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%。     

Incorporating microgrids coupling with utilization of flexible switching to enhance self-healing ability of electric distribution systems

Electric distribution networks have to deal with issues caused by natural disasters. These problems possess unique characteristics, and their severity can make load restoration methods impotent. One solution that can help in alleviating the aftermath is the use of microgrids (MGs). Employing the cumulative capacity of the generation resources through MG coupling facilitates the self-healing capability and leads to better-coordinated energy management during the restoration period, while the switching capability of the system should also be considered. In this paper, to form and schedule dynamic MGs in distribution systems, a novel model based on mixed-integer linear programming (MILP) is proposed. This approach employs graph-related theories to formulate the optimal formation of the networked MGs and management of their proper participation in the load recovery process. In addition, the Benders decomposition technique is applied to alleviate computability issues of the optimization problem. The validity and applicability of the proposed model are evaluated by several simulation studies.     

Notwendigkeit und Vermarktung von Flexibilitätsoptionen im Energiesystem der Zukunft

Demands on production, distribution and consumption of electrical energy change fundamentally with the energy revolution. Energy purchasing costs for inflexible consumers are rising and proceeds of inflexible producers are sinking. Companies are able to reduce costs by marketing operational flexibility options. This article sets out the need of flexibility in the energy system and the new marketing options. Flexibility potentials within infrastructure plants of a chemical park are analyzed, evaluated regarding marketing and activated in the presented research project FlexChemistry.     

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。     

Structural load alleviation using distributed delay shaper: Application to flexible aircraft

Lightweight flexible aircraft suffers from unwanted oscillatory vibrations during aircraft manoeuvres. A recently developed distributed-delay signal (DZV) shaper is therefore proposed to be applied as a feedforward controller to alleviate the manoeuvre loads, as an alternative to traditional structural filters used routinely in this context. Structural filters are essentially linear low-pass filters with bandwidth below the significant flexible modes, applied to control signals generated either by the pilot’s direct input or by the flight control system. It has been showed that if instead a properly tuned signal shaper is used, better performance can be achieved: first, the target modes are significantly attenuated while the responsiveness of the aircraft is less compromised and secondly, the oscillatory nature of the vibrations are reduced. The high fidelity simulation results on a full scaled dynamic model of a highly flexible blended wing–body (BWB) aircraft show that in comparison to traditional structural filters, signal shapers significantly reduce the wing root loading (forces and moments) which provides potential structural benefits.     

Bearing capacity of horizontally layered geosynthetic reinforced stone columns

In very soft soils, the bearing capacity of stone columns may not improve significantly due to very low confinement of the surrounding soil. Therefore, they may be reinforced with geosynthetics by using vertical encasement or horizontal layers. Very limited studies exist on horizontally reinforced stone columns (HRSCs). In this research, some large body laboratory tests have been performed on horizontally reinforced stone columns with diameters of 60, 80, and 100?mm and groups of stone columns with 60?mm diameter. Results show that the bearing capacity of stone columns increases by using horizontally reinforcing layers. Also, they reduce lateral bulging of stone columns by their frictional and interlocking effects with stone column aggregates. Finally, numerical analyses were carried out to study main affecting parameters on the bearing capacity of HRSCs. Numerical analysis results show that the bearing capacity increases considerably with increasing the number of horizontal layers and decreasing space between layers.     

含分布式能源区域电网月最大净负荷概率预测

负荷预测在电网规划和运行中十分重要,大规模分布式能源接入电网参与能量交换,可使电网用户优化其用电模式,但造成区域电网月最大净负荷特性发生根本性改变,增加了月最大净负荷预测的不确定性。为此,结合BP神经网络算法与分位数回归模型,构建了区域电网月最大净负荷的非线性概率预测模型;并利用核密度估计算法计算得到了月最大净负荷概率预测分布曲线;最后,以上海某含分布式能源区域电网为例,验证了该方法的可行性与可靠性。结果表明,该方法可准确刻画月最大净负荷波动特性,为电网规划与负荷管理提供依据。     

基于降噪时序深度学习网络的风电功率短期预测方法

利用风电场历史功率数据预测未来一段时间内的风功率,对保障电网安全稳定运行具有重要的意义。本文提出一种基于奇异谱分析SSA(singular spectrum analysis)和长短时记忆LSTM(long-short term memory net⁃work)网络的时序特征预测框架用于短期风功率的预测。首先通过SSA对历史风功率原始数据进行降噪处理,然后经过数据转换之后,以LSTM网络为基础进行预测模型的训练,最后通过某风电场提供的两个风机的历史功率数据进行验证。实验结果表明,奇异谱分析对风电场的历史数据具有良好的降噪性,SSA+LSTM模型在测试数据上取得了较好的预测性能,能够有效进行短期风功率的预测。