The application of artificial neural networks to substation load forecasting

The substation loading is highly correlated with the customers served. The substations in a distribution system can be categorized as residential, commercial and industrial. Each type has a different power consumption pattern. The substation loading will be varied according to the combination of the above three types of customers. In this paper, a supervisory functional artificial neural network (ANN) technique is applied to solve the load forecasting of three Taipower substations which serve the different customer types. The load forecasting accuracy is enhanced by considering the temperature effect on the substation load demand. With the converged ANN models derived by a training procedure, the temperature sensitivity of the substation load demand is easily obtained by the recall process. It is suggested that the substation load forecasting can be performed efficiently by the proposed method to support distribution operation effectively.     

电力系统短期负荷预测的混合模型神经元网络方法

提出了一种将线性模型方法和神经元网络方法相结合的负荷预测方法－－混合模型神经元网络方法。该方法将一部分线性变化的负荷分量用线性模型描述,其它发量用神经元网络建立,国而同时具有线性模型的优点和神经元网络的优点。交过一方法用于江苏省连云港市超前２４小时负荷预测,取得了比单纯的神经元网络模型高的预测精度。     

Neural network based short-term load forecasting using weathercompensation

This paper presents a novel technique for electric load forecasting based on neural weather compensation. Our proposed method is a nonlinear generalization of Box and Jenkins approach for nonstationary time-series prediction. A weather compensation neural network is implemented for one-day ahead electric load forecasting. Our weather compensation neural network can accurately predict the change of actual electric load consumption from the previous day. The results, based on Hong Kong Island historical load demand, indicate that this methodology is capable of providing a more accurate load forecast with a 0.9% reduction in forecast error     

分时段短期电价预测

分时段电价序列比顺序电价序列的变化特征更单一，有利于电价的分析建模，从而提高预测精度，因此采用各时段电价分别预测的分时段预测方法。该文将相关系数作为选取电价影响因素的标准，考虑了历史电价、负荷、负荷率等影响电价的因素。以小波分析和神经网络作为工具，对不同输入因素和不同预测方法下的电价预测精度进行了研究，并重点比较了基于分时段电价序列的预测方法和基于顺序电价序列的预测方法。算例采用美国新英格兰电力市场历史数据，对其2002年第4季度的电价进行了连续预测。与基于顺序电价序列的预测方法相比，分时段短期电价预测方法能够使平均相对百分比误差下降约3个百分点。     

基于完整自适应噪声集成经验模态分解的LSTM-Attention网络短期电力负荷预测方法

短期电力负荷预测在电网安全运行和制定合理调度计划方面发挥着重要作用。为了提高电力负荷时间序列预测的准确度,提出了一种由完整自适应噪声集成经验模态分解(complete ensemble empirical mode decomposition with adaptive noise, CEEMDAN)和基于注意力机制的长短期记忆神经网络(long short-term memory network based on attention mechanism, LSTM-Attention)相结合的短期电力负荷预测模型。完整自适应噪声集成经验模态分解有效地将负荷时间序列分解成多个层次规律平稳的本征模态分量,并通过神经网络模型预测极大值,结合镜像延拓方法抑制边界效应,提高分解精度,同时基于注意力机制的长短期记忆神经网络自适应地提取电力负荷数据输入特征并分配权重进行预测,最后各预测模态分量叠加重构后获得最终预测结果。通过不同实际电力负荷季节数据分别进行实验,并与其他电力负荷预测模型结果分析进行比较,验证了该预测方法在电力负荷预测精度方面具有更好的性能。     

Next day load curve forecasting using hybrid correction method

This work presents an approach for short-term load forecast problem, based on hybrid correction method. Conventional artificial neural network based short-term load forecasting techniques have limitations especially when weather changes are seasonal. Hence, we propose a load correction method by using a fuzzy logic approach in which a fuzzy logic, based on similar days, corrects the neural network output to obtain the next day forecasted load. An Euclidean norm with weighted factors is used for the selection of similar days. The load correction method for the generation of new similar days is also proposed. The neural network has an advantage of dealing with the nonlinear parts of the forecasted load curves, whereas, the fuzzy rules are constructed based on the expert knowledge. Therefore, by combining these two methods, the test results show that the proposed forecasting method could provide a considerable improvement of the forecasting accuracy especially as it shows how to reduce neural network forecast error over the test period by 23% through the application of a fuzzy logic correction. The suitability of the proposed approach is illustrated through an application to actual load data of the Okinawa Electric Power Company in Japan.     

基于GRU-NN模型的短期负荷预测方法

目前基于统计分析和机器学习的预测方法难以同时兼顾负荷数据的时序性和非线性特点。文中提出了一种基于GRU-NN模型的短期电力负荷预测方法。该方法基于深度学习思想处理不同类型的负荷影响因素,引入门控循环单元(GRU)网络处理具有时序性特点的历史负荷序列,建模学习负荷数据内部动态变化规律,其输出结果与其他外部影响因素(天气、日类型等)融合为新的输入特征,使用深度神经网络进行处理,整体分析特征与负荷变化的内在联系,最后完成负荷预测。以美国某公共事业部门提供的公开数据集和中国某地区的负荷数据作为实际算例,该方法预测精度分别达到了97.30%和97.12%,并与长短期记忆神经网络、多层感知机以及GRU神经网络方法进行对比,实验结果表明所提方法具有更高的预测精度和更快的预测速度。     

基于局部均值分解与神经网络的短期负荷预测

短期负荷预测是电力系统调度和运行的基础,为了提高电力系统短期负荷预测的精度,提出了基于局部均值分解和人工神经网络的电力系统短期负荷预测方法。该方法首先对负荷序列进行局部均值分解,针对分解后具有不同特点的各PF分量设定具体的神经网络参数进行预测,将各分量的预测结果进行重构得到最终的预测结果。仿真实验表明,LMD-BP神经网络的预测方法与传统的EMD-BP神经网络方法相比具有更高的预测精度,同时也验证了该方法的实用性和有效性。     

基于模糊神经网络的电力负荷短期预测

针对电力负荷的特点,综合考虑了温度及日期类型等因素对日最大负荷的影响,提出了一种采用模糊神经网络进行短期负荷预测的方法,并详细介绍了该方法的实现过程。通过对EUNITE(the European Network of Excellence on Intelligent Technologies for Smart Adaptive Systems)网络提供的实际数据进行详细分析确定了影响日最大负荷的相关因素,进而选择了合适的模糊输入以建立相应的模糊神经网络预测模型,并取得了较为理想的预测结果。算例分析结果充分证明了模糊神经网络在短期电力负荷预测方面具有较好的应用前景。     

基于Dropout-ILSTM网络的短期电力负荷预测

针对传统BP神经网络难以处理电力负荷数据间关联的问题,提出了一种基于Dropout的改进的长短期记忆神经网络结构用于短期电力负荷预测。这种改进的长短期记忆神经网络(Improved LSTM,ILSTM),通过将长短期记忆网络的多个时间步输入与输出矢量进行全连接,增强了对目标系统中线性成分的表征;使用Dropout对ILSTM网络进行优化,提高了网络的泛化能力,同时减少了模型的训练时间;以日期、温度、电价和电力负荷数据作为输入构建了Dropout-ILSTM电力负荷预测模型。以AEMO提供的新南威尔士州电力负荷数据作为测试用例,实验结果表明,相较其它神经网络模型,文中所提出的Dropout-ILSTM模型预测精度更高、泛化能力更强,适用于不同预测宽度的电力负荷预测。     

基于神经网络的短期负荷预测与误差纠正算法

提出一种基于模糊神经网络的电力短期负荷预测方法,并对其运行特点进行分析。提出通过改进数据样本从而改善模糊神经网络的方法,可以预测在一些不确定性条件发生剧变的情况下发生突变的负荷。还提出了一个关于误差整合的观点,根据此观点提出了减小误差的方法。实例计算表明,这一模型和方法应用于短期负荷预测能获得较高的预测精度。     

Short-term load forecasting for special days in anomalous loadconditions using neural networks and fuzzy inference method

Conventional artificial neural network (ANN) based short-term load forecasting techniques have limitations in their use on holidays. This is due to dissimilar load behaviors of holidays compared with those of ordinary weekdays during the year and to insufficiency of training patterns. The purpose of this paper is to propose a new short-term load forecasting method for special days in anomalous load conditions. These days include public holidays, consecutive holidays, and days preceding and following holidays. The proposed method uses a hybrid approach of ANN based technique and fuzzy inference method to forecast the hourly loads of special days. In this method, special days are classified into five different day-types. Five ANN models for each day-type are used to forecast the scaled load curves of special days, and two fuzzy inference models are used to forecast the maximum and the minimum loads of special days. Finally, the results of the ANN and the fuzzy inference models are combined to forecast the 24 hourly loads of special days. The proposed method was tested with actual load data of special days for the years of 1996-1997. The test results showed very accurate forecasting with the average percentage relative error of 1.78%     

融合历史数据和实时影响因素的精细化负荷预测

随着智能电网技术的飞速发展,对负荷预测的精度提出了越来越高的要求。融合负荷、天气等多源数据,提出了一种基于数据融合的支持向量机精细化负荷预测方法。首先对负荷历史数据进行聚类分析,将运行日分成六类。然后将负荷数据和温度、湿度等天气数据进行融合,针对六类聚类结果分别建立基于数据融合的支持向量机精细化负荷预测模型,并对模型参数进行全局优化。采用不同的预测模型对浙江省某地级市2013年的负荷进行预测,结果表明所提出的负荷预测方法的预测精度明显高于传统的负荷预测方法的预测精度。     

应用于月度用电量预测的小波分析法

月度用电量预测是中期负荷预测的主要内容,也是制定月度发电规划的基础。文中以美国亚利桑那州为例,采用小波分析法,首先使用小波变换获得若干个采样点减少一半的小波系数;然后分别对各系数插零、重构,恢复到原数据的长度;最后采用RBF神经网络对恢复长度的各系数进行预测。该方法将月度用电量的时间序列分解成趋势项和波动项,分别进行预测,提高了预测精度。     

基于改进BP神经网络的短期电力负荷预测方法研究

针对短期负荷预测精度低、准确性差等问题,将猫群算法CSO和BP神经网络相结合用于短期负荷预测,模型的输入因子是负荷数据和气象信息等,利用猫群算法对BP神经网络的权值和阈值进行优化,得到BP神经网络预测模型的最优解,建立了短期预测模型。通过实例验证了预测模型的有效性和有效性,结果表明,改进模型能够有效降低BP神经网络模型的预测误差,提高预测精度,为我国电力系统短期负荷预测的发展提供了参考和借鉴。     

计及需求响应和深度结构多任务学习的电力系统短期负荷预测

随着需求响应技术的快速发展,使得电力系统负荷数据呈现出规模庞大、结构复杂的非线性特征,基于深度机器学习和高效数据处理平台的负荷预测方法是当前的研究重点。为实现计及需求响应的电力系统短期负荷预测,建立了基于Spark平台和时钟频率驱动循环神经网络(CW-RNNs)的短期负荷预测方法。首先,在Spark平台上设置不同工作组将全部数据分割为多个子数据模块,通过并行化计算提高数据处理效率,进而基于需求响应技术对负荷曲线做出调整,计算得到用户预期收益和用户舒适度影响指标值;其次,采用离散小波变换将调整后的负荷曲线分解,得到一组高、低频信号;并采用偏最小二乘回归模型和CW-RNNs回归模型分别对低、高频信号进行训练学习;最后,将训练好的PLS模型和CW-RNNs模型通过加权平均得到最终组合预测模型(Spark-CW-RNNs)。通过实例计算验证算法的准确性和有效性,结果表明：Spark-CW-RNNs模型比其他单一模型的预测误差更小、预测精度更高,模型具有有效性和可行性。     

一种基于数据挖掘的馈线可装容量模型分析方法

馈线作为配网运行最关键的设备之一,评估馈线供电能力是保障配网运行的重要手段。本文通过引入馈线组负荷同时系数和需要系数两个参数,构建计算模型,求解馈线可装容量以评估馈线供电能力。首先,通过聚类分析和神经网络预测等方法预测馈线组负荷同时系数。然后,将馈线各负荷根据其实际接入容量情况分为饱和负荷和未饱和负荷,采用灰色预测和神经网络相结合的组合预测方法计算未饱和负荷的需要系数。最后,将预测得到的两个系数代入馈线可装容量计算模型进行求解。实际算例分析表明:所提方法的计算结果具有一定的预测趋势,充分利用了馈线载流量,并兼顾了配电网运行的可靠性,对于指导电网营销部门业扩报装工作具有重要意义。     

Demand forecasting in power distribution systems usingnonparametric probability density estimation

Customer demand data are required by power flow programs to accurately simulate the behavior of electric distribution systems. At present, economic constraints limit widespread customer monitoring, resulting in a need to forecast these demands for distribution system analysis. This paper presents the application of nonparametric probability density estimation to the problem of customer demand forecasting using information readily available at most utilities. The method utilizes demand survey information, including weather conditions, to build a probabilistic demand model that expresses both the random nature of demand and its temperature dependence. The paper describes a procedure for developing such a model and its application for demand forecasting based on customer energy usage and outside temperature     

Toward Estimating Autonomous Neural Network-Based Electric Load Forecasters

Anticipation of load's future behavior is very important for decision making in power system operation and planning. During the last 40 years, many different load models have been proposed for short-term forecasting. After 1991, the literature on this subject has been dominated by neural network (NN) based proposals. This is mainly due to the NNs' capacity for capturing the nonlinear relationship between load and exogenous variables. However, one major risk in using neural models is the possibility of excessive training data approximation, i.e., overfitting, which usually increases the out-of-sample forecasting errors. The extent of nonlinearity provided by NN-based load forecasters, which depends on the input space representation, has been adjusted using heuristic procedures. Training early stopping based on cross validation, network pruning methods, and architecture selection based on trial and error are popular. The empirical nature of these procedures makes their application cumbersome and time consuming. This paper develops two nonparametric procedures for solving, in a coupled way, the problems of NN structure and input selection for short-term load forecasting.     

用自适应模糊推理系统预测电力短期负荷

为寻求有效的电力系统负荷预测方法以提高预测结果的准确度,提出了基于Takagi-Sugeno(T-S)模型的自适应神经模糊推理系统(ANFIS)。该系统采用减法聚类初始化模糊推理,把神经网络学习机制引入到逻辑推理中,并用混合学习算法调整前件参数和结论参数,自动产生模糊规则。考虑气象、日期类型等因素后将学习样本分为3组进行训练和检测。该方法对于受天气影响较明显的电网,能有效防止不合理预测结果的出现。对于武汉地区实际负荷的预测结果的分析表明该方法有较高的预测准确度,取得了令人满意的结果。