Applications of the Fuzzy Neural Networks to Short term Load Forecasting

This paper presents a fuzzy neural network approach to short term load forecasting.It can predict the hourly loads for next day or next week with the fuzzy information.The practical examples have proved the efficiencies of the proposed approach.     

Load Forecasting Based on BP ANN for Economical Operation of Electric Boiler with Heat Reservoir Under Time-sharing price

Along with the generalization of DSM and time-sharing price system, the use of electric boiler with heat reservoir becomes more and more extensive. Load forecasting of heat supply system is an important base in the study of economical operation of electric boiler with heat reservoir under time-sharing price. The BP ANN modeling of the load forecasting for a 1200 kW electric boiler is discussed. The result of hourly heat load forecasting accords well with the real heat load.     

Improving cereal yield forecasts in Europe – The impact of weather extremes

The impact of extreme events (such as prolonged droughts, heat waves, cold shocks and frost) is poorly represented by most of the existing yield forecasting systems. Two new model-based approaches that account for the impact of extreme weather events on crop production are presented as a way to improve yield forecasts, both based on the Crop Growth Monitoring System (CGMS) of the European Commission. A first approach includes simple relations – consistent with the degree of complexity of the most generic crop simulators – to explicitly model the impact of these events on leaf development and yield formation. A second approach is a hybrid system which adds selected agro-climatic indicators (accounting for drought and cold/heat stress) to the previous one. The new proposed methods, together with the CGMS-standard approach and a system exclusively based on selected agro-climatic indicators, were evaluated in a comparative fashion for their forecasting reliability. The four systems were assessed for the main micro- and macro-thermal cereal crops grown in highly productive European countries. The workflow included the statistical post-processing of model outputs aggregated at national level with historical series (1995–2013) of official yields, followed by a cross-validation for forecasting events triggered at flowering, maturity and at an intermediate stage. With the system based on agro-climatic indicators, satisfactory performances were limited to microthermal crops grown in Mediterranean environments (i.e. crop production systems mainly driven by rainfall distribution). Compared to CGMS-standard system, the newly proposed approaches increased the forecasting reliability in 94% of the combinations crop × country × forecasting moment. In particular, the explicit simulation of the impact of extreme events explained a large part of the inter-annual variability (up to +44% for spring barley in Poland), while the addition of agro-climatic indicators to the workflow mostly added accuracy to an already satisfactory forecasting system.     

自适应加权最小二乘支持向量机的空调负荷预测

为了提高建筑空调负荷的预测精度,在分析空调负荷主要影响因素的基础上提出了一种基于自适应加权最小二乘支持向量机(AWLS-SVM)的建筑空调负荷预测方法。该方法根据预测误差的统计特性,采用基于改进正态分布加权规则,自适应地赋予每个建模样本不同的权值,以克服异常样本点对模型性能的影响。建模过程中采用粒子群优化(PSO)算法对模型参数进行优化,以进一步提高模型预测精度。基于DeST模拟数据将AWLS-SVM方法应用于南方地区某办公建筑的逐时空调负荷预测中,并与径向基神经网络(RBFNN)模型、LS-SVM模型及WLS-SVM模型作比较,其平均预测绝对误差分别降低了51.84 %、13.95 %和3.24 %,并进一步基于实际空调负荷数据将该方法应用于另一办公建筑的逐日空调负荷预测中。预测结果表明：AWLS-SVM预测的累积负荷误差为4.56 MW,亦优于其他3类模型,证明了AWLS-SVM具有较高的预测精度和较好的泛化能力,是建筑空调负荷预测的一种有效方法。     

The Genetic Algorithms Applied in the Combination Forecasting of Economic Chaos

Economic chaos is a random-like dynamic behavior resulting from definitive economic system . Although the time series from economic system isn't forecasted in a long term ,but can be predicted precisely in a short term , thus , by which a deterministic model can be constructed . To search chaos character in economic time series , we present a combined forecasting method of economic chaos basing on genetic algorithms and the reconstruction of phase space given by Wolf, this method takes advantage of genetic algorithms to determine the weighting coefficient of combined forecasting. It's greatly overcome the defaults that when traditional forecasting of economic chaos single model is mostly used so as to affect the forecasting precision. At last , an example is given to testify the validity and feasibility of this method.     

Combination of GPS monitoring and ANN prediction for slope deformation

Based on the evolution pattern of slope deformation and failure, stability status of a slope is evaluated through analyzing the data of GPS monitoring. A neural network model of slope displacement time is developed based on the GPS monitoring data. It can be used to forecast slope deformation trends. A neural network displacement prediction model of slope deformation is proposed with Matlab ANN toolbox. Upon a case study, the ANN prediction results based on GPS monitoring data are analyzed.     

用模糊神经网络提高洪峰预报精度的研究

在大量研究的基础上,提出了基于模糊理论的神经网络改进算法,用来提高对洪峰的预报精度。该方法在网络训练时引入模糊理论来确定网络误差修改的程度。引入的算法增大了大值输出样本和期望输出的误差,使得网络向着提高洪峰拟合精度的方向修改权重。应用表明,改进的模糊BP神经网络能够较好的反映洪水演进机理,提高了神经网络洪水预报模型对洪峰的预报精度,保证了洪峰预报的可靠性。     

大型商场建筑夏季冷负荷动态预测模型

夏季建筑冷负荷的正确预测是实现大型复杂中央空调优化运行、节能降耗的关键。笔者探讨了商场建筑冷负荷的主要影响因素,确定了建筑动态冷负荷预测模型的输入,提出了夏季基于新风机组供电频率的商场顾客率间接测量方法,解决了商场内顾客量难以检测的难题。还提出了AFC-HCMAC神经网络预测模型算法,实现了大型商场建筑冷负荷的动态预测。仿真结果表明:顾客率在商场冷负荷预测中占有重要地位,在冷负荷预测模型中增加商场顾客率可显著提高预测精度;AFC-HCMAC神经网络预测算法与传统的HCMAC神经网络算法比较,可有效降低神经网络节点数,提高预测精度。     

A Fuzzy Regression Method for Long-Term and Medium-Term Load Forecasting

In view of the observation data fuzziness and load pattern fuzziness,a new fuzzy regression prediction method was presented for long-term and medium-term load forecasting. With the established fuzzy regression model, the future load value can be forecasted based on the fuzzy historical observation data. The validity of the proposed method was verified with the numerical example of a practical system.     

Application of Combination Grey Model in Power Load Forecasting

Based on the gray forecast theory, this paper studies the principle and deficiency in power load forecasting by the basic grey model and other improved models, and introduces a new method -the combination grey model to forecast the long-medium power load. Based on an example, the basic grey model, other improved models and combination grey model are used to forecast power load and results of all models are analyzed and compared. The calculation results show that forecasting power load by grey theory is credible and simple. For this type of complex problems such as forecasting the long-medium power load, the combination grey model is specially useful because of it's high precision and facility. The method can be used as one of the tools of forecasting the long-medium power load.     

Application of the CSM-CERES-Maize model for planting date evaluation and yield forecasting for maize grown off-season in a subtropical environment

In recent years, maize has become one of the main alternative crops for the Autumn–Winter growing season (off-season) in several regions of Brazil. Water deficits, sub-optimum temperatures and low solar radiation levels are some of the more common problems that are experienced during this growing season. However, the impact of variable weather conditions on crop production can be analyzed with crop simulation models. The objectives of this study were to evaluate the Cropping System Model (CSM)-CERES-Maize for its ability to simulate growth, development, grain yield for four different maturity maize hybrids grown off-season in a subtropical region of Brazil, to study the impact of different planting dates on maize performance under rainfed and irrigated conditions, and for yield forecasting for the most common off-season production system. The CSM-CERES-Maize model was evaluated with experimental data collected during three field experiments conducted in Piracicaba, SP, Brazil. The experiments were completely randomized with three replications for the 2001 experiment and four replications for the 2002 experiments. For the yield forecasting application, daily weather data for 2002 were used until the forecast date, complemented with 25 years of historical daily weather data for the remainder of the growing season. Six planting dates were simulated, starting on February 1 and repeated every 15 days until April 15. The evaluation of the CSM-CERES-Maize showed that the model was able to simulate phenology and grain yield for the four hybrids accurately, with normalized RMSE (expressed in percentage) less than 15%. The planting date analysis showed that a delayed planting date from February 1 to April 15 caused a decrease in average yield of 55% for the rainfed and 21% for the irrigated conditions for all hybrids. The yield forecasting analysis demonstrated that an accurate yield forecast could be provided at approximately 45 days prior to the harvest date for all four maize hybrids. These results are promising for farmers and decision makers, as they could have access to accurate yield forecasts prior to final harvest. However, to be able to make practical decisions for stock management of maize grains, it is necessary to develop this methodology for different locations. Future model evaluations might also be needed due to the release of new cultivars by breeders.     

沈阳2次降水过程ANC和TRACER检验分析

随着大城市的不断发展和社会对于气象精细化要求的提高,临近预报特别是突发性灾害天气的临近预报已经成为了社会关注的重点。为了提升短临预报能力,沈阳市气象局先后引进了ANC和TRACER系统,但是由于使用时间较短,之前还没有总结出对于2个系统预报产品的订正技术。本研究通过2013年10月10日与2014年8月24日沈阳2次大雨到暴雨天气过程,总结出ANC和TRACER在短临预报中的不同,ANC的优势更侧重于局地性的强对流天气的预报,而TRACER更有利于相对大范围的、连续性的降水预报。希望研究结果能够给预报员利用ANC和TRACER制作沈阳地区精细化预报预提供订正方法和依据。     

Application of the CSM-CERES-Maize model for planting date evaluation and yield forecasting for maize grown off-season in a subtropical environment

In recent years, maize has become one of the main alternative crops for the Autumn–Winter growing season (off-season) in several regions of Brazil. Water deficits, sub-optimum temperatures and low solar radiation levels are some of the more common problems that are experienced during this growing season. However, the impact of variable weather conditions on crop production can be analyzed with crop simulation models. The objectives of this study were to evaluate the Cropping System Model (CSM)-CERES-Maize for its ability to simulate growth, development, grain yield for four different maturity maize hybrids grown off-season in a subtropical region of Brazil, to study the impact of different planting dates on maize performance under rainfed and irrigated conditions, and for yield forecasting for the most common off-season production system. The CSM-CERES-Maize model was evaluated with experimental data collected during three field experiments conducted in Piracicaba, SP, Brazil. The experiments were completely randomized with three replications for the 2001 experiment and four replications for the 2002 experiments. For the yield forecasting application, daily weather data for 2002 were used until the forecast date, complemented with 25 years of historical daily weather data for the remainder of the growing season. Six planting dates were simulated, starting on February 1 and repeated every 15 days until April 15. The evaluation of the CSM-CERES-Maize showed that the model was able to simulate phenology and grain yield for the four hybrids accurately, with normalized RMSE (expressed in percentage) less than 15%. The planting date analysis showed that a delayed planting date from February 1 to April 15 caused a decrease in average yield of 55% for the rainfed and 21% for the irrigated conditions for all hybrids. The yield forecasting analysis demonstrated that an accurate yield forecast could be provided at approximately 45 days prior to the harvest date for all four maize hybrids. These results are promising for farmers and decision makers, as they could have access to accurate yield forecasts prior to final harvest. However, to be able to make practical decisions for stock management of maize grains, it is necessary to develop this methodology for different locations. Future model evaluations might also be needed due to the release of new cultivars by breeders.     

Application of data mining method in power load bad data intelligent identification and correction

There is a number of bad data in the load database produced, thus the data must be cleaned before it is used to forecasting electric load or performing power system analysis. The WKFCM measures distance by kernel functions instead of the complicated Euclidean distance and this kernel based distance is used as dissimilarity function of target clustering formula which can reduce the calculation complexity. After the clustering, a super circle covering neural network based identification model for load data is proposed, and the bad data is modified. It is proved that the proposed data processing model has good effect.     

Cause and Consequence in Maize Planting Dates in Germany

An important part of agricultural adaptation is the timing of crop sowing dates, affecting yields and the level of risk incurred during a particular season. Cold stress is especially relevant in maize, Zea mays L., so that the timing of planting in the spring is a tactical response to short‐term weather, but is also subject to strategic planning with regard to longer‐term climate. Both factors compare the potential implications of cold stress to the additional yield obtainable through earlier planting. New cultivars suited to growing conditions in Europe and generally increasing spring temperatures have enabled earlier planting, but it is still dependent on short‐term weather during the planting period. In the context of field‐level decision‐making, a panel regression is used to estimate the relationship between weekly local temperature and precipitation and planting dates at specific sites throughout Germany. Next, localised weather data and planting behaviour are linked to yields at the district (Landkreis) level to show the effects of planting date on yield. Based on these relationships optimal planting dates are explored with some associated costs and benefits. Results show a trend towards earlier planting that follows observed increasing spring temperatures and the availability of more cold‐tolerant cultivars but this advance is buffered by the increasing severity of minimum temperatures during a critical period. Earlier planting potentially increases yield but this is offset by additional management costs and risk. A robust and simple depiction of farmer behaviour in climatic, technological and economic context can help to understand trends in crop management and productivity that effect agricultural landscapes.     

冬季彩条布覆盖棚香梨树体气温特征分析

为了揭示冬季香梨园彩条布覆盖棚内外树体温度的变化特征,在2014～2015年库尔勒市上户镇原种场果园进行气温观测试验,对2015年1月7日～3月8日不同天气类型下彩条布覆盖棚内外树体气温进行分析。结果表明：⑴彩条布覆盖棚内平均气温、逐时气温高于棚外,棚内外气温总体变化趋势一致,不同天气类型下棚内外白天气温变化速度总体表现为：晴天＞多云＞阴天,夜间各天气类型气温变化均较平稳。⑵棚内树体阳面与阴面平均气温差逐渐较大,夜间树体阳面与阴面的逐时气温几乎相似,不同天气类型下棚内树体阳面逐时气温较阴面变化幅度大。⑶不同天气类型下棚外树体阳面最低气温均出现在9:00,阴面滞后1 h,晴天树体阳面最高气温出现在16:00,多云、阴天滞后1 h,阴面滞后2 h。     

Intelligent Extracting Method for Feature Mode of Electric Days Load

Generally there have a number of bad data in the electric load data and it affects the precision of load forecasting,so it is necessary for extracting the feature mode of days load data,then cleaning the load data before it is used to forecasting electric load or performing power system analysis.Inspired by soft clustering thought,a intelligent feature mode of days load data extracting method is proposed based on the mutual offset of fuzzy c-means clustering arithmetic and Kohonen self organization feature map neural network.With the merits of not only high extracting precision and convergent speed but also dynamic calculation capability,the method proposed can supply load forecasting or system analysis procedure with due data.Test results using actual data of Chengqu power supply bureau in Chongqing demonstrate the effectivity and feasibility of the method.     

Maquiladora Employment Dynamics in Nuevo Laredo

ABSTRACT The Nuevo Laredo maquiladora sector has grown enormously during the last two decades. The short‐term time series characteristics of this portion of the regional economy are analyzed in an attempt to quantify the trends underlying this remarkable performance. Parameter estimation is accomplished via linear transfer function (LTF) analysis. Data are drawn from the January 1990–December 2000 sample period. Empirical results indicate that real wage rates, maquiladora plants, U.S. industrial activity, and the real exchange rate of the peso play significant roles in determining month‐to‐month fluctuations in maquiladora employment. Furthermore, sub‐sample forecast simulation exercises are conducted as an additional means for verifying model reliability. Empirical results indicate that the forecasts generated with the LTF model are less accurate than those associated with a simple random walk procedure for twelve separate step‐length periods.     

雷暴大风、冰雹天气的预报方法研究

为了最大限度地减轻雷暴大风、冰雹天气造成的损失,提高这2种灾害性天气的预报预警能力,笔者在统计安徽省2000-2005年4-9月无雷暴、普通雷暴、强对流（雷暴大风、冰雹）样本的基础上,利用1×1格点NCEP资料计算了表征热力、动力、水汽条件的43个参数,对比分析了无雷暴、普通雷暴、强对流（雷暴大风、冰雹）时的物理量极值、归一化平均值等,并基于分析结果选取雷暴大风、冰雹的消空、预报指标,逐月逐时次的确定预报指标的阈值。最后,利用指标叠套法生成安徽省雷暴大风、冰雹天气潜势预报产品。用该方法对2007年的实时运行情况进行检验,2007年6-9月共有28个雷暴大风、冰雹过程,全部报出,空报9个过程,无漏报,过程TS为30.4%。从检验效果来看,指标叠加的数值越大,出现雷暴大风或冰雹的概率也就越大,对农业防灾减灾起到一定积极的作用。     

Fast Algorithm About Unit Commitment Based on Revised BP Artificial Neural Network and Dynamic Search

In order to reduce the operation cost and optimize the unit commitment,the fast algorithm about unit commitment based on revised BP ANN(Artificial Neural Network) and dynamic search is discussed.The BP ANN is trained with Levenberg-Marquardt algorithm,which aiming at its drawback of the storage of some matrices that can be quite large for certain problems,and a revised algorithm is presented.The BP ANN is used to generate a pre-schedule according to the input load profile.Then the dynamic search is performed some stages where the commitment states of some of the units are not certain.The experimental results indicate that the proposed algorithm can reduce the execution time and memory space without degrading the quality of the generation schedule.