Accurate Demand Prediction Research Articles

Intercity Online Car-Hailing Travel Demand Prediction via a Spatiotemporal Transformer Method

Traffic prediction is a critical aspect of many real-world scenarios that requires accurate traffic status predictions, such as travel demand prediction. The emergence of online car-hailing activities has given people greater mobility and makes intercity travel more frequent. The increase in online car-hailing demand has often led to a supply–demand imbalance where there is a mismatch between the immediate availability of car-hailing services and the number of passengers in certain areas. Accurate prediction of online car-hailing demand promotes efficiencies and minimizes resources and time waste. However, many prior related studies often fail to fully utilize spatiotemporal characteristics. With the development of newer deep-learning models, this paper aims to solve online car-hailing problems with an ST-transformer model. The spatiotemporal characteristics of online car-hailing data are analyzed and extracted. The study region is divided into subareas, and the demand for each subarea is summed at a specific time interval. Historical demand of the areas is used to predict future demand. The results of the ST-transformer outperformed other baseline models, namely, VAR, SVR, LSTM, LSTNet, and transformers. The validated results suggest that the ST-transformer is more capable of capturing spatiotemporal characteristics compared to the other models. Additionally, compared to others, the model is less affected by data sparsity.

A new insight for real-time wastewater quality prediction using hybridized kernel-based extreme learning machines with advanced optimization algorithms.

Accurate prediction of inlet chemical oxygen demand (COD) is vital for better planning and management of wastewater treatment plants. The COD values at the inlet follow a complex nonstationary pattern, making its prediction challenging. This study compared the performance of several novel machine learning models developed through hybridizing kernel-based extreme learning machines (KELMs) with intelligent optimization algorithms for the reliable prediction of real-time COD values. The combined time-series learning method and consumer behaviours, estimated from water-use data (hour/day), were used as the supplementary inputs of the hybrid KELM models. Comparison of model performances for different input combinations revealed the best performance using up to 2-day lag values of COD with the other wastewater properties. The results also showed the best performance of the KELM-salp swarm algorithm (SSA) model among all the hybrid models with a minimum root mean square error of 0.058 and mean absolute error of 0.044.

Prediction and analysis of water resources demand in Taiyuan City based on principal component analysis and BP neural network

Abstract Water is a fundamental natural and strategic economic resource that plays a vital role in promoting economic and social development. With the accelerated urbanization and industrialization in China, the potential demand for water resources will be enormous. Therefore, accurate prediction of water resources demand is important for the formulation of industrial and agricultural policies, development of economic plans, and many other aspects. In this study, we develop a model based on principal component analysis (PCA) and back propagation (BP) neural network to predict water resources demand in Taiyuan, Shanxi Province, a city with severe water shortage in China. The prediction accuracy is then compared with PCA-ANN, ARIMA, NARX, Grey–Markov, serial regression, and LSTM models, and the results showed that the PCA-BP model outperformed other models in many evaluation factors. The proposed PCA-BP model reduces the dimensionality of high-dimensional variables by PCA and transformed them into uncorrelated composite data, which can make them easier to compute. More importantly, BP and weight threshold adjustment in model training further improve the prediction accuracy of the model. The model analysis will provide an important reference for water demand assessment and optimal water allocation in other regions.

Energy prediction for CNC machining with machine learning

Nowadays, the reduction of CO2 emissions by moving from fossil to renewable energy sources is on the policy of many governments. At the same time, these governments are forcing the reduction of energy consumption. Since large industries have been in the focus for the last decade, today also small and medium enterprises with production lot size one are increasingly being obliged to reduce their energy requirements in production. Energy-efficient CNC machine tools contribute to this goal. In machining processes, the machining strategy also has a significant influence on energy demand. For manufacturing of lot size one, the prediction of the energy demand of a machining strategy, before a part is manufactured plays a decisive role. In numerous previous studies, analytical models between the energy demand and the machining strategy have been developed. However, their accuracy depends largely on the parameterization of these models by dedicated experiments. In this paper, different machine learning algorithms, especially variations of the decision tree (’DecisionTree’, ’RandomForest’, boosted ’RandomForest’) are investigated for their ability to predict the energy demand of CNC machining operations based on real production data, without the need for dedicated experiments. As shown in this paper, the most accurate energy demand predictions can be achieved with the ’RandomForest’ algorithm.

머신러닝을 활용한 공군 수리부속 수요예측 정확도 개선에 관한 연구

The following research is conducted to study how much demand prediction accuracy is improved when machine learning is implemented on ROKAF spare parts demand prediction calculations. Based on the data from the last three years of ROKAF’s three major aircraft models, the study compares the demand prediction accuracy values computed through the time series technique and machine learning models. Generally utilized machine learning models, such as Decision Tree(DT), Linear Discriminant Analysis (LDA), Logistic Regression(LR), K-Nearest Neighbor (K-NN) and Support Vector Machines (SVM), were implemented. Experiment results show that all machine learning models yield higher accuracy of the demand prediction than the time series technique. SVM, DT, K-NN and LR machine learning models yield excellent results, with accuracy values higher than 85%, while the LDA model shows relatively poor performance.

Demand Forecasting of Online Car-Hailing with Combining LSTM + Attention Approaches

The accurate prediction of online car-hailing demand plays an increasingly important role in real-time scheduling and dynamic pricing. Most studies have found that the demand of online car-hailing is highly correlated with both temporal and spatial distributions of journeys. However, the importance of temporal and spatial sequences is not distinguished in the context of seeking to improve prediction, when in actual fact different time series and space sequences have different impacts on the distribution of demand and supply for online car-hailing. In order to accurately predict the short-term demand of online car-hailing in different regions of a city, a combined attention-based LSTM (LSTM + Attention) model for forecasting was constructed by extracting temporal features, spatial features, and weather features. Significantly, an attention mechanism is used to distinguish the time series and space sequences of order data. The order data in Haikou city was collected as the training and testing datasets. Compared with other forecasting models (GBDT, BPNN, RNN, and single LSTM), the results show that the short-term demand forecasting model LSTM + Attention outperforms other models. The results verify that the proposed model can support advanced scheduling and dynamic pricing for online car-hailing.

Water demand prediction optimization method in Shenzhen based on the zero-sum game model and rolling revisions

AbstractIn this study, a deep learning model based on zero-sum game (ZSG) was proposed for accurate water demand prediction. The ensemble learning was introduced to enhance the generalization ability of models, and the sliding average was designed to solve the non-stationarity problem of time series. To solve the problem that the deep learning model could not predict water supply fluctuations caused by emergencies, a hypothesis testing method combining Student's t-test and discrete wavelet transform was proposed to generate the envelope interval of the predicted values to carry out rolling revisions. The research methods were applied to Shenzhen, a megacity with extremely short water resources. The research results showed that the regular bidirectional models were superior to the unidirectional model, and the ZSG-based bidirectional models were superior to the regular bidirectional models. The bidirectional propagation was conducive to improving the generalization ability of the model, and ZSG could better guide the model to find the optimal solution. The fluctuations in water supply were mainly caused by the floating population, but the fluctuation was still within the envelope interval of the predicted values. The predicted values after rolling revisions were very close to the measured values.

Iterative Prediction-and-Optimization for E-Logistics Distribution Network Design

The emergence of online retailers has brought new opportunities to the design of their distribution networks. Notably, for online retailers that do not operate offline stores, their target customers are more sensitive to the quality of logistic services, such as delivery speed and reliability. This paper is motivated by a leading online retailer for cosmetic products on Taobao.com that aimed to improve its logistics efficiency by redesigning its centralized distribution network into a multilevel one. The multilevel distribution network consists of a layer of primary facilities to hold stocks from suppliers and transshipment and a layer of secondary facilities to provide last-mile delivery. There are two major challenges of designing such a facility network. First, online customers can respond significantly to the change of logistics efficiency with the redesigned network, thereby rendering the network optimized under the original demand distribution suboptimal. Second, because online retailers have relatively small sales volumes and are very flexible in choosing facility locations, the facility candidate set can be large, causing the facility location optimization challenging to solve. To this end, we propose an iterative prediction-and-optimization strategy for distribution network design. Specifically, we first develop an artificial neural network (ANN) to predict customer demands, factoring in the logistic service quality given the network and the city-level purchasing power based on demographic statistics. Then, a mixed integer linear programming (MILP) model is formulated to choose facility locations with minimum transportation, facility setup, and package processing costs. We further develop an efficient two-stage heuristic for computing high-quality solutions to the MILP model, featuring an agglomerative hierarchical clustering algorithm and an expectation and maximization algorithm. Subsequently, the ANN demand predictor and two-stage heuristic are integrated for iterative network design. Finally, using a real-world data set, we validate the demand prediction accuracy and demonstrate the mutual interdependence between the demand and network design. Summary of Contribution: We propose an iterative prediction-and-optimization algorithm for multilevel distribution network design for e-logistics and evaluate its operational value for online retailers. We address the issue of the interplay between distribution network design and the demand distribution using an iterative framework. Further, combining the idea in operational research and data mining, our paper provides an end-to-end solution that can provide accurate predictions of online sales distribution, subsequently solving large-scale optimization problems for distribution network design problems.

Application of Artificial Intelligence to Evaluate the Fresh Properties of Self-Consolidating Concrete.

This paper numerically investigates the required superplasticizer (SP) demand for self-consolidating concrete (SCC) as a valuable information source to obtain a durable SCC. In this regard, an adaptive neuro-fuzzy inference system (ANFIS) is integrated with three metaheuristic algorithms to evaluate a dataset from non-destructive tests. Hence, five different non-destructive testing methods, including J-ring test, V-funnel test, U-box test, 3 min slump value and 50 min slump (T50) value were performed. Then, three metaheuristic algorithms, namely particle swarm optimization (PSO), ant colony optimization (ACO) and differential evolution optimization (DEO), were considered to predict the SP demand of SCC mixtures. To compare the optimization algorithms, ANFIS parameters were kept constant (clusters = 10, train samples = 70% and test samples = 30%). The metaheuristic parameters were adjusted, and each algorithm was tuned to attain the best performance. In general, it was found that the ANFIS method is a good base to be combined with other optimization algorithms. The results indicated that hybrid algorithms (ANFIS-PSO, ANFIS-DEO and ANFIS-ACO) can be used as reliable prediction methods and considered as an alternative for experimental techniques. In order to perform a reliable analogy of the developed algorithms, three evaluation criteria were employed, including root mean square error (RMSE), Pearson correlation coefficient (r) and determination regression coefficient (R2). As a result, the ANFIS-PSO algorithm represented the most accurate prediction of SP demand with RMSE = 0.0633, r = 0.9387 and R2 = 0.9871 in the testing phase.

A multi-task memory network with knowledge adaptation for multimodal demand forecasting

Travel demand forecasting is useful for both trip and service planning, and thus is of great importance. Most existing studies focus on demand forecasting for a single mode, while much less attention has been paid to multimodal demand forecasting. This paper develops a multimodal demand forecasting approach, which can learn and utilize information/knowledge from different public transit modes and thus improve the demand prediction of the travel mode with sparse observations (e.g., station-sparse mode). In particular, this study focuses on improving the passenger demand prediction accuracy of the station-sparse mode(s) with the help of the station-intensive mode (i.e., the mode with more sufficient knowledge and intensive station distribution over space). We propose a novel Knowledge Adaptation with Attentive Multi-task Memory Network (KA2M2) in order to utilize closely-related demand patterns from the station-intensive mode for demand forecasting of the station-sparse mode(s). Specifically, we first design a memory-augmented recurrent network for enhancing the ability to capture the long-and-short term demand information and storing the extracted temporal knowledge of each transit mode. Then, we develop and integrate an attention-based knowledge adaptation module to adapt relevant information from the station-intensive source to the station-sparse source(s). The experimental results on a real-world dataset collected from the Greater Sydney area covering four public transport modes (bus, train, light rail, and ferry) demonstrate that the proposed approach consistently outperforms a number of baseline methods and state-of-the-art models. Our findings also illustrate that incorporating information/knowledge from multimodal trip records can enhance the demand forecasting accuracy for station-sparse modes.

Long-term hybrid prediction method based on multiscale decomposition and granular computing for oxygen supply network

An accurate long-term prediction of oxygen demand can provide guidance for planning and scheduling the real production of the steel industry. In this paper, a polynomial-feature granulation prediction method based on long short-term memory network (GLSTM) is first developed and uses quadratic polynomials to form linguistic descriptors for data granules and perform prediction with LSTM. Considering the multiscale characteristics of oxygen flow data, a long-term oxygen demand prediction method based on multiscale decomposition and granular computing for oxygen supply network is further proposed. In this method, oxygen flow data are decomposed into low-, middle-, and high-frequency sublayers by empirical wavelet transformation. After removing the high-frequency noise sublayers, the GLSTM algorithm is employed to predict the low-frequency sublayers, while the k-SVM is employed to predict the middle-frequency sublayers. Finally, the effectiveness and performance of the proposed method is demonstrated in an industrial case study.

Short-Term Demand Prediction Using an Ensemble of Linearly-Constrained Estimators

The benefits of forecasting power demand can bring increased stability to any power grid. Between optimizing the production and control of grid resources and interacting with energy markets, there is a strong motivation for generation, transmission, and distribution grid stakeholders to obtain accurate power demand prediction, which requires more sophisticated prediction methods. We introduce an ensemble of linear predictive nodes called the Ensemble Prediction Network (EPN), which optimizes demand prediction motivated by various microgrid considerations. EPN outputs a nonlinear combination of the individual predictions whose mixing weights are optimized in the least-squares sense. Using a large number of publicly available datasets, we show that on-the-whole, EPN provides substantial improvement relative to each individual predictor. Furthermore, we compare our method with a Long Short-Term Memory (LSTM) neural network and a multi-layer perceptron, and demonstrate the advantages of the proposed method.

Forecasting Oil Demand with the Development of Comprehensive Tourism

The prediction of oil demand is an important issue related to national energy security and economic development. With the COVID-19 outbreak, the international oil price fluctuates sharply, and oil consumption growth slows down. Therefore, accurate prediction of oil demand plays an important practical and theoretical role. In this paper, in accordance with the Chinese state policy stimulation of domestic demand for energy resources, we have selected 15 major factors and analyzed their influence on the domestic oil demand from the perspective of comprehensive tourism analysis. Based on the data analysis of oil consumption from 2000 to 2018, four neutral network methods are used to predict the influence of selected factors on oil consumption demand of China. The experimental results show that the best correlation is obtained between domestic tourism revenue and total tourism expenditure factors and oil demand, and the Layer Recurrent Neutral Network method has high prediction accuracy, stronger stability, and the best performance.

Probabilistic Model for Resource Demand Prediction in Cloud

Dynamic cloud infrastructure provisioning is possible with the virtualization technology. Cost, agility and time to market are the key elements of the cloud services. Virtualization is the software layer responsible for interaction with multiple servers, bringing entire IT resources together and provide standardized Virtual compute centers that drives the entire infrastructure. The increased pooling of shared resources helps in improving self-provisioning and automation of service delivery. Probabilistic model proposed in this article is based on the hypothesis that the accurate resource demand predictions can benefit in improving the virtualization layer efficiency. The probabilistic method, uses the laws of combinatorics. The probability space gives an idea about both the partial certainty and randomness of the variable. The method is popular in theoretical computer science. The probabilistic models provide the predictions considering the randomness of the variables. In the cloud environment there are multiple factors dynamically affecting the resource demand needs. The resource demand has a certain degree of certainty but the randomness of requirements. This further leads to decrease in risk related to leveraging cloud services. It accelerates development and implementation of cloud services that overall improves the services pertaining to SLA.

Neural Networks with Improved Extreme Learning Machine for Demand Prediction of Bike-sharing

Accurate demand prediction of bike-sharing is an important prerequisite to reducing the cost of scheduling and improving the user satisfaction. However, it is a challenging issue due to stochasticity and non-linearity in bike-sharing systems. In this paper, a model called pseudo-double hidden layer feedforward neural networks is proposed to approximately predict actual demands of bike-sharing. Specifically, to overcome limitations in traditional back-propagation learning process, an algorithm, an extreme learning machine with improved particle swarm optimization, is designed to construct learning rules in neural networks. The performance is verified by comparing with other learning algorithms on the dataset of Streeter Dr bike-sharing station in Chicago.

A Multi-Task Matrix Factorized Graph Neural Network for Co-Prediction of Zone-Based and OD-Based Ride-Hailing Demand

Ride-hailing service has witnessed a dramatic growth over the past decade but meanwhile raised various challenging issues, one of which is how to provide a timely and accurate short-term prediction of supply and demand. While the predictions for zone-based demand have been extensively studied, much less efforts have been paid to the predictions for origin-destination (OD) based demand (namely, demand originating from one zone to another). However, OD-based demand prediction is even more important and worth further explorations, since it provides more elaborate trip information in the near future as reference for fine-grained operations, such as the routing and matching of shared ride-hailing services that pick up and drop off two or more passengers in each ride. Simultaneous prediction of both zone-based and OD-based demand can be an interesting and practical problem for the ride-hailing platforms. To address the issue, we propose a multi-task matrix factorized graph neural network (MT-MF-GCN), which consists of two major components: (1) a GCN (graph convolutional network) basic module that captures the spatial correlations among zones via mixture-model graph convolutional (MGC) network, and (2) a matrix factorization module for multi-task predictions of zone-based and OD-based demand. By evaluations on the real-world on-demand data in Manhattan and Haikou, we show that the proposed model outperforms the state-of-the-art baseline methods in both zone- and OD-based predictions.

A combined deep learning application for short term load forecasting

An accurate prediction of buildings' load demand is one of the most important issues in smart grid and smart building applications. In this way, an important contribution is made to improving the reliability of the power system, facilitating the integration of renewable energy sources and making demand response processes more effective. Nowadays, the electricity prediction based on sensor data has become quite common with the increasing popularity of smart meter applications. While such approaches produce very successful results, they often require large amounts of data recorded over long periods of time during the training of machine learning models to make accurate predictions. The fact that smart meter and sensor applications are becoming more widespread in different parts of the world and that the newly constructed buildings and new meters have relatively small historical data is an important constraint for sensor-based approaches. In this article, a cross-correlation based transfer learning approach is proposed on getting data from different parts of the world to obtain more successful predictive results with limited data. Results of application on actual energy system validate the advantages of proposed model.

Burst Detection by Water Demand Nowcasting Based on Exogenous Sensors

Bursts of drinking water pipes not only cause loss of drinking water, but also damage below and above ground infrastructure. Short-term water demand forecasting is a valuable tool in burst detection, as deviations between the forecast and actual water demand may indicate a new burst. Many of burst detection methods struggle with false positives due to non-seasonal water consumption as a result of e.g. environmental, economic or demographic exogenous influences, such as weather, holidays, festivities or pandemics. Finding a robust alternative that reduces the false positive rate of burst detection and does not rely on data from exogenous processes is essential. We present such a burst detection method, based on Bayesian ridge regression and Random Sample Consensus. Our exogenous nowcasting method relies on signals of all nearby flow and pressure sensors in the distribution net with the aim to reduce the false positive rate. The method requires neither data of exogenous processes, nor extensive historical data, but only requires one week of historical data per flow/pressure sensor. The exogenous nowcasting method is compared with a common water demand forecasting method for burst detection and shows sufficiently higher Nash-Sutcliffe model efficiencies of 82.7% - 90.6% compared to 57.9% - 77.7%, respectively. These efficiency ranges indicate a more accurate water demand prediction, resulting in more precise burst detection.

Prediction Modelling of Cold Chain Logistics Demand Based on Data Mining Algorithm

Modern information technologies such as big data and cloud computing are increasingly important and widely applied in engineering and management. In terms of cold chain logistics, data mining also exerts positive effects on it. Specifically, accurate prediction of cold chain logistics demand is conducive to optimizing management processes as well as improving management efficiency, which is the main purpose of this research. In this paper, we analyze the existing problems related to cold chain logistics in the context of Chinese market, especially the aspect of demand prediction. Then, we conduct the mathematical calculation based on the neural network algorithm and grey prediction. Two forecasting models are constructed with the data from 2013 to 2019 by R program 4.0.2, aiming to explore the cold chain logistics demand. According to the results estimated by the two models, we find that both of models show high accuracy. In particular, the prediction of neural network algorithm model is closer to the actual value with smaller errors. Therefore, it is better to consider the neural network algorithm as the first choice when constructing the mathematical forecasting model to predict the demand of cold chain logistic, which provides a more accurate reference for the strategic deployment of logistics management such as optimizing automation and innovation in cold chain processes to adapt to the trend.

Residential preference transitions of disaster victims: A case using three-wave panel data in Mashiki following the 2016 Kumamoto earthquake in Japan

The Japanese government supplies post-disaster public housing (PDPH) to victims who are unable to rebuild homes damaged by a disaster. The efficient supply of PDPH requires an accurate prediction of housing demand, based on survey results. However, non-negligible households often change their residential preferences from the initial survey, and these changes make the demand prediction difficult. This study aims to examine the transition of victims’ residential preferences in Mashiki, Japan, post the 2016 Kumamoto earthquake. The study utilizes a three-wave panel data analysis comprising two sets of household survey data and the applicant data for PDPH to investigate disaster victim behavior with greater accuracy and provide a predictive tool for disaster management. The results indicate that households that initially preferred “rebuilding/repairing their homes” or “relocating to another place,” had young householders, did not live in post-disaster temporary housing, and had a high annual income tended to cancel moving into PDPH. These results can be instrumental in predicting the transition of residential preferences in future disasters. This study can establish patterns that, in turn, would help local governments predict the demand of PDPH provided as a form of disaster relief.