Short-term wind speed forecasting based on random forest model combining ensemble empirical mode decomposition and improved harmony search algorithm

ABSTRACT

Wind speed forecasting plays an important role in power grid dispatching management. This article proposes a short-term wind speed forecasting method based on random forest model combining ensemble empirical modal decomposition and improved harmony search algorithm. First, the initial wind speed data set is decomposed into several ensemble empirical mode functions by EEMD, then feature extraction of each sub-modal IMF is performed using fast Fourier transform to solve the cycle of each sub-modal IMF. Next, combining the high-performance parameter optimization ability of the improved harmony search algorithm, two optimal parameters of random forest model, number of decision trees, and number of split features are determined. Finally, the random forest model is used to forecast the processing results of each submodal IMF. The proposed model is applied to the simulation analysis of historical wind data of Chaoyang District, Liaoning Province from April 27, 2015 to May 22, 2015. To illustrate the suitability and superiority of the EEMD-RF-IHS model, three types of models are used for comparison: single models including ANN, SVM, RF; EMD combination models including EMD-ANN, EMD-SVM, EMD-RF; EEMD combination models including EEMD-ANN, EEMD-SVM, EEMD-RF. The analysis results of evaluation indicators show that the proposed model can effectively forecast short-term wind data with high stability and precision, providing a reference for forecasting application in other industry fields.     

Multi-objective-based optimal transmission switching and demand response for managing congestion in hybrid power systems

ABSTRACT

This paper proposes a novel congestion management (CM) approach by using the optimal transmission switching (OTS) and demand response (DR) for a system with conventional thermal generators and renewable energy sources (RESs). In this paper, wind and solar PV units are considered as the RESs. The stochastic behavior of wind and solar PV powers are modeled by using the appropriate probability density functions (PDFs). The proposed CM methodology simultaneously optimizes the generation dispatch, demand response, and also the network topology of the power system. The OTS identifies the branches that should be taken out of service by significantly reducing the operating cost of the system while respecting the system security. Here, the total operating cost minimization/social welfare maximization and system losses minimization are considered as the objectives to be optimized. The proposed CM problem is solved using the multi-objective Jaya algorithm and it is used to determine a set of Pareto-optimal solutions. The Jaya algorithm is simple and it does not have any algorithmic-specific parameters to be tuned. This aspect reduces the designer’s effort in tuning the parameters to arrive at the optimum objective function value. A fuzzy logic-based approach is used to identify the best compromise solution. The effectiveness of the proposed CM approach is examined on modified IEEE 30 and practical Indian 75 bus test systems. The obtained simulation results are analyzed and they show the effectiveness of the proposed approach.     

Investigation of sustainable energy alternatives for powering remote communities in northern Ontario

ABSTRACT

Remote communities in the North of Ontario survive in isolation as their proximity to the southern industrial sector of the province limits their accessibility to the major grid. The lack of grid connection has led to antiquated methods of power generation which pollute the environment and deplete the planet of its natural resources. Aside from the primary means of electricity generation being by diesel generators, generation infrastructure is deteriorating due to age and the stagnation of the power supply has led to communities facing load restrictions. These challenges may be resolved by introducing clean energy alternatives and providing a fuel blend option. The primary energy sources investigated in this research are solar, wind, and hydrogen. To assess the viability of these energy production methods in Northern communities, an exergy analysis is employed as it utilizes both the first and second law of thermodynamics to determine systems’ efficiency and performance in the surroundings. Local weather patterns were used to determine the viability of using wind turbines, solar panels and/or hydrogen fuel cells in a remote community. Through analysis of the resources available at the community, it was determined that the hydrogen fuel cell was best suited to provide clean energy to the community. Wind resulted in low efficiency in the range of 2–3% while solar efficiencies resulted in ranges of 18 – 19%, as the seasonal variations between the three years is not very great. Due to the higher operating efficiencies observed of the PV panels it would also be an attractive alternative to diesel generators however, the lack of consistent operation above 30% efficiency throughout the year, resulted in hydrogen fuel cells being a better alternative.     

The hybrid model of empirical wavelet transform and relevance vector regression for monthly wind speed prediction

ABSTRACT

In order to improve the prediction ability for the monthly wind speed of RVR, the hybrid model of empirical wavelet transform and relevance vector regression (EWT-RVR) is proposed for monthly wind speed prediction in this study. Compared with empirical mode decomposition (EMD), empirical wavelet transform (EWT) can obtain a more consistent decomposition and have a mathematical theory. In order to testify the superiority of EWT-RVR, several traditional RVR models are used to compare with the proposed EWT-RVR method under the situation of the same embedding dimensions. The experimental results show that the proposed EWT-RVR method has a better prediction ability for monthly wind speed than RVR. It can be concluded that the proposed EWT-RVR method for monthly wind speed is effective.     

提高节理面c和φ对岩坡开挖变形的影响

为了反映岩质边坡在节理面注浆后的变形效应,首先,通过室内试验,分析注浆前后岩体变形和破坏的全过程,以探讨其抗剪性能(粘结力c和内摩擦角φ)的变化;然后,基于理想弹塑性本构模型的Mohr-Cou-lomb准则,运用拉格朗日元数值方法(FLAC3D),对岩坡注浆前后变形效应(水平位移、垂直位移、剪应变增量)进行模拟。结果表明:注浆加固后,岩体的位移场变得均匀和连续,节理面处的较大位移受到抑制,边坡的整体性得到提高,有利于边坡的稳定性。     

最大剪切模量对土动力参数及地震反应的影响

最大剪切模量是影响土的动剪切模量比、阻尼比和土层地震反应的最重要参数之一。通常采用室内应变法来确定最大剪切模量，给出土的动剪切模量比和阻尼比，而采用现场剪切波速法求得的结果则很少见。研究了剪切波速法和应变法所确定的最大剪切模量对土动剪切模量比、阻尼比和土层地震反应的影响，推导了两种方法所确定的动剪切模量比和阻尼比之间的关系式。结果表明：最大动剪切模量对土的动剪切模量比、阻尼比和土层地震反应的影响很显著。     

低周荷载下型钢混凝土柱抗剪性能智能分析

为了研究型钢混凝土短柱的抗震性能，通过21根SRC柱在低周反复荷载作用下的剪切黏结破坏试验结果，在利用灰色关联理论进行模型输入变量选择的基础上，建立了其基于改进神经网络模型的受剪承载力分析模型，进而研究了混凝土抗压强度、腹板宽度、轴压比及箍筋间距等因素对SRC柱抗剪能力的影响规律，并对SRC柱的受剪承载力进行了预测。结果表明，所提方法能够反映受剪承载力与影响因素间的非线性变化规律，可供SRC柱在低周往复荷载作用下的受剪承载力分析参考。     

苏南地区CO2本底浓度及源汇特征

基于2015~2018年苏州张家港站CO₂在线观测数据，采用时序检查、选取稳定性数据、异常值剔除等质量控制方法获得可靠数据，并通过平均移动过滤（MAF）本底筛分法获得本底数据，讨论苏南地区CO₂变化特征.结果发现：CO₂本底浓度日变化为单峰结构，谷值和峰值分别出现在下午15：00和凌晨5：00前后；季节变化为双峰结构，峰值分别出现在12月和4月；日、季节变化的分布特征均与陆地生态系统、气象条件和人类活动有关.此外，2015~2018年CO₂浓度呈逐年上升趋势，抬升浓度占比逐年增加，吸收浓度占比波动较小，表明人类活动对CO₂浓度的影响正在逐年增加；而陆地生态系统对CO₂吸收汇的作用则相对稳定.源汇分析显示，CO₂抬升浓度随季节小幅波动；吸收浓度则夏半年较低，冬半年较高；抬升浓度日变化为单峰结构，谷值和峰值分别出现在15：00和8：00前后，早晨正值上班高峰，机动车排放可能为早晨峰值的主要因素；吸收浓度日间低、夜间高，这主要与植物光合作用及对流输送有关.分析CO₂浓度与风的关系发现，所有季节静风情况下，CO₂浓度偏高均最为明显，大部分方向CO₂浓度高低与风速大小有明显的负相关，其中S~WNW方向偏高最为明显，这可能是因为SW~NW方向主要为内陆城市群，且测站周边建筑区主要位于W~N方向，弱风有利于本地排放累积的结果.此外，WNW方向风速较大时浓度仍偏高明显，可能与测站W~N方向为建筑区及内陆城市群有关；而测站偏东方向主要为农田和林区，受人类活动影响较小，且海上气流较为洁净，故偏东风较弱时浓度也不高；说明了CO₂浓度除了与风速大小有关外，与周边下垫面类型及较远距离环境特征（城市群或海洋）也有一定的关系.     

风对定日镜影响的计算流体动力学数值模拟

利用linux系统下软件平台Fluent 6.3的并行计算技术和实用的结构网格划分方法,基于Reynolds 时均方程,分别采用两种湍流封闭模型:标准k-ε和MMK修正的k-ε模型,模拟计算了定日镜结构的平均风压系数、阻力、升力以及力矩系数和平均风流场.分析了定日镜镜体平均风压、平均风流场的分布规律和特点;并将数值计算结果与风洞试验进行了比较.结果表明,基于Fluent 6.3的MMK修正的k-ε模型较之标准k-ε模型有更好的预测效果.     

热浮力及室外风压耦合驱动下高层建筑疏散走廊烟气运动网络模拟分析

火灾发生后,火灾烟气主要通过疏散走廊向建筑的其他部位蔓延.有效控制疏散走廊中的烟气,可以阻止其进一步蔓延到楼梯间.了解火灾烟气在疏散走廊中的运动规律,是控制其蔓延扩散的前提.热浮力和室外风压是烟气在走廊中运动的主要驱动力,研究二者耦合作用对走廊中烟气运动的影响,对进一步弄清火灾烟气的流动规律具有较大的意义.采用网络模拟软件CONTAM 3.0模拟疏散走廊中火灾烟气在上述两种驱动力作用下的运动情况.结果表明,随室外风速增大,疏散走廊中火灾烟气的运动速度增大,远大于单纯热浮力作用时烟气的运动速度;当热浮力和室外风压耦合驱动时,室外风压对烟气运动的影响起主要作用.