Assessment of predictive uncertainty within the framework of water demand forecasting using the Model Conditional Processor (MCP)

This paper presents an application of the Model Conditional Processor (MCP), originally proposed by Todini (2008) within the hydrological framework, to assess the predictive uncertainty in water demand forecasting related to water distribution systems. The MCP enables us to assess the probability distribution of the future water demand conditional on the forecasts provided by two or more deterministic forecasting models. In the numerical application described here, where two years of hourly water demand data for a town in northern Italy are considered, two forecasting models are applied in order to forecast hourly water demands from 1 to 24 hours ahead: the first model has a modular structure comprising a periodic component which reflects the long-term effects and a persistence component which represents the short-term memory of the process; the latter is based on neural networks. The results highlight the effectiveness of the approach, provided that the data set used for the MCP parameterization is properly selected so as to be actually representative of the accuracy of the real-time water demand forecasting models.     

Large metropolitan water demand forecasting using DAN2, FTDNN,and KNN models: A case study of the city of Tehran,Iran

Efficient operation of urban water systems necessitates accurate water demand forecasting. We present daily, weekly, and monthly water demand forecasting using dynamic artificial neural network (DAN2), focused time-delay neural network (FTDNN), and K-nearest neighbor (KNN) models for the city of Tehran. The daily model investigates whether partitioning weekdays into weekends and non-weekends can improve forecast results; it did not. The weekly model yielded good results by using the summation of the daily forecast values into their corresponding weeks. The monthly results showed that partitioning the year into high and low seasons can improve forecast accuracy. All three models offer very good results for water demand forecasting. DAN2, the best model, yielded forecasting accuracies of 96%, 99%, and 98%, for daily, weekly, and monthly models respectively.     

Domestic Water Demand Forecasting: A Static Microsimulation Approach

Planning the provision of a future water supply depends upon forecasts of likely demand. Existing forecasting techniques suffer from a lack of spatially relevant information on likely trends in the micro-components of demand. At a sub-regional level, current approaches also understate between-area variability. A static micro-simulation model is described, which makes more efficient use of existing data in producing forecasts of domestic water consumption. Spatially detailed synthetic microdata are reweighted towards level population estimates which are derived from official Government population projections. A 30% increase in domestic consumption between 1991 and 2025 is forecast for the Yorkshire Water region, three-quarters of which is attributable to changes in consumer behaviour.     

Using extreme learning machines for short-term urban water demand forecasting

This study explores the ability of various machine learning methods to improve the accuracy of urban water demand forecasting for the city of Montreal (Canada). Artificial Neural Network (ANN), Support Vector Regression (SVR) and Extreme Learning Machine (ELM) models, in addition to a traditional model (Multiple linear regression, MLR) were developed to forecast urban water demand at lead times of 1 and 3 days. The use of models based on ELM in water demand forecasting has not previously been explored in much detail. Models were based on different combinations of the main input variables (e.g., daily maximum temperature, daily total precipitation and daily water demand), for which data were available for Montreal, Canada between 1999 and 2010. Based on the squared coefficient of determination, the root mean square error and an examination of the residuals, ELM models provided greater accuracy than MLR, ANN or SVR models in forecasting Montreal urban water demand for 1 day and 3 days ahead, and can be considered a promising method for short-term urban water demand forecasting.     

Forecasting the sales of precast concrete building products

Sales of precast concrete building products are influenced by the general demand for construction. This demand is subject to substantial fluctuations, caused by such diverse factors as capital spending by Government, the general strength of the economy, the demand for housing — which in turn reflects mortgage interest rates -and also by seasonal factors and weather. These are some of the difficulties associated with sales forecasting in the precast concrete industry. Sales forecasting is crucial managerial practice and its accuracy is vital for any company's business survival. A survey of the current forecasting and planning practices in the industry concluded that forecasting, especially for major product groups, is fairly basic and not reliable. Against this background, a forecasting model has been developed to analyse historical data and forecast demand for 12 months ahead. Two forecasting methods were applied to historical data of 12 groups of products of a major manufacturer. The results of the forecasting model were encouraging and more accurate than the manufacturer's existing forecasting system. The authors interviewed the firm's marketing and sales staff to identify the advantages and disadvantages of the forecasting system and identify the factors which affect sales and forecasting in general. Some tangible indication of the practical use of this work is the support given to this research project by staff of this company, at all levels. The work described in this paper is part of a more general computerized capacity planning system for the precast industry. This would be suitable for major companies, most of whom produce a large number of different products in a number of different manufacturing plants dispersed throughout the UK.     

改进单指数平滑法预测某市日用水量

为实现供水管网经济、可靠、科学的优化调配用水量,给出一种基于改进单指数平滑预测方法,该预测方法引进"追踪信号"来反应时间序列的变化,通过重新修正平滑常数a以建立改进单指数预测模型。以东北某城市日用水量为原始数据进行了实际预测,模型精度检验的结果满足Y市用水量要求,该预测模型应用于Y市的日用水量预测,为Y市供水优化调配提供有效依据。     

Forecasting short-term electricity load using hybrid support vector regression with grey catastrophe and random forest modeling

This paper develops a novel short-term load forecasting model that hybridizes several machine learning methods, such as support vector regression (SVR), grey catastrophe (GC (1,1)), and random forest (RF) modeling. The modeling process is based on the minimization of both SVR and risk. GC is used to process and extract catastrophe points in the long term to reduce randomness. RF is used to optimize forecasting performance by exploiting its superior optimization capability. The proposed SVR-GC-RF model has higher forecasting accuracy (MAPE values are 6.35% and 6.21%, respectively) using electric loads from Australian-Energy-Market-Operator; it can provide analytical support to forecast electricity consumption accurately.     

地区间货物运输量预测方法谱系

本文整理了近些年地区间(城市间)货物运输量预测方法的研究。论文分析了和旅客运输相比,地区间货物运输的特点,提出了货物运输需求量的预测在理论和方法上和客流需求量的预测有所不同的依据。将以往的地区间货运量预测模型按不同阶段做了分类整理。其次,根据物流的行为者将地区间货运量预测模型分为计量经济学模型、空间相互作用模型及网络模型等类型。较为详尽地分析了各类预测模型的特点。并结合我国物流业的发展现状,对货物运输量预测方法研究的发展方向进行了展望。     

Forecasting construction demand: a vector error correction model with dummy variables

Modelling the level of demand for construction is vital in policy formulation and implementation as the construction industry plays an important role in a country’s economic development process. In construction economics, research efforts on construction demand modelling and forecasting are various, but few researchers have considered the impact of global economy events in construction demand modelling. An advanced multivariate modelling technique, namely the vector error correction (VEC) model with dummy variables, was adopted to predict demand in the Australian construction market. The results of prediction accuracy tests suggest that the general VEC model and the VEC model with dummy variables are both acceptable for forecasting construction economic indicators. However, the VEC model that considers external impacts achieves higher prediction accuracy than the general VEC model. The model estimates indicate that the growth in population, changes in national income, fluctuations in interest rates and changes in householder expenditure all play significant roles when explaining variations in construction demand. The VEC model with disturbances developed can serve as an experimentation using an advanced econometrical method which can be used to analyse the effect of specific events or factors on the construction market growth.     

重庆市主城区停车位需求预测分析

该文通过介绍停车需求预测模型,从而选定预测重庆主城区停车需求的方法,并收集和整理相关资料,确定基础参数,最后根据模型公式推导出最终的预测结果。     

基于关联耦合法探讨城市地下空间需求模型

地下空间开发已成为中国发达地区向心式城市化的重要途径,对地下空间的需求评估为地下空间科学高效的开发提供了保障。目前地下空间需求评估常采用专家打分法、层次分析法等方法,但不能反映开发规模。本文以福州市中心城区为例,借助Arcgis建立城市地下空间需求模型。模型分为需求预测与相关规划校正两个步骤,其中需求预测运用关联耦合法,对地下空间需求较大的城市用地的地上建设量进行预测,通过停车、民防与商业三个主要功能的地上地下协调系数,推算其地下空间建设量。最后通过相关规划进行校正。与传统预测方法相比,此方法能结合地下空间的整体预测与专项规划,创建地下空间需求量数据库,为现有的需求评估方法提供重要的补充。     

基于等维灰数递补动态GM（1，1）模型的矿区需水量预测研究

在研究煤矿区中长期需水量预测过程中,针对常规GM（1,1）模型存在的不足,选用等维灰数递补动态GM（1,1）模型来进行矿区需水量预测,运用此模型对神东矿区自来水需水量进行了拟合和预测,结果表明此模型拟合精度高,适合于矿区中长期需水量预测使用,可为矿区水资源的开发利用规划和可持续利用提供必要的参考。     

我国城镇化对商品住房需求的拉动效应研究

为探究城镇化对我国商品住房市场的拉动效应,从3 个方面定性分析了城镇化对房地产市场的影响,采用协整分析方法,建立商品住房需求的拉动效应模型并进行模型检验,考虑到模型内部的短期动态波动,构建了误差修正模型,利用格兰杰因果检验探究了两者的因果关系。通过对1992~2012 年间的城镇化水平与商品住宅需求的实证研究,发现我国城镇化水平对商品住宅需求存在一种长期稳定的拉动效应,即城镇化水平每提高1%,会拉动商品住房长期增长3.22%;城镇化水平是商品住宅需求的格兰杰原因;并且这种均衡关系由短期偏离向长期均衡调整的速度较慢。     

城市轨道交通规划线网生成模型研究

建立城市轨道交通线网规划阶段的线网定量化生成数学模型,模型在考虑提高轨道交通客流分担竞争力的基础上,以线网平均负荷强度最大为目标,以线网拓扑关系、节点和区间重复度、线路条件、客流平衡、换乘条件、线网规模、舒适度水平为约束;提出以城市主要客流走廊和客流集散点为基础的确定线网搜索范围和搜索方向的策略,合理把握线路的走向边界;由于该问题属于NP-Hard问题,对于大型网络搜索空间大,难以求解,文章基于模拟退火框架设计邻域搜索算法求解方法。以X市为例,计算得到该市轨道交通远期规划线网各线路走向,通过与X市既有规划线网的对比分析,可以看出,基于本模型生成的规划线网,在满足主客流走廊和城市发展主轴方向的客流需求下,具有规模小、线网利用率高的特点,从而验证模型与算法的有效性。     

Developing a production management modelling approach for precast concrete building products

Production management in this research is concerned with three key decisions: demand forecast, production scheduling and stock forecast. These three decisions are very much interrelated and cannot be made in isolation. Previous studies of precast concrete industry activities concluded that production management is fragmented. For example, production planning is done in isolation from demand forecasting and from stock forecasting. This has contributed to poor production management performance in terms of resource utilization and over-stocking. This paper goes beyond traditional production management theories and practices and develops a model to integrate all aspects of production management. The main objective is to develop an integrated production management model for the make-to-stock sector of precast concrete building products, in order to help production managers make better planning decisions and explore alternative options. The model is a factory simulator which examines and evaluates the effect of several managerial strategies on production planning and stock forecasting before actual production commences. It uses different measures of performance which facilitate the choice of planning strategies under various demands and factory conditions.     

Application of a new hybrid forecast engine with feature selection algorithm in a power system

To operate a power system effectively, an accurate prediction model is demanded. So, short-term load forecast is one of the major discussions in deregulated power markets. This prediction model needs a strong and accurate method to tackle the complexity, non-stationary and volatility of this signal. Hence, a new hybrid forecasting model is proposed in this paper, to solve the load forecast requirement. The proposed structure consists of a three-stage Neural Network-based forecast engine with different learning algorithms. Also, the input signal of this forecast engine is filtered by a new feature selection model to find the high relevancy and low redundancy of features. The proposed strategy is implemented and tested on real-world engineering data through a comparison with other techniques. The numerical results obtained demonstrate the validity of the proposed method.     

深厚表土层地区混凝土井壁变形监测及灰色模型预测

基于深厚表土层地区混凝土井壁破裂变形预测及井壁破裂预防性信息化施工的需要,介绍混凝土井壁变形自动监测的原理、方法及监测特点,基于实测监测信息,建立某井壁混凝土变形预测非等间隔灰色预测模型,实测与预测结果表明该模型可用于混凝土井壁变形超前预测.     

The market size of a city-pair route at an airport

A model is developed for estimating the size of the market for a city-pair route at an airport from both the demand and supply sides of air transportation. The average airport access cost, average passenger delay cost, and average airline operating cost all either increase or decrease with an increase in the market size of a city-pair route at an airport, so the optimum market size can be determined from trade-offs among these costs. A nonlinear mathematical programming problem is formulated to determine the optimal number of passengers, the local service area of a city-pair market and to perform sensitivity analyses. The results show that long-haul services ought to be concentrated in one large airport, while short-haul services might be dispersed among many small airports. Improvements in the technology of the airport access mode or increases in the average income of the cities served can expand the market size and service area, but at a declining expansion rate. In metropolitan areas with high population density, airlines can operate more efficiently and distribute air services among more airports. City-pair markets with stable passenger demand, or markets served by airlines with efficient scheduling technology are shown to exhibit high cost efficiencies.     

基于VAR和VEC模型的广东省建筑行业人才分析与预测

在人力资源对新一轮经济发展仍起到重要作用的背景下,建筑行业要想实现良性发展,就必须重视人力资源的把握。通过Johansen协整检验、Granger因果检验和误差修正(VEC)模型分析,探讨了建筑业增加值与人力资源数量的长短期关系。研究表明:建筑行业发展与人力资源数量之间存在长期均衡关系;建筑业的发展对人力资源数量的增长起到了积极的作用;当建筑业增加值增长1%时,人力资源数量将增加0.1481%。分别通过线性回归模型法和比率分析法对未来10年内建筑业专门人才的数量进行了预测,并针对人才缺口不断扩大的问题提出了发展策略。     

Characterization and performance evaluation of a full-scale activated carbon-based dynamic botanical air filtration system for improving indoor air quality

A dynamic botanical air filtration system (DBAF) was developed for evaluating the short and long-term performance of botanical air cleaning technology under realistic indoor conditions. It was a fan-assisted with controlled airflow, activated-carbon/hydroculture based potted plant unit. The DBAF was first tested using a full-scale stainless chamber to evaluate its short-term performance. It was then integrated in the HVAC system of a new office space (96.8 m²) to study the effects of moisture content in the root bed on the removal efficiency, and the long-term performance. The results indicated that 5% outdoor air plus botanical filtration lead to the similar indoor formaldehyde/toluene concentration level as 25% outdoor air without filtration, which means that the filtration system was equivalent to 20% outdoor air (476 m³/h). The DBAF was effective for removing both formaldehyde and toluene under 5–32% volumetric water content of the root bed. It also performed consistently well over the relatively long testing period of 300 days while running continuously. The reduction in outdoor ventilation rate while using the botanical filtration system to maintain acceptable air quality would lead to 10–15% energy saving for the cold climate (Syracuse, NY), based on simulation analysis using EnergyPlus. For winter condition, the filter was also found to increase the supply air RH by 20%, which would decrease the dryness of air. For summer condition, the increase of RH in summer would be within 15% of the RH condition when no botanical air filtration is present.