Electricity price forecasting using generalized regression neural network based on principal components analysis

A combined model based on principal components analysis (PCA) and generalized regression neural network (GRNN) was adopted to forecast electricity price in day-ahead electricity market. PCA was applied to mine the main influence on day-ahead price, avoiding the strong correlation between the input factors that might influence electricity price, such as the load of the forecasting hour, other history loads and prices, weather and temperature; then GRNN was employed to forecast electricity price according to the main information extracted by PCA. To prove the efficiency of the combined model, a case from PJM (Pennsylvania-New Jersey-Maryland) day-ahead electricity market was evaluated. Compared to back-propagation (BP) neural network and standard GRNN, the combined method reduces the mean absolute percentage error about 3%.

Material Design and Experimental Analysis of a New Type of Semiconductor ER Fluids

To improve the electrorheological effect of electrorheological fluid (ERF), a new type of the electrosensitive particle material, polynaphthalene quinone was prepared, whose molecules contain blended atoms of nitrogen, oxygen, sulphur and big π bond conjugate system. In both DC and AC electric fields, the ERF material showed a distinct ER effect. Especially, in the alternating electric field, the shear stress of this material versus AC voltage has a better quadratic relation than that of the other materials. The experimental data showed that organic semiconductor polymers with big π bond conjugate system are a new type of electrosensitive particle materials which are worth well developing.

Prediction of Soil Salinity Using Remote Sensing Tools and Linear Regression Model

Soil salinity is one of the most damaging environmental problems worldwide, especially in arid and semi-arid regions. Multispectral data Sentinel_2 are used to study saline soils in southern Tunisia. 34 soil samples were collected for ground truth data in the investigated region. A moderate correlation was found between electrical conductivity and the spectral indices from SWIR. Different spectral indices were used from original bands of Sentinel_2 data. Statistical correlation between ground measurements of Electrical Conductivity (EC), spectral indices and Sentinel_2 original bands showed that SWIR bands (b11 and b12) and the salinity index SI have the highest correlation with EC. Based on these results and combining these remotely sensed variables into a regression analysis model yielded a coefficient of determination R2 = 0.48 and an RMSE = 4.8 dS/m.

Analysis of China's Electricity Price and Electricity Burden of Basic Industries under the Carbon Peak Target before 2030

The Chinese government is deepening reformation of electricity prices during the 14th Five Year Plan period and has set a carbon emission reduction target of reaching carbon peak before 2030.In this context,will the carbon emission target influence electricity pricing and will electricity price influence competitiveness of Chinese main industries are two questions needing to be answered.This paper compares China's electricity price level with the selected major countries in the world,and four typical industries are selected to evaluate their electricity burden respectively.Then,the correlation between residential electricity price and industrial electricity price and the influencing factors is analyzed,from the perspectives of scale,structure and technology.According to the model obtained by regression analysis,the electricity price level and corresponding residential and industrial electricity burden in 2025 and 2030 are forecasted.Index Terms-Electricity burden,industrial electricity price,regression analysis,residential electricity price.

Electrical conductivity optimization of the Na3AlF6–Al2O3–Sm2O3 molten salts system for Al–Sm intermediate binary alloy production

Metal Sm has been widely used in making Al–Sm magnet alloy materials. Conventional distillation technology to produce Sm has the disadvantages of low productivity, high costs, and pollution generation. The objective of this study was to develop a molten salt electrolyte system to produce Al–Sm alloy directly, with focus on the electrical conductivity and optimal operating conditions to minimize the energy consumption. The continuously varying cell constant(CVCC) technique was used to measure the conductivity for the Na3AlF6–AlF3–LiF–MgF2–Al2O3–Sm2O3electrolysis medium in the temperature range from 905 to 1055°C. The temperature(t) and the addition of Al2O3(W(Al2O3)), Sm2O3(W(Sm2O3)), and a combination of Al2O3and Sm2O3into the basic fluoride system were examined with respect to their effects on the conductivity(κ) and activation energy. The experimental results showed that the molten electrolyte conductivity increases with increasing temperature(t) and decreases with the addition of Al2O3or Sm2O3or both. We concluded that the optimal operation conditions for Al–Sm intermediate alloy production in the Na3AlF6–AlF3–LiF–MgF2–Al2O3–Sm2O3system are W(Al2O3) + W(Sm2O3) = 3wt%, W(Al2O3):W(Sm2O3) = 7:3, and a temperature of 965 to 995°C, which results in satisfactory conductivity, low fluoride evaporation losses, and low energy consumption.

电场处理对卷荚相思种子萌发特性的影响

【目的】分析不同电场、时间及两者交互处理对卷荚相思种子萌发特性的影响,为卷荚相思种子萌发及可持续经营提供理论参考。【方法】以卷荚相思种子为研究对象,采用室内模拟试验,以不同电场强度和处理时间为控制因素,电压强度为0.0、0.2、0.4、0.6、0.8、1.0 kV·cm^(-1),时间处理为0、15、30、45、60 min,研究不同电场强度和时间交互处理对其种子萌发特性的影响。【结果】随着电场强度增强,处理时间的延长,卷荚相思种子的发芽率、发芽势和发芽指数均呈现不同程度的变化趋势。其中,在处理时间15、30、60 min下发芽率随着电场强度的增强呈现先降后升再降的趋势,但在处理时间45 min下发芽率随着电场强度的增强呈现先升后降的趋势;而发芽势和发芽指数均在电场强度0.6~0.8 kV·cm^(-1)和处理时间45 min下处于最优状态,且与CK相比具有显著差异(P<0.05)。经过多元非线性回归分析得出,不同电场强度与时间交互处理下的最优回归方程为:Y=7.73+135.23X_(1)+1.24X_(2)-86.16X_(1)^(2)-0.00911X_(2)^(2)-0.75X_(1)X_(2)(R^(2)=0.81,P<0.05)。聚类分析结果电场和时间交互环境处理对发芽指数有非常显著的影响。【结论】电场和时间两者交互处理对卷荚相思种子萌发特性具有一定的影响,发芽率在0.6 kV·cm^(-1)处理45 min最高,说明适宜电场强度和处理时间可以提高卷荚相思种子发芽率。

基于分类-关联-修正的电力需求预测方法研究

电力需求的波动性较大,导致难以预测。针对区域电网宏观电力需求预测,提出了一种基于分类-关联-修正的电力需求预测方法。利用灰色关联分析方法筛选出关键的产业用电,以及影响各产业用电程度较大的因素。在传统回归预测方法的基础上,结合灰色预测方法对电力需求的影响因素进行预测,建立电力需求回归预测模型。以产业电量占全社会电量的比值对模型预测值进行修正,从而提高预测精度。相比于整体预测方法,该方法分产业开展关键影响因素识别与电力需求预测,并进行宏观修正。基于河南省2011—2022年的电力数据,验证该方法可准确预测未来电力需求的发展趋势,可为区域电网的长期预警提供参考依据。

基于混合回归模型的电炉生产企业经济产业结构影响因素多变量分析

分析经济产业结构影响因素对扩大电炉企业生产规模、重构电炉生产经济产业结构有着十分重要的现实意义,因此基于混合回归模型,分析了电炉生产企业经济产业结构影响因素。分析电炉生产规模现状,根据现阶段电炉国际贸易格局,选择四项指标构建混合回归模型。将我国电炉进口规模、电炉交通运输能力、电炉生产技术创新和环境规制作为自变量,电炉生产规模作为因变量带入混合回归模型中,实现电炉生产企业经济产业结构影响因素的深入分析。分析结果表明,我国电炉进口规模与电炉生产存在负相关联系,电炉交通运输能力、电炉生产技术创新和环境规制强度与电炉生产存在正相关联系。根据分析结果,可以优化经济产业结构,扩大生产规模,推动电炉生产发展。

Data-driven sensitivity analysis and electricity consumption prediction for water source heat pump system using limited information

The studies on predicting the energy consumption of air conditioning systems are meaningful to building energy conservation and management. Generally, the more comprehensive the building information is, the easier the prediction model can be developed. However, it is very difficult to get detailed information about existing/old buildings (information-poor buildings), it is a big challenge to predict the energy consumption accurately by limited information. This study aims to predict the electricity consumption of the water source heat pump system of an office building based on meteorological data. The key variables are selected by error analysis and sensitivity analysis, and the effects of each variable on the models’ prediction performance can be obtained. Besides, the prediction models are established by support vector regression algorithm and trained by the local meteorological data. The results show that the positive and negative variables can be identified, and these positive variables are responsible for more than 70% of the total importance. Moreover, the root mean square error falls to 4.6044 from 7.8227 and the relative square error falls to 0.1494 from 0.4313 when the negative inputs are removed. And the errors reduce further to 4.1160 and 0.1194 by parameter optimization.

电碳材料燃烧排放对大气颗粒物浓度的影响研究

电碳材料燃烧排放产生的颗粒物在大气中传输和扩散受到风场和大气条件的影响,其中包括风速、温度和湿度的变化和不确定性,预测电碳材料燃烧排放的分布变得困难。因此,研究电碳材料燃烧排放对大气颗粒物浓度的影响。使用大气监测仪器收集数据,并建立高斯烟羽模型,模拟电碳材料燃烧排放颗粒物在大气中的沉积与扩散情况。将辽宁省某火电厂作为监测区域,采用线性回归分析方法分析并验证了电碳燃烧排放颗粒物浓度与气象因子之间的关系。通过不同方法对比说明:所提方法分析出的电碳材料燃烧排放对大气颗粒物浓度的影响更符合实际情况。

Analysis of the time-domain spectrum of hydrogen in electric field near helium surface

The Ryderberg electronic wave packet dynamics of hydrogen atom near helium surface in an electric field is investigated using the semiclassical method. The autocorrelation function is calculated when the photoionized electron is excited by a short laser pulse for different atom-surface separations. The results show that new recurrences appear because of the helium surface, and the number of recurrent peaks increases with the decrease in atom-surface distance. The new feature is ascribed to the bifurcation of new closed orbits in the classical dynamics of the photoionized electron. Therefore, surface properties have a significant effect on the spectrum of nearby atoms or ions.

基于主成分回归分析的纯电客车车内声品质评价模型构建

以11款纯电动客车车内噪声样本为研究对象,利用主成分分析方法对样本的客观参数进行降维处理,以降维后的主成分为自变量,以主观评价打分结果为因变量,构建多元线性回归预测模型。结果表明,该模型平均相对误差为4.6%,预测结果可靠。

煤电基地CO_(2)和CH_(4)遥感监测及时空特征分析

【目的】CO_(2)和CH_(4)是煤电基地能源生产活动中的主要温室气体排放种类,其监测与时空分布是研究区碳监测体系建设的重要内容。【方法】以安徽淮南市为例,利用GOSAT、OCO-2和Sentinel-5P这3种卫星数据进行研究区CO_(2)和CH_(4)浓度监测,得到CO_(2)、CH_(4)柱浓度(XCO_(2)和XCH_(4))变化和分布情况,采用源清单法分析CO_(2)行业和区域排放特征,同时采用Pearson相关系数和多元回归方法分析影响研究区XCO_(2)和XCH_(4)浓度的主控因素。【结果和结论】结果表明:(1)基于GOSAT和OCO-2卫星融合数据分析显示,淮南市2016-2020年XCO_(2)和XCH_(4)浓度整体呈增长趋势,期间XCO_(2)浓度增加12×10^(-6)、XCH_(4)浓度增加23×10^(-9);XCO_(2)浓度和累计发电量的Pearson相关系数为0.98,XCH_(4)浓度和累计煤炭产量的Pearson相关系数为0.99,均呈极强相关。(2)利用Sentinel-5P卫星搭载的对流层观测仪(TROPOMI)高分辨产品数据分析淮南市各区域XCH_(4)浓度分布时空特征发现,研究区秋季XCH_(4)浓度高于夏季,XCH_(4)浓度受能源生产和农业生产两方面的影响。(3)源清单法得出淮南市一级源分类CO_(2)排放最多的为化石燃料固定燃烧源,占全市CO_(2)总排放量的89.59%,化石燃料固定燃烧源中电力供热占比99%以上;主要为淮南市潘集区和凤台县燃煤电厂CO_(2)排放;源识别显示集中分布在淮南市北部的火力发电厂为研究区CO_(2)最主要排放源。(4)影响研究区XCO_(2)浓度的主控因素为地区生产总值、累计发电量和第二产业产值,影响XCH_(4)浓度的主控因素为累计煤炭产量、第一产业产值、播种面积。研究结果对我国“双碳”目标下煤电基地碳监测体系构建与完善具有重要的参考意义。

基于主成分分析法的全社会用电量影响因素研究

为探究全社会用电量的影响因素,文章采用主成分分析法,搜集A省2005—2021年的全社会用电量及经济、城镇发展、工业、气象指标,将其分为两个主成分,再通过多元回归构建线性模型,根据回归处理得出各指标的影响程度。回归结果表明,A省全社会用电量与第一主成分显著相关,与第二主成分相关性不强,其中城镇化率和城镇居民人均住房面积对全社会用电量的影响最大。

基于支持向量机的电力系统短期负荷预测

对将径向基函数(Radial Base Function,RBF)作为核函数的支持向量机(Support Vector Machine,SVM)方法应用于短期负荷预测进行了研究。作者使用基于 SVM 的回归估计算法建立了回归估计函数表达式,给出了SVM 网络结构;采用江苏省某市的实际负荷数据,按照不同的负荷日属性和历史负荷数据进行样本选择,使用 LIBSVM 算法和适当的核函数进行了负荷预测,并将该预测结果同由时间序列及 BP 神经网络方法得到的预测结果进行了比较,结果表明,所提出的预测方法有较高的精度。

考虑市场力的短、中、长期电价预测

分别介绍了采用BP神经网络模型和线性回归模型进行电价预测的方法和结果。方法的突出特点是在预测模型中引入了一个衡量市场力的新指标———发电容量必须运行率 (MRR) ,从而充分考虑了市场力对电价的影响 ,提高了电价预测的精度 ,特别是增强了短期预测模型对最高限价的预测能力。文中对MRR指标进行了简单的介绍 ,并针对电价预测的不同特点 ,对预测模型和预测变量的选择进行了探讨 ,提出了自己的观点。基于浙江电力市场实际运营数据的初步预测结果表明 ,所建预测模型是适用的 ,选择的预测输入变量是恰当的 ,电价预测精度能够满足电力市场实际运营的需要。

珠三角地区的土壤电阻率温度修正模型

不同温度下测量得到的土壤电阻率需要进行温度修正。目前土壤电阻率或电导率的温度修正模型主要建立在土壤浸出液或电解质溶液的实验基础上,但仍被广泛应用于实际土壤的电阻率或电导率温度修正,这些模型对于不同土壤的应用效果及模型适应性值得研究。为此选取了珠三角地区具有代表性的砂土、砂粉土、粉土、粉壤土、粘壤土等5种不同质地各3种土壤样品,采用四极法布置的Miller soil box土壤电阻率测试箱,运用交流伏安法进行了5～45°C范围的土壤电阻率温度特性实验,结果表明目前大多基于土壤浸出液或电解质溶液提出的土壤电阻率温度修正模型对实际土壤数据的修正效果不理想。采用非线性回归分析方法分别针对5种土壤建立了4种形式的电阻率温度修正模型,结果表明,乘幂模型不适合在5～45°C的宽温度范围进行电阻率修正,建立的比率模型、指数模型和多项式模型对土壤电阻率温度修正效果较好。在此基础上建立了针对不同土壤的统一温度修正模型。

考虑多重周期性的短期电价预测

考虑到电价各时段变化以及周末与工作日变化的差异,提出了区分周末的分时段短期电价预测模型。该模型首先将各日中同一时段的电价形成该时段的电价序列,再将各时段电价序列分为工作日电价序列和周末电价序列。这样形成了多个消除了日周期性和星期周期性的子电价序列,分别对各子电价序列进行预测以得到预测日电价。采用基于小波分析的广义回归神经网络对这些子电价序列分别进行提前一天的预测,各子电价序列的预测电价就形成了下一天的预测电价。采用该方法对西班牙电力市场电价进行了长时间的连续预测,并与已有的预测方法进行了详细的比较分析,研究表明该方法能够提供更准确的预测电价。

考虑非气象因素的电网夏季降温负荷研究

考虑非气象因素,对夏季降温负荷进行研究。在分析降温负荷与温度因子关系的基础上,对回归模型中降温负荷的常量和变量部分与相应关键影响因素进行进一步的相关性分析,揭示经济因子和区位电能消费倾向因子对电网夏季降温负荷的影响并提出一种新的负荷模型。该模型可根据日最高气温、GDP和城乡人口统计数据的有机组合,实现夏季降温负荷变化规律的有效分析。山东电网夏季降温负荷的规律分析验证了该模型的有效性和适用性。

航天电连接器综合应力可靠性统计模型的验证

针对目前普遍存在的可靠性统计模型准确性的问题,依据从失效机理推导出的电连接器综合应力作用下的广义Eyring-Weibull模型,从统计检验角度出发,利用恒定综合应力加速寿命试验数据,应用概率纸检验法及范-蒙特福特检验法,验证了电连接器的寿命服从威布尔分布;利用图分析和回归分析,验证了航天电连接器的加速寿命方程为广义Eyring模型。验证结果表明,广义Eyring-Weibull模型能较好地描述Y11P系列电连接器寿命特征在综合应力作用下的变化规律。