Long-Term Load Forecasting of Southern Governorates of Jordan Distribution Electric System

Load forecasting is vitally important for electric industry in the deregulated economy. This paper aims to face the power crisis and to achieve energy security in Jordan. Our participation is localized in the southern parts of Jordan including, Ma’an, Karak and Aqaba. The available statistical data about the load of southern part of Jordan are supplied by electricity Distribution Company. Mathematical and statistical methods attempted to forecast future demand by determining trends of past results and use the trends to extrapolate the curve demand in the future.

Characteristics of dynamic strain and strength of frozen silt under long-term dynamic loading

The dynamic swain and strength of frozen silt under long-term dynamic loading are studied based on creep tests. Three groups of tests are performed (Groups I, II, and III). The initial deviator stresses of Groups I and II are same and the dynamic stress ampli- tude of Group II is twice as that of Group I. The minimum value of dynamic stress in Group IlI is near zero and its dynamic stress amplitude is larger than those of Groups I and II. In tests of all three groups there are similar change trends of accttmulative sWain, but with different values. The accumulative swain curves consist of three stages, namely, the initial stage, the steady stage, and the gradual flow stage. In the tests of Groups I and II, during the initial stage with vibration times less than 50 loops the strain ampli- tude decreased with the increase of vibration times and then basically remained constant, fluctuating in a very small range. For the tests of Group III, during the initial and steady stages the sWain amplitude decreased with the increase of vibration times, and then increased rapidly in the gradual flow stage. The dynamic strength of frozen silt decreases and trends to terminal dynamic strength as the vibration times of loading increase.

Long Term Load Forecasting and Recommendations for China Based on Support Vector Regression

Long-term load forecasting (LTLF) is a challenging task because of the complex relationships between load and factors affecting load. However, it is crucial for the economic growth of fast developing countries like China as the growth rate of gross domestic product (GDP) is expected to be 7.5%, according to China’s 11th Five-Year Plan (2006-2010). In this paper, LTLF with an economic factor, GDP, is implemented. A support vector regression (SVR) is applied as the training algorithm to obtain the nonlinear relationship between load and the economic factor GDP to improve the accuracy of forecasting.

Long-Term Electrical Load Forecasting in Rwanda Based on Support Vector Machine Enhanced with Q-SVM Optimization Kernel Function

In recent years, Rwanda’s rapid economic development has created the “Rwanda Africa Wonder”, but it has also led to a substantial increase in energy consumption with the ambitious goal of reaching universal access by 2024. Meanwhile, on the basis of the rapid and dynamic connection of new households, there is uncertainty about generating, importing, and exporting energy whichever imposes a significant barrier. Long-Term Load Forecasting (LTLF) will be a key to the country’s utility plan to examine the dynamic electrical load demand growth patterns and facilitate long-term planning for better and more accurate power system master plan expansion. However, a Support Vector Machine (SVM) for long-term electric load forecasting is presented in this paper for accurate load mix planning. Considering that an individual forecasting model usually cannot work properly for LTLF, a hybrid Q-SVM will be introduced to improve forecasting accuracy. Finally, effectively assess model performance and efficiency, error metrics, and model benchmark parameters there assessed. The case study demonstrates that the new strategy is quite useful to improve LTLF accuracy. The historical electric load data of Rwanda Energy Group (REG), a national utility company from 1998 to 2020 was used to test the forecast model. The simulation results demonstrate the proposed algorithm enhanced better forecasting accuracy.

Optimal Scheme with Load Forecasting for Demand Side Management (DSM) in Residential Areas

Utilities around the world have been considering Demand Side Management (DSM) in their strategic planning. The costs of constructing and operating a new capacity generation unit are increasing everyday as well as Transmission and distribution and land issues for new generation plants, which force the utilities to search for another alternatives without any additional constraints on customers comfort level or quality of delivered product. De can be defined as the selection, planning, and implementation of measures intended to have an influence on the demand or customer-side of the electric meter, either caused directly or stimulated indirectly by the utility. DSM programs are peak clipping, Valley filling, Load shifting, Load building, energy conservation and flexible load shape. The main Target of this paper is to show the relation between DSM and Load Forecasting. Moreover, it highlights on the effect of applying DSM on Forecasted demands and how this affects the planning strategies for utility companies. This target will be clearly illustrated through applying the developed algorithm in this paper on an existing residential compound in Cairo-Egypt.

基于双重分解和双向长短时记忆网络的中长期负荷预测模型

针对中长期电力负荷序列噪声含量高、难以直接提取序列周期规律从而影响预测精度的问题,提出了一种基于完全自适应噪声集合经验模态分解(complete ensemble empirical mode decomposition with adaptive noise,CEEMDAN)和奇异谱分析(singular spectrum analysis,SSA)双重分解的双向长短时记忆网络(bidirectional long and short time memory,BiLSTM)预测模型。首先,采用CEEMDAN对历史负荷进行分解,以得到若干个周期规律更为清晰的子序列;再利用多尺度熵(multiscale entropy,MSE)计算所有子序列的复杂程度,根据不同时间尺度上的样本熵值将相似的子序列重构聚合;然后,利用SSA去噪的功能,对高度复杂的新序列进行二次分解,去除序列中的噪声并提取更为主要的规律,从而进一步提高中长序列预测精度;再将得到的最终一组子序列输入BiLSTM进行预测;最后,考虑到天气、节假日等外部因素对电力负荷的影响,提出了一种误差修正技术。选取了巴拿马某地区的用电负荷进行实验,实验结果表明,经过双重分解可以将均方根误差降低87.4%;预测未来一年的负荷序列时,采用的BiLSTM模型将拟合系数最高提高2.5%;所提出的误差修正技术可将均方根误差降低9.7%。

EXPERIENCE WITH THERMOMECHANICAL FATIGUE UNDER SERVICE-TYPE LOADING

The thermomechanical fatigue behaviour of different high temperature alloys has been investigated and is under investigation respectively. The creep-fatigue behaviour of heat resistant steels was investigated by long-term service-type strain cycling tests simulating thermomechanical fatigue (TMF-) loading conditions at the heated surface of e.g. turbine rotors. Single-stage as well as three-stage cycles leads to similar results at the application of the damage accumulation rule. Life prediction which simulates typical combinations of cold starts, warm starts and hot starts has been established successfully for isothermal service-type loading and will be exceeded for thermomechanical loading. Long-term thermomechanical fatigue testing of Thermal Barrier Coating systems show typical delamination damage. An advanced TMF cruciform testing system enables complex multiaxial loading.

一种采用记忆神经网络和曲线形状修正的负荷预测方法

针对分布式电源和新型负荷容量累积造成负荷影响因素多元化和不确定性特性增强的问题,文中提出一种采用记忆神经网络和曲线形状修正的负荷预测方法。在负荷峰值预测中,采用最大信息系数计算负荷峰值与影响因素的非线性相关性,实现对输入特征的筛选;综合考虑负荷峰值序列的长短期自相关性和输入特征与负荷峰值的不同程度相关性,结合Attention机制和双向长短时记忆(bidirectional long short-term memory,BiLSTM)神经网络建立负荷峰值预测模型。在负荷标幺曲线预测中,通过误差倒数法组合相似日和相邻日,建立负荷标幺曲线预测模型;针对预测偏差的非平稳特征,利用自适应噪声的完全集成经验模态分解和BiLSTM网络建立误差预测模型,对曲线形状进行修正。应用中国北方某城市的区域电网负荷数据为算例,验证了所提模型的有效性。

基于集群辨识和卷积神经网络-双向长短期记忆-时序模式注意力机制的区域级短期负荷预测

为了解决区域级短期电力负荷预测时输入特征过多和负荷时序性较强的问题,提出一种基于集群辨识和卷积神经网络(convolutional neural networks,CNN)-双向长短期记忆网络(bi-directional long short-term memory,BiLSTM)-时序模式注意力机制(temporal pattern attention,TPA)的预测方法。首先,将用电模式和天气作为影响因素,基于二阶聚类算法对区域内的负荷节点进行集群辨识,再从每个集群中挑选代表特征作为深度学习模型的输入,这样既能减少输入特征维度,降低计算复杂度,又能综合考虑预测区域的整体特征,提升预测精度。然后,针对区域电力负荷时序性的特点,用CNN-BiLSTM-TPA模型完成训练和预测,该模型能提取输入数据的双向信息生成隐状态矩阵,并对隐状态矩阵的重要特征加权,从多时间步上捕获双向时序信息用于预测。最后,在美国加利福尼亚州实例上分析验证了所提方法的有效性。

基于变量选择与Transformer模型的中长期电力负荷预测方法

准确且有效的负荷预测对于电力系统的实时运行和调度非常重要。提出了一种融合变量选择与稀疏Transformer模型的预测方法,将静态变量和时序变量作为输入,充分发挥静态变量在全局时间范围内的信息增强作用,基于门控机制设计变量分权组件,根据变量与预测结果的相关性,赋予变量不同的权重。设计了双层编码结构,进行时序特征提取,对注意力进行稀疏处理,通过多变量输入对未来时刻负荷进行预测。基于真实电力负荷数据的实验表明,本文模型能够提高中长期负荷预测精度和效率。

基于生成对抗网络和EMD-ISSA-LSTM的短期电力负荷预测

针对电力负荷本身固有的不稳定性和非线性,导致短期电力负荷预测精度难以提升问题。本文提出一种基于EMD和LSTM相结合的短期电力负荷预测方法。首先,利用EMD将原始信号分解为一系列本征模态函数和一个残差量。随后,将所有分量输入LSTM中。为进一步提升负荷预测精度和优化模型泛化能力,分别对大分量信号引入改进麻雀搜寻算法优化LSTM超参数和对原始负荷数据引入表格生成对抗网络生成新数据样本,形成基于表格生成对抗网络和EMD-ISSA-LSTM的短期电力负荷预测方法。最后,分别采用第九届电工数学建模竞赛负荷数据和湖南省某地市含分布式电源的负荷数据进行效果验证。结果表明,在两种数据集下,该模型的平均绝对百分比误差分别为2.37%和2.76%,验证了该方法的有效性。

基于改进金豺算法的短期负荷预测

针对电力负荷序列波动性和预测精度不高的问题,提出一种基于变分模态分解、排列熵和改进金豺算法优化双向长短期记忆网络的预测模型。首先,利用变分模态分解重构原始负荷序列,再采用排列熵理论对分解后的子序列进行熵值重组;然后,利用改进金豺算法对双向长短期记忆网络的参数进行优化,并对每个子序列建立预测模型;最后,组合各模型结果得到最终预测值。实验结果表明,本文模型预测精度更高,与真实值拟合度更好。

长期循环荷载下土的动力学特性与本构模型研究进展

随着交通基础设施的快速发展,长期循环荷载下土体的动力性能与相应的本构模型体系愈发受到关注,其能为该类荷载下地基或者岩土构筑物的动力稳定性和服役性能评估提供理论基础与技术支撑.最近20年来,国内外相关学者已开展了大量的室内试验探索长期循环荷载下土的动力特性与影响因素,建立相应的理论模型描述土体的长期循环变形特征,并努力将其应用于工程实践.目前,对长期循环荷载下土体动力学性能与主要影响因素的研究基本明确,但在如何减少本构模型参数,增强本构模型在变幅值、变频率等复杂实际工况时的适用性等研究尚需进一步加强.本文通过对该方向研究发展的总结,明确了未来的发展方向,并提出了当前研究局限的可能解决思路,有利于进一步推进相关研究成果应用于工程实践的进程.

基于STE-TCN的中短期电力负荷预测

目的 针对传统电力负荷预测模型对长序列预测精度低的问题,提出一种结合跳级卷积连接与时间编码网络的新型时序卷积神经网络(TCN)模型——STE-TCN模型。方法 首先对TCN模型加入跨周期的膨胀卷积通道(Skip-convolution)提取电力数据周期信息;再进行特征融合得到Skip-TCN网络,使网络抓取周期规律,增加信息利用长度;最后设计日期编码网络(Time encoding network)捕捉生活周期和季节性特征,与Skip-TCN进行特征融合得到STE-TCN模型,实现对电力负荷数据长序列预测。结果 实验表明:在与TCN模型和传统时序网络的对比下,Skip-TCN的预测精度均有提升,在预测长度更长的测试上提升尤为明显。结论 实验结果验证了通过对更长跨度时序关系的捕捉,STE-TCN网络改进方法有效提升了对长序列电力负荷的预测精度。

基于Stacking集成学习的远程资源传输负荷预测

传统电网远程资源传输负荷预测方法忽略了对资源的集成训练,导致电网负荷预测结果与实际值偏差较大。为此,提出基于Stacking集成学习的远程资源传输负荷预测方法。构建Stacking集成学习模型,同时通过长短时记忆网络构建Stacking-LSTM网络混合模型,利用时间滑动窗口构建影响因素数据特征图,并将其输入网络混合模型,利用Stacking基础学习训练层实现训练,并将训练结果输入LSTM网络层,完成电网远程资源传输负荷预测。实验结果表明:该方法的网络收敛速度较快,获取特征的贡献度较高,且负荷预测结果接近实际值,可以较好地跟踪负荷变化情况。

基于改进Q学习算法和组合模型的超短期电力负荷预测

单一模型在进行超短期负荷预测时会因负荷波动而导致预测精度变差,针对此问题,提出一种基于深度学习算法的组合预测模型｡首先,采用变分模态分解对原始负荷序列进行分解,得到一系列的子序列。其次,分别采用双向长短期记忆网络和优化后的深度极限学习机对每个子序列进行预测。然后,利用改进Q学习算法对双向长短期记忆网络的预测结果和深度极限学习机的预测结果进行加权组合,得到每个子序列的预测结果。最后,将各个子序列的预测结果进行求和,得到最终的负荷预测结果。以某地真实负荷数据进行预测实验,结果表明所提预测模型较其他模型在超短期负荷预测中表现更佳,预测精度达到98%以上。

基于Bi-LSTM网络的时变综合负荷模型参数辨识

考虑到实际电网负荷的组成会随着系统运行方式、环境状况等因素发生变化,以及各类分布式电源的接入,负荷模型中增加了具有各种时变特性的负荷分量,对其进行参数辨识的难度日益加大。这里提出了一种基于深度学习的时变参数辨识模型,用于综合负荷模型时变参数的辨识。采用两个并行的双向长短期记忆(Bi-LSTM)网络,利用时变参数以及有功、无功功率和正序电压的时序特性,综合考虑它们对时变参数的影响,并在系统测量范围的情况下,辨识综合负荷模型的所有时变参数。

基于历史天气的区域电网负荷预测

随着社会经济的迅速发展,人们对电能的需要日益增加,但是在电网运行中,常常会出现电力产能过剩或者不足的情况,为保证电力系统安全稳定、经济运行,就必须掌握各种区域电网负荷的变化规律和发展趋势。论文对重庆市区供电分公司供电区域电网中长期负荷进行预测,提出一种预测区域电网中长期负荷的方法,即一种基于前12个月历史天气条件和区域电网负荷关联关系的多元非线性拟合的特征参数因子曲线的中长期负荷预测方法,建立基于不同算法的多种预测模型,通过归一化处理,得到的区域电网中长期负荷预测的精度高,与实际区域电网负荷之间的误差小,对于区域电网中长期负荷预测分析具有重要参考利用价值。

基于MSW-LSTM的卫星功率负荷预测方法

文章提出一种基于多尺度小波变换的长短期记忆神经网络(Multi-scale Wavelet-Long Short-term Memory,MSW-LSTM)卫星功率负荷预测方法,利用多尺度小波变换的时频特性将卫星功率负荷数据进行平稳化处理,结合LSTM算法针对多尺度小波分解并降噪后的各尺度功率负荷序列进行预测,并对预测得到的各序列数据进行重构得到时域功率负荷数据,从而提高卫星功率负荷预测的精度。通过某在轨卫星真实功率负荷数据进行分析,仿真结果表明本文提出的算法可以有效地提高功率负荷预测的精度,且针对不同轨道的卫星功率负荷预测有较高的普适性和鲁棒性。

基于数据融合的中长期概率性负荷预测方法研究

月度负荷预测是电力系统中长期运行和营销工作开展的基础,概率性电力负荷预测能够刻画中长期不确定性,更好地支撑新型电力系统负荷评估和调控策略制定。在此背景下,以系统负荷作为研究对象开展中长期概率性预测方法研究,提出了基于细粒度数据融合的中长期概率性预测方法。首先,根据影响因素建立小时级的多元线性回归模型对细粒度的负荷进行建模,再根据影响因素的不同预测值生成未来不同场景下的细粒度预测结果。其次,根据“自下而上”的时间层级协调策略,对每一个场景均进行月度聚合,生成不同层级地区的月度负荷预测结果,形成概率性预测结果。最后,以中国东部某区域及其下辖地区的负荷数据为例,验证了方法的有效性。