorithms will then be classified and then applied in supply chain management such as neural networks,k-nearest neighbors,time series forecasting,clustering,regression analysis,support vector regression and support vector machines.An extensive hierarchical model for short-term auto parts demand assess-ment was employed to avoid the shortcomings of the earlier models and to close the gap that regarded mainly a single time series.The concept of extensive relevance assessment was proposed,and subsequently methods to reflect the relevance of automotive demand factors were discussed.Using a wide range of skills,the factors and co-factors are expressed in the form of a correlation characteristic matrix to ensure the degree of influence of each factor on the demand for automotive components.Then,it is compared with the existing data and predicted the short-term historical data.The result proved the predictive error is less than 6%,which supports the validity of the prediction method.This research offers the basis for the macroeconomic regulation of the government and the production of auto parts manufacturers.

Inventory Management and Demand Forecasting Improvement of a Forecasting Model Based on Artificial Neural Networks

Forecasting is predicting or estimating a future event or trend.Supply chains have been constantly growing in most countries ever since the industrial revolution of the 18th century.As the competitiveness between supply chains intensifies day by day,companies are shifting their focus to predictive analytics techniques to minimize costs and boost productivity and profits.Excessive inventory(overstock)and stock outs are very significant issues for suppliers.Excessive inventory levels can lead to loss of revenue because the company's capital is tied up in excess inventory.Excess inventory can also lead to increased storage,insurance costs and labor as well as lower and degraded quality based on the nature of the product.Shortages or out of stock can lead to lost sales and a decline in customer contentment and loyalty to the store.If clients are unable to find the right products on the shelves,they may switch to another vendor or purchase alternative items.Demand forecasting is valuable for planning,scheduling and improving the coordination of all supply chain activities.This paper discusses the use of neural networks for seasonal time series forecasting.Our objective is to evaluate the contribution of the correct choice of the transfer function by proposing a new form of the transfer function to improve the quality of the forecast.

Hybrid LEAP modeling method for long-term energy demand forecasting of regions with limited statistical data

An accurate long-term energy demand forecasting is essential for energy planning and policy making. However, due to the immature energy data collecting and statistical methods, the available data are usually limited in many regions. In this paper, on the basis of comprehensive literature review, we proposed a hybrid model based on the long-range alternative energy planning (LEAP) model to improve the accuracy of energy demand forecasting in these regions. By taking Hunan province, China as a typical case, the proposed hybrid model was applied to estimating the possible future energy demand and energy-saving potentials in different sectors. The structure of LEAP model was estimated by Sankey energy flow, and Leslie matrix and autoregressive integrated moving average (ARIMA) models were used to predict the population, industrial structure and transportation turnover, respectively. Monte-Carlo method was employed to evaluate the uncertainty of forecasted results. The results showed that the hybrid model combined with scenario analysis provided a relatively accurate forecast for the long-term energy demand in regions with limited statistical data, and the average standard error of probabilistic distribution in 2030 energy demand was as low as 0.15. The prediction results could provide supportive references to identify energy-saving potentials and energy development pathways.

System Dynamics Approach to Urban Water Demand Forecasting—A Case Study of Tianjin

A system dynamics approach to urban water demand forecasting was developed based on the analysis of urban water resources system, which was characterized by multi-feedback and nonlinear interactions among sys-tem elements. As an example, Tianjin water resources system dynamic model was set up to forecast water resources demand of the planning years. The practical verification showed that the relative error was lower than 10%. Fur-thermore, through the comparison and analysis of the simulation results under different development modes pre-sented in this paper, the forecasting results of the water resources demand of Tianjin was achieved based on sustain-able utilization strategy of water resources.

Spare Parts Demand Forecasting:a Review

Spare parts are very common in industry and military fields, and the investigations of spare parts demand forecasting methods have draws much attention in recent years. However,to the best of our knowledge,only few papers reviewed the forecasting papers systematically. This paper is an attempt to provide a novel and comprehensive view to summarize these methods. A new framework was proposed to classify the demand forecasting methods into four categories,including empirical methods,methods based on historical data,analytical methods and simulation methods. Some typical literatures related to each category were reviewed.Moreover, a general spare parts forecasting procedure was summarized and some evaluation criteria were presented. Finally,characteristics of different forecasting methods and some avenues for further research were illustrated. This work provides the managers with a systematical idea about the spare parts demand forecasting and it can be used in practical applications.

Synthetic Reconstruction of Water Demand Time Series for Real Time Demand Forecasting

The forecasting of the demand applied to water supply systems has been an important tool to realize time control. The use of the time series to do the forecasting of the demand is the main way that has been used by researchers. By this way, the need of a complete time demand series increases. This work presents two ways to reconstruct the water demand time series synthetically, using the Average Reconstruction Method and Fourier Method. Both the methods were considered interesting to do the synthetic reconstruction and able to complete the time series, but the Fourier Method showed better results and a better fitness to approximation of the water consumption pattern.

Improved grey-based approach for power demand forecasting

Grey theory is a multidisciplinary and generic theory to cope with systems of poor or deficient information. We proposed in this paper an improved grey method (GM) to overcome the disadvantages of the general GM(1,1). In the improved GM(1,1), a new background value formula is deduced and Markov-chain sign estimation is imbedded into the residual modification model. We tested the efficiency and accuracy of our model by applying it to the power demand forecasting in Taiwan. Experimental results demonstrate the new method has obviously a higher prediction accuracy than the general model.

Equipment Maintenance Material Demand Forecasting Based on Gray-Markov Model

Maintenance material reserves must keep an appropriate scale,in order to meet the possible demand of support objectives.According to the sequence of maintenance material consumption,this paper establishes a Gray-Markov forecasting model by combining Gray system theory and Markov model. Few data are needed in the proposed Gray-Markov forecasting model which has high prediction precision by involving small parameters. The performance of Gray-Markov forecasting model was demonstrated using practical application and the model was proved to be a valid and accurate forecasting method. This Gray-Markov forecasting model can provide reference for making material demand plan and determining maintenance material reserves.

Design of an Evacuation Demand Forecasting Module for Hurricane Planning Applications

This paper discusses the development and implementation of an evacuation demand forecasting module that was incorporated into a comprehensive decision support system for the planning and management of contraflow operations in the Gulf of Mexico. Contraflow implies the reversing of one direction of a highway in order to permit a substantially increased travel demand exiting away from an area impacted by a natural disaster or any other type of catastrophic event. Correctly estimating the evacuation demand originated from such a catastrophic event is critical to a successful contraflow implementation. One problem faced by transportation officials is the arranging of the different stages of this complex traffic procedure. Both the prompt deployment of resources and personnel as well as the duration of the actual contraflow affect the overall effectiveness, safety and cost of the evacuation event. During this project, researchers from the University of Alabama developed an integral decision support system for contraflow evacuation planning to assist the Alabama Department of Transportation Maintenance Bureau in the evaluation and planning of contraflow operations oriented to mitigate the evacuation burdens of a hurricane event. This paper focuses on the design of the demand forecasting module of such a decision support system.

Research on inventory management and demand forecasting

With the rapid economic development and the increasing speed and scale of grid construction, material procurement and management, cost control is facing new demands and challenges.This paper proposes on innovative management and forecasting methods, from inventory management and demand forecasting perspective supplies,through these two key nodes in-depth research and analysis, this paper provides a theoretical support for the realization of effective materials management.

The Concept of MDSA （Macro Demand Spatial Approach） on Spatial Demand Forecasting for Main Development Area in Transmission Planning

MDSA （macro demand spatial approach） is an approach introduced in long time electricity demand forecasting considering location. It will be used at transmission planning and policy decision on electricity infrastructure development in a region. In the model, MDSA combined with PCA （principal component analysis） and QA （qualitative analysis） to determine main development area in region and the variables that affecting electricity demand in there. Main development area is an area with industrial domination as a driver of economic growth. The electricity demand driver variables are different for type of electricity consumer. However, they will be equal for main development areas. The variables which have no significant effect can be reduced by using PCA. The generated models tested to assess whether it still at the range of confidence level of electricity demand forecasting. At the case study, generated model for main development areas at South Sumatra Subsystem as a part of Sumatra Interconnection System is still in the range of confidence level. Thus, MDSA can be proposed as alternative approach in transmission planning that considering location.

Electricity demand forecasting at distribution and household levels using explainable causal graph neural network

Forecasting electricity demand is an essential part of the smart grid to ensure a stable and reliable power grid. With the increasing integration of renewable energy resources into the grid, forecasting the demand for electricity is critical at all levels, from the distribution to the household. Most existing forecasting methods, however, can be considered black-box models as a result of deep digitalization enablers, such as deep neural networks, which remain difficult to interpret by humans. Moreover, capture of the inter-dependencies among variables presents a significant challenge for multivariate time series forecasting. In this paper we propose eXplainable Causal Graph Neural Network (X-CGNN) for multivariate electricity demand forecasting that overcomes these limitations. As part of this method, we have intrinsic and global explanations based on causal inferences as well as local explanations based on post-hoc analyses. We have performed extensive validation on two real-world electricity demand datasets from both the household and distribution levels to demonstrate that our proposed method achieves state-of-the-art performance.

A demand forecasting model for urban air mobility in Chengdu,China

The successful application of new technologies such as remotely piloted aircraft systems,distributed electric propulsion systems,and automatic control systems on electric vertical take-off and landing(eVTOL)aircraft has prompted Urban Air Mobility(UAM)to be mentioned frequently.UAM is a newly raised transport mode of using eVTOL aircraft to transport people and cargo in urban areas,which is thought to share some of the traffic on the ground.One of the prerequisites for UAM to operate on a regular basis is that its demand can support the operating costs,so forecasting UAM demand is necessary.We conduct UAM demand forecasting based on the four-step method,focusing on improving the third-step modal split,and propose a demand forecasting model based on the logit model.The model combines a nested logit(NL)model with a multinomial logit(MNL)model to solve the problem of non-existent UAM sharing rates.We use Chengdu,China as an example,and focus on forecasting the UAM traffic demand in 2030 with the help of the four-step method.The results show that UAM is suitable for shared operation during the early stages.With a fully shared operation,the UAM share rate increases by 0.73%for every kilometer increase in distance.Moreover,UAM is more competitive than other modes for delivery distances exceeding 15 km.Finally,using the distributions of the share rate and traffic flow pattern from the simulation,we propose the routes that can be prioritized for UAM operations in Chengdu.

Tourism demand forecasting and tourists’search behavior:evidence from segmented Baidu search volume

Given the importance of web search volume for reflecting tourists'preferences for certain tourism services and destinations,incorporating these data into forecasting models can significantly improve forecasting performance.This study enriches the literature on tourism demand forecasting and tourists'search behavior through segmented Baidu search volume data.First,this study divides Baidu search volume data based on volume sources and periods.Then,by analyzing the most relevant keywords in tourism demand in different segments,this study captures the dynamic characteristics of tourist search behavior.Finally,this study adopts a series of econometric and machine learning models to further improve the performance of tourism demand and forecasting.The findings indicate that tourists’search behavior has changed significantly with the prevalence and popularization of 4G technology and suggest that search volume improves forecasting performance,especially search volume on mobile terminals,from 2014M1–2019M12.

A hybrid Wavelet-CNN-LSTM deep learning model for short-term urban water demand forecasting

Short-term water demand forecasting provides guidance on real-time water allocation in the water supply network, which help water utilities reduce energy cost and avoid potential accidents. Although a variety of methods have been proposed to improve forecast accuracy, it is still difficult for statistical models to learn the periodic patterns due to the chaotic nature of the water demand data with high temporal resolution. To overcome this issue from the perspective of improving data predictability, we proposed a hybrid Wavelet-CNN-LSTM model, that combines time-frequency decomposition characteristics of Wavelet Multi-Resolution Analysis (MRA) and implement it into an advanced deep learning model, CNN-LSTM. Four models - ANN, Conv1D, LSTM, GRUN - are used to compare with Wavelet-CNN-LSTM, and the results show that Wavelet-CNN-LSTM outperforms the other models both in single-step and multi-steps prediction. Besides, further mechanistic analysis revealed that MRA produce significant effect on improving model accuracy.

Water demand forecasting of Beijing using the Time Series Forecasting Method

It is essential to establish the water resources exploitation and utiliz~~tion planning, which is mainly based on recognizing and forecasting the water consumed structure rationally and scientifically. During the past 30 years （1980-2009）, mean annual precipil：ation and total water resource of Beijing have decreased by 6.89% and 31.37% compared with those per- ennial values, respectively, while total water consumption during the same [：period reached pinnacle historically. Accordingly, it is of great significance for the harmony between socio-economic development and environmental development. Based on analyzing total water consumption, agricultural, industrial, domestic and environmental water consumption, and evolution of water consumed structure, further driving forces of evolution of total water consumption and water consumed structure are revealed systematically. Prediction and dis- cussion are achieved for evolution of total water consumption, water consumed structure, and supply-demand situation of water resource in the near future of Beijing using Time Series Forecasting Method. The purpose of the endeavor of this paper is to provide scientific basis for the harmonious development between socio-economy and water resources, for the es- tablishment of rational strategic planning of water resources, and for the social sustainable development of Beijing with scientific bases.

Forecasting tourism demand by extracting fuzzy Takagi-Sugeno rules from trained SVMs

Tourism demand forecasting has attracted substantial interest because of the significant economic contributions of the fast-growing tourism industry. Although various quantitative forecasting techniques have been widely studied, highly accurate and understandable forecasting models have not been developed. The present paper proposes a novel tourism demand forecasting method that extracts fuzzy Takagi-Sugeno （T-S） rules from trained SVMs. Unlike previous approaches, this study uses fuzzy T-S models extracted from the outputs of trained SVMs on tourism data. Owing to the symbolic fuzzy rules and the generalization ability of SVMs, the extracted fuzzy T-S rules exhibit high forecasting accuracy and include understandable pre-condition parts for practitioners. Based on the tourism demand forecasting problem in Hong Kong SAR, China as a case study, empirical findings on tourist arrivals from nine overseas origins reveal that the proposed approach performs comparably with SVMs and can achieve better prediction accuracy than other forecasting techniques for most origins. The findings demonstrated that decision makers can easily interpret fuzzy T-S rules extracted from SVMs. Thus, the approach is highly beneficial to tourism market management. This finding demonstrates the excellent scientific and practical values of the proposed approach in tourism demand forecasting.

A Research on Demands Forecasting and Personnel Training of Tourism Talents A Case Study of Zhejiang Province

By analyzing the recent 15 years＇ statistical data of Zhejiang tourism human resources, this paper analyzes the status of Zhejiang tourism talents. ARIMA （Autoregressive Integrated Moving Average） model is a method of time series prediction. This paper predicts the trends of the next three years＇ demands of Zhejiang tourism talents based on ARIMA model in order to promote the tourism in Zhejiang Province. According to the demands forecasting, the number of the employees required by the hotels is 10 times of travel agencies in 2015. At last, some solutions and suggestions are provided such as strengthening the talents training establishing tourism talents mobility mechanism and improving tourism talents excitation mechanism

An empirical study on travel demand management modeling based on discrete choice method

In view of the problem that the requirements of travel demand management and traffic policy-sensitivity are ignored during the establishment process of the travel demand forecasting model, a discrete-choice-based travel demand forecasting model is proposed to demonstrate its applicability to travel demand management. A car-bus discrete choice model is established, including three variables, i. e,, individual socioeconomic characteristics, time, and cost, and the traffic policy-sensitivity is evaluated through two kinds of traffic policies： parking charges and bus priorities. The empirical results show that travel choice is insensitive to the policy of parking charges as 88. 41% of the travelers are insensitive to parking charges; travel choice is, however, sensitive to the policy of bus priorities as 67.70% of the car travelers and 77.02% of the bus travelers are sensitive to bus priorities. The discrete-choice-based travel demand forecasting model is quite policy-sensitive and also has a good adaptability for travel demand management when meeting the basic functions of the demand forecasting model.

Comparative study of univariate and multivariate strategy for short-term forecasting of heat demand density:Exploring single and hybrid deep learning models

Accurate short-term forecasting of heating energy demand is needed for achieving optimal building energy management,cost savings,environmental sustainability,and responsible energy consumption.Furthermore,short-term heating energy prediction contributes to zero-energy building performance in cold climates.Given the critical importance of short-term forecasting in heating energy management,this study evaluated six prevalent deep-learning algorithms to predict energy load,including single and hybrid models.The overall best-performing predictors were hybrid models using Convolutional Neural Networks,regardless of whether they were multivariate or univariate.Nevertheless,while the multivariate models performed better in the first hour,the univariate models often were more accurate in the final 24 h.Thus,the best-performing predictor of the first timestep was a multivariate hybrid Convolutional Neural Network–Recurrent Neural Network model with a coefficient of determination(R^(2))of 0.98 and the lowest mean absolute error.Yet,the best-performing predictor of the final timestep was the univariate hybrid model Convolutional Neural Network–Long Short-Term Memory with an R^(2)of 0.80.Also,the prediction accuracy of the best-performing multivariate hybrid models reduced faster per hour compared to the univariate models.These findings suggest that multivariate models may be better suited for early timestep predictions,while univariate models may be better suited for later time steps.Hence,combining the models can enhance accuracy at various timesteps for achieving high fidelity in forecasting and offering a comprehensive tool for energy management.