粉体含能材料生产与储运中的静电安全及防护

分析了静电产生的原因,阐述了粉体含能材料生产中的静电起电现象、静电的危害、静电安全性评估标准以及建立在此标准基础上的静电放电危险的评价办法,提出了粉体含能材料在生产、运输中所需要采取的静电防护措施。     

基于VMD和改进TCN的短期光伏发电功率预测

光伏发电功率存在波动性,且光伏出力易受各种气象特征影响,传统TCN网络容易过度强化空间特性而弱化个体特性。针对上述问题,文中提出一种基于VMD和改进TCN的短期光伏发电功率预测模型。通过VMD将原始光伏发电功率时间序列分解为若干不同频率的模态分量,将各个模态分量以及相对应的气象数据输入至改进TCN网络进行建模学习。利用中心频率法确定VMD的最优分解模态分解个数。在传统TCN预测模型的基础上,使用DropBlock正则化取代Dropout正则化以达到抑制卷积层中信息协同的效果,并引入注意力机制自主挖掘并突出关键气象输入特征的影响,量化各气象因素对光伏发电的影响,从而提高预测精度。以江苏省某光伏电站真实数据为例进行仿真实验,结果表明所提预测方法的RMSE为0.62 MW,MAPE为2.03%。     

Binary whale optimization algorithm: a new metaheuristic approach for profit-based unit commitment problems in competitive electricity markets

This article presents a metaheuristic approach, the binary whale optimization algorithm (BWOA), to solve complex, constrained, non-convex, binary-nature profit-based unit commitment (PBUC) optimization problems of a price-taking generation company (GenCo) in the electricity market. To simulate the binary-nature PBUC problem, the continuous, real-value whale position/location is mapped into binary search space through various transfer functions. This article introduces three variants of BWOA using tangential hyperbolic, inverse tangent (arctan) and sigmoidal transfer functions. The effectiveness of the BWOA approaches is examined in test systems with different market mechanisms, i.e. an energy-only market, and energy and reserve market participation with different reserve payment methods. The simulation results are presented, discussed and compared with other existing approaches. The convergence characteristics, solution quality and consistency of the results across different BWOA variants are discussed. The superiority and statistical significance of the proposed approaches with respect to existing approaches is also presented.     

Oil Demand and Stocks

Current data of world oil demand. This includes international bunkers and refinery fuel. Updated on a monthly basis. Current data of oil demand from counties such as Canada, the United States of America, Japan, OECD Europe, Belgium, France, Germany, Italy, Netherlands, Spain, Sweden, the United Kingdom, Australia, Mexico, Republic of Korea, and Turkey. Updated on a monthly basis. Current data for crude oil and refined product stocks in Canada, Chile, Mexico, the United States (Western Hemisphere), France, Germany, Italy, Netherlands, Spain, the United Kingdom and Other Europe (Europe), Japan, Republic of Korea, Other Pacific (Asia-Pacific), and Total OECD (Table 12.1) Current data for refined product stocks in the OECD Western Hemisphere, OECD Europe, OECD Asia-Pacific and Total OECD. Products include gasoline, diesel and gasoil, and heavy fuel oil. Updated on a monthly basis (Table 12.2).     

Electricity Production

Current data on net electricity production, as well as a breakdown of production by country. Updated on a monthly basis.     

Electricity Production

Current data on net electricity production, as well as a breakdown of production by country. Updated on a monthly basis.     

时态神经网络模型及其在股票分类预测上应用

对具有时间属性的数据进行数据挖掘称为时态数据挖掘，用以发现数据在时间上的知识，当数据变化不规律时，如股票交易数据,就很难发现有价值的规律与规则。而神经网络具有并行、容错、可以硬件实现以及自我学习的优点,可作为股票分类预测应用的一种方法。通过将股票数据与时态型相结合，将股票数据转换成时态型股票数据，提出时态神经网络模型的分类方法，对收集的若干上市公司十年内的股票数据进行分析，构建了时态股票数据神经网络分类器对股票进行分类预测。经过实验验证，相比改进前的神经网络和支持向量机方法，该分类器具有更高的分类准确率。结果证明，这种时态数据神经网络模型对于多只股票的分类预测是非常有效的，可以很好地运用到股票市场的分类预测中。     

不同苯乙烯工艺技术经济分析及建议

通过对国内外苯乙烯市场供需趋势的梳理,针对4种苯乙烯主要生产工艺,重点从原料可获性、产品质量、能耗物耗以及成本竞争力等方面对不同工艺主要技术经济指标进行了对比分析,并提出了行业可持续发展的有关建议。     

基于流数据聚类算法的电力大数据异常检测

针对电力大数据流的异常检测问题,该文将流数据聚类算法与电力大数据相结合,针对现有流数据聚类算法不易存储全部数据、断电数据易丢失等问题,以及流数据聚类算法对于离线阶段聚类算法实时应答的要求,从数据的完整性、安全性以及流数据聚类算法的低时间复杂度的角度出发,对CluStream流数据聚类算法进行改进,提出流式K-means聚类算法。对在线阶段,使用Redis集群进行流数据的缓冲,并设计节点时间衰减策略,增大心跳消息中有效消息所占比例;对离线阶段聚类算法进行优化,使用最佳距离法确定初始聚类中心,减少迭代次数;最后,使用所提出的流式K-means聚类算法进行用户用电异常行为检测,实验结果表明,该算法能够很好的发现用户用电异常行为。     

Understanding the determinants on household electricity consumption in Korea: OLS regression and quantile regression

The paper aims to investigate the determinants of household electricity consumption in Korea by using both the OLS regression and quantile regression. The results show that the effects of socio-demographic, dwelling, and electricity consumption characteristics on household electricity consumption may differ between two regressions and may differ across quantiles. We found that age group of household head, number of household, housing area, the number of household appliances, and refrigerator usage time were significant in all quantiles.