Demand Forecasting and Demand Management

2015 ◽  
pp. 94-127
Keyword(s):  
Demand Management ◽  
Demand Forecasting

scholarly journals Automotive OEM Demand Forecasting: A Comparative Study of Forecasting Algorithms and Strategies

2021 ◽  
Vol 11 (15) ◽  
pp. 6787
Author(s):  
Jože M. Rožanec ◽  
Blaž Kažič ◽  
Maja Škrjanc ◽  
Blaž Fortuna ◽  
Dunja Mladenić
Keyword(s):  
Machine Learning ◽  
Automotive Industry ◽  
Demand Management ◽  
Demand Forecasting ◽  
Machine Learning Algorithms ◽  
Superior Performance ◽  
Forecast Errors ◽  
Manufacturing Companies ◽  
Case Scenario ◽  
Crucial Component

Demand forecasting is a crucial component of demand management, directly impacting manufacturing companies’ planning, revenues, and actors through the supply chain. We evaluate 21 baseline, statistical, and machine learning algorithms to forecast smooth and erratic demand on a real-world use case scenario. The products’ data were obtained from a European original equipment manufacturer targeting the global automotive industry market. Our research shows that global machine learning models achieve superior performance than local models. We show that forecast errors from global models can be constrained by pooling product data based on the past demand magnitude. We also propose a set of metrics and criteria for a comprehensive understanding of demand forecasting models’ performance.

Demand Forecasting

2020 ◽  
pp. 1-21
Author(s):  
Natalie Nicole Mar Hernández ◽  
Patricia Cano-Olivos ◽  
Diana Sánchez-Partida ◽  
José-Luis Martínez-Flores ◽  
Santiago Omar Caballero-Morales
Keyword(s):  
Neural Networks ◽  
Demand Management ◽  
Demand Forecasting ◽  
Planning Horizon ◽  
Statistical Information ◽  
Production Data ◽  
Ann Model ◽  
Abc Classification ◽  
The City

This chapter provides a proposal for demand management in furniture SMEs located in the city of Puebla, México. The historical production data reviewed, and the classification of the most critical articles was made using the ABC classification methodology. Subsequently, the literature of SMEs was analyzed as well as the current situation and statistical information was sought. Additionally, it presented an overview of the models to forecast demand and applied to the most relevant articles. Due to the results and previous study, it was decided to implement a forecasting technique which is modelled by artificial neural networks. The ANN model developed with the TANSIGMOID transfer function by using MATLAB software. The appropriate forecasting techniques selected according to the variability of the demand of the articles takes a short-term planning horizon. This research will help the company reduce uncertainty, forecasting sales, and achieve better production planning through ANNs.

scholarly journals Power Demand Forecasting using Long Short-Term Memory (LSTM) Deep-Learning Model for Monitoring Energy Sustainability

2020 ◽  
Vol 12 (3) ◽  
pp. 1109 ◽  
Author(s):  
Choi ◽  
Cho ◽  
Kim
Keyword(s):  
Deep Learning ◽  
Short Term Memory ◽  
Demand Management ◽  
Demand Forecasting ◽  
Sudden Change ◽  
Residential Building ◽  
Error Rates ◽  
Seasonal Forecasting ◽  
Power Demand ◽  
Short Term

The purpose of this study is to design a novel custom power demand forecasting algorithm based on the LSTM Deep-Learning method regarding the recent power demand patterns. We performed tests to verify the error rates of the forecasting module, and to confirm the sudden change of power patterns in the actual power demand monitoring system. We collected the power usage data in every five-minute resolution in a day from some groups of the residential, public offices, hospitals, and industrial factories buildings in one year. In order to grasp the external factors and to predict the power demand of each facility, a comparative experiment was conducted in three ways; short-term, long-term, seasonal forecasting exp[eriments. The seasonal patterns of power demand usages were analyzed regarding the residential building. The overall error rates of power demand forecasting using the proposed LSTM module were reduced in terms of each facility. The predicted power demand data shows a certain pattern according to each facility. Especially, the forecasting difference of the residential seasonal forecasting pattern in summer and winter was very different from other seasons. It is possible to reduce unnecessary demand management costs by the designed accurate forecasting method.

scholarly journals Machine Learning and Data Analytic Techniques in Digital Water Metering: A Review

Water ◽  
2020 ◽  
Vol 12 (1) ◽  
pp. 294 ◽  
Author(s):  
Md Shamsur Rahim ◽  
Khoi Anh Nguyen ◽  
Rodney Anthony Stewart ◽  
Damien Giurco ◽  
Michael Blumenstein
Keyword(s):  
Machine Learning ◽  
Water Conservation ◽  
Demand Management ◽  
Relevant Literature ◽  
Demand Forecasting ◽  
Feedback Systems ◽  
Socioeconomic Analysis ◽  
Crucial Component ◽  
Significant Research ◽  
Data Analytic

Digital or intelligent water meters are being rolled out globally as a crucial component in improving urban water management. This is because of their ability to frequently send water consumption information electronically and later utilise the information to generate insights or provide feedback to consumers. Recent advances in machine learning (ML) and data analytic (DA) technologies have provided the opportunity to more effectively utilise the vast amount of data generated by these meters. Several studies have been conducted to promote water conservation by analysing the data generated by digital meters and providing feedback to consumers and water utilities. The purpose of this review was to inform scholars and practitioners about the contributions and limitations of ML and DA techniques by critically analysing the relevant literature. We categorised studies into five main themes: (1) water demand forecasting; (2) socioeconomic analysis; (3) behaviour analysis; (4) water event categorisation; and (5) water-use feedback. The review identified significant research gaps in terms of the adoption of advanced ML and DA techniques, which could potentially lead to water savings and more efficient demand management. We concluded that further investigations are required into highly personalised feedback systems, such as recommender systems, to promote water-conscious behaviour. In addition, advanced data management solutions, effective user profiles, and the clustering of consumers based on their profiles require more attention to promote water-conscious behaviours.

Designing cost effective water demand management programs in Australia

2002 ◽  
Vol 46 (6-7) ◽  
pp. 225-232 ◽  
Author(s):  
S.B. White ◽  
S.A. Fane
Keyword(s):  
Water Conservation ◽  
Traditional Approach ◽  
Demand Management ◽  
Unit Cost ◽  
Demand Forecasting ◽  
Cost Effective ◽  
Resource Planning ◽  
Conservation Strategies ◽  
Recent Experience ◽  
End Use

This paper describes recent experience with integrated resource planning (IRP) and the application of least cost planning (LCP) for the evaluation of demand management strategies in urban water. Two Australian case studies, Sydney and Northern New South Wales (NSW) are used in illustration. LCP can determine the most cost effective means of providing water services or alternatively the cheapest forms of water conservation. LCP contrasts to a traditional approach of evaluation which looks only at means of increasing supply. Detailed investigation of water usage, known as end-use analysis, is required for LCP. End-use analysis allows both rigorous demand forecasting, and the development and evaluation of conservation strategies. Strategies include education campaigns, increasing water use efficiency and promoting wastewater reuse or rainwater tanks. The optimal mix of conservation strategies and conventional capacity expansion is identified based on levelised unit cost. IRP uses LCP in the iterative process, evaluating and assessing options, investing in selected options, measuring the results, and then re-evaluating options. Key to this process is the design of cost effective demand management programs. IRP however includes a range of parameters beyond least economic cost in the planning process and program designs, including uncertainty, benefit partitioning and implementation considerations.

scholarly journals Demand Analysis Models for Passenger Air Transportation

2020 ◽  
Vol 18 (1) ◽  
pp. 134-144
Author(s):  
V. E. Zhukov
Keyword(s):  
Quantitative Methods ◽  
Expert Knowledge ◽  
Demand Management ◽  
Demand Forecasting ◽  
Air Transportation ◽  
Demand Analysis ◽  
Air Transport ◽  
Demand Forecast ◽  
Route Network ◽  
Transport Services

Analysis of demand for air transportation is a key business process around which each airline develops strategic and operational plans. Based on the demand forecast, strategic plans for development of the airline’s route network are developed, as well as budgeting, financial planning, sales and marketing plans, aircraft fleet planning, risk assessment and plans to overcome their consequences. Demand analysis also facilitates important management activities, such as decision-making, performance evaluation, and reasonable allocation of resources in specific and uncertain conditions for development of the air transport system. Based on the specific requirements of the airline or in relation to a specific airline, an individual demand forecasting model can be developed. Such a model is an extension or a combination of various qualitative and quantitative methods for forecasting demand. The task of developing a custom model is often iterative, highly detailed, and driven by expert knowledge and can be accomplished by introducing suitable demand management software. The task stated in the article is not a staging task for building a model, but only offers to study the available theoretical material for the analysis of demand for air transportation based on the most famous models for forecasting demand for transportation. The method of scientific research of the problem posed in the article is the method of scientific analysis of existing models. Offer and demand for air transport services are reciprocal but asymmetric. Although the realized demand for transportation cannot take place without an appropriate level of supply, an air transport service can exist without appropriate demand. This is often found in projects that are developed with a margin that meets the expected level of demand, which may or may not be realized, or it may take several years to be realized. Regular air transport services form a supply that exists even if demand is insufficient. Several models presented in the article emphasize the conditions in which there is supply saturation, and on the other hand, the models in which demand is formed due to the mutual attractiveness of the entities that form demand are considered.

Demand Forecasting Models With Time Series and Random Forest

2021 ◽  
pp. 76-99
Author(s):  
Halit Alper Tayali
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Random Forest ◽  
Operations Management ◽  
Production Management ◽  
Demand Management ◽  
Demand Forecasting ◽  
Time Series Forecasting ◽  
The Novel ◽  
Forecasting Models

This chapter presents the recent methodological developments in demand management and demand forecasting subjects of the operations management. The background section provides detailed information on the domain of production management, operational analytics, and demand forecasting while providing introductory information on time series forecasting and related machine learning methodologies. The novel contribution of the chapter is the exploration developed in the solutions and recommendations section while examining the effect of stationarity in the time series forecasting methodologies of machine learning with improved benchmark results.

scholarly journals How does the built environment affect transit use by train, tram and bus?

2020 ◽  
Vol 13 (1) ◽  
pp. 625-650
Author(s):  
Chris De Gruyter ◽  
Tayebeh Saghapour ◽  
Liang Ma ◽  
Jago Dodson
Keyword(s):  
Land Use ◽  
Built Environment ◽  
Public Transport ◽  
Demand Management ◽  
Explanatory Power ◽  
Demand Forecasting ◽  
Explanatory Variables ◽  
Transport Services ◽  
Transit Ridership ◽  
Transit Use

While much research has explored the influence of the built environment on public transport use, little focus has been given to how this influence varies by public transport mode. Using a case study of Melbourne, this study assesses the influence of the built environment and other characteristics (transit service quality, demand management and socio-demographics) on commuting by train, tram and bus. Key findings indicate that the built environment has a significant influence, but with notable differences between individual public transport modes. Commuting by tram was found to have the strongest association with the explanatory variables, while bus had the weakest explanatory power. Differences in the geographical coverage of public transport services in Melbourne play a key role in explaining the influence of the built environment. Population density is positively associated with tram use, which operates in older, higher density environments, but is negatively associated with train and bus use. Furthermore, the association with land-use mix is only significant for train and tram use, as buses tend to operate in areas with greater land-use homogeneity. When focused on inner Melbourne only, the influence of the built environment is diluted, while distance to public transport becomes more significant. The findings have important implications for practice, not only in terms of improving transit demand forecasting but also in targeting changes to the built environment to leverage higher transit ridership by mode.

Product Demand Forecasting in Ecommerce Based on Nonlinear Autoregressive Neural Network

2021 ◽  
Author(s):  
Peijian Wu ◽  
Yulu Chen
Keyword(s):  
Neural Network ◽  
Demand Management ◽  
Time Series Prediction ◽  
Demand Forecasting ◽  
Set Partition ◽  
Data Set ◽  
Product Demand ◽  
Real Scene ◽  
Nonlinear Autoregressive ◽  
Autoregressive Neural Network

Abstract With the rapid growth of the e-commerce business scale, to meet customers' demand for efficient order processing, it is of great significance to establish an order management mechanism capable of responding quickly by accurately predicting product demand. This study used real e-commerce order demand data and established a nonlinear autoregressive neural network (NAR) model after pre-processing methods including down-sampling and data set partition to effectively forecast the demand of products in the next 13 weeks. Compared with the Prophet time series prediction framework, NAR had better generalization ability, and the prediction time was reduced by 18.54%. Finally, we summarized two methods' characteristics and gave instructions on applying our model in the real scene. After being deployed in the actual demand management, the trained artificial neural network provides a scientific reference for the data-driven e-commerce decision-making process and brings new advantages over other companies, achieving the rational allocation of resources.

Price Responsive Demand Management of an Industrial Buyer in Day-ahead Electricity Market

2017 ◽  
Vol 18 (1) ◽  
Author(s):  
Arvind Kumar Jain ◽  
S. C. Srivastava
Keyword(s):  
Cost Saving ◽  
Electricity Market ◽  
Demand Management ◽  
Demand Forecasting ◽  
High Price ◽  
Bidding Strategy ◽  
Transmission Congestion ◽  
Market Clearing ◽  
Purchase Cost ◽  
Bus System

Abstract An industrial buyer, who can reschedule its production plan, may develop strategic bid by shifting its demand from high price period to low price period. Based on this concept, a new optimization formulation has been proposed to develop bidding strategy of such buyers considering Price Responsive Demand Shifting (PRDS). Since the bidding strategy of the buyer depends upon the market clearing price, which is volatile/uncertain due to various factors like gaming behavior of participants, demand forecasting error, transmission congestion etc, the proposed optimization problem is formulated as a stochastic linear problem, comprising of two sub-problems. The first sub-problem represents the market clearing process by the System Operator, which is formulated to maximize the social welfare of the market participants, while the second sub-problem aims at maximizing the purchase cost saving of the industrial buyer. The optimal bidding strategy has been obtained by solving these two sub-problems considering hourly market clearing for 24-hour scheduling period. The effectiveness of the proposed method has been tested on a 5-bus system and modified IEEE 30-bus system. Results obtained with the demand shifting based bidding strategy have been compared with those obtained with a Conventional Price Quantity (CPQ) bid strategy. It has been observed that the proposed approach leads to enhancement in the purchase cost saving as compared to the CPQ and meets the energy consumption targets of the industrial buyer.

Sign in / Sign up

Export Citation Format

Share Document