共查询到20条相似文献,搜索用时 203 毫秒
1.
模糊聚类分析和代数算法结合的短期负荷预测 总被引:2,自引:0,他引:2
为了提高短期负荷预测速度和精度,提出了将模糊聚类分析和神经网络代数算法相结合的短期负荷预测方法.综合考虑天气、日类型、历史负荷等对未来负荷变化的影响,通过模糊聚类分析选取学习样本,找出同预测目相符的预测类别,采用神经网络代数算法训练样本,对24小时负荷(24点)每点建立一个预测模型.该方法充分发挥了神经网络和模糊理论处... 相似文献
2.
3.
《电网技术》2021,45(11):4532-4539
短期电力负荷预测能准确评估地区整体电力负荷变化情况,为电力系统运行决策提供准确参考。电力负荷参数受多维因素影响,为充分挖掘电力负荷数据中的时序特征,提升电力负荷预测精度,该文提出一种基于特征筛选的卷积神经网络—双向长短期记忆网络组合模型的短期电力负荷预测方法。以真实电力负荷数据作为数据集,通过对多维输入参数的优化筛选,选取高相关性特征向量作为输入,构建预测模型。通过与添加注意力机制的组合模型对比验证了输入参数优化分析的可行性和优越性。最后利用实际算例将该方法与利用自动化模型构建工具构建的梯度增强基线模型及常用预测模型相比,该方法构建的组合模型可以提升多维电力负荷数据的短期预测精度。 相似文献
4.
短期电力负荷预测是电力部门进行电网规划和运行调度的重要工作之一,针对负荷数据的时序性特征,为提升电力负荷预测精度,建立了一种基于多分支门控残差卷积神经网络(residualgatedconvolutional neural network,RGCNN)的短期电力负荷预测模型。该模型首先采用多分支门控残差卷积神经网络对历史负荷的周周期特征、日周期特征、近邻特征进行深度特征提取;其次为增加模型的非线性拟合能力,采用注意力机制对权重进一步合理分配;最后通过归一化指数函数计算后输出负荷预测结果。使用2016年某电力竞赛数据进行实验,通过与4种常用模型对比,该模型预测结果的平均绝对百分误差(MAPE)评价指标下降了0.02%~0.70%,验证了该模型提高负荷预测精度的有效性。 相似文献
5.
为了应对电动汽车规模化发展之后庞大的充电站负荷对电力调度配送等环节带来的影响,依据当前北京奥运快换式公交充电站的相关实测数据,对快换式公交充电站负荷特征及其影响因素进行分析,提出一种基于模糊聚类分析与BP神经网络相结合的快换站短期负荷预测方法。利用该方法对四组不同的测试日进行预测实例分析,并与单一BP网络模型的预测效果进行比较。统计结果表明,基于模糊聚类分析与BP神经网络相结合的预测方法具有较高的预测精度,满足一定的应用要求,适用于快换式公交充电站短期负荷预测工作。 相似文献
6.
短期电力负荷预测作为电力系统运行规划的重要依据,对电力系统的安全经济运行有重要意义。提出一种长期和短期时间序列网络(LSTNet)模型对配电台区的短期负荷变化进行预测。该模型用卷积神经网络(CNN)提取负荷数据间的局部依赖关系,用长短时记忆(LSTM)神经网络提取负荷数据长期变化趋势,再融合传统自回归模型解决神经网络对负荷数据极端值的不敏感问题,最后将某一配电台区的电力负荷数据用于网络的训练和预测过程中。通过仿真实验案例发现,相较于以往LSTM、双向长短时记忆神经网络(Bi-LSTM)和CNN-LSTM的预测模型,LSTNet模型在短期负荷预测方面更具优势、预测精度更高。 相似文献
7.
8.
9.
为提高超短期负荷预测精度,特别是负荷曲线在拐点处的精度,在模糊聚类分析的基础上提出了一种选取局部相似日的改进模型。通过该模型选取局部相似日,并结合RBF网络提出一种新的预测超短期负荷方法。采用该方法建立2个预测模型,分别用于预测下个时刻和下一个小时段的数据。将该方法与灰色关联分析预测方法进行比较,发现该方法在预测精度上具有显著优势,证明新的预测超短期负荷方法有较高的可靠性与有效性。仿真结果表明,新的预测超短期负荷方法在工作日或休息日负荷曲线拐点处的预测上,均具有较高精度。 相似文献
10.
《电力学报》2019,(6)
短期电力负荷预测为电力规划的科学性、电力调度的合理性、电力运行的经济性提供了有效的指导,近年来,神经网络在预测短期电力负荷中得到了广泛应用。针对BP神经网络预测方法的自主学习能力强但预测结果容易陷入局部最小值的缺点,首先建立了三种短期电力负荷预测模型,分别是基于BP神经网络的预测模型,基于自适应网格法的多目标粒子群优化算法(MOPSO)优化BP神经网络的MOPSO-BP预测模型,以及基于拥挤距离法改进的MOPSO优化BP神经网络的改进MOPSO-BP预测模型;再利用Matlab软件进行仿真对比,研究哪种模型预测电力负荷的精度更高。结果显示,基于拥挤距离法的改进MOPSO-BP模型预测结果比其他两个预测模型的预测结果更接近真实负荷值,这表明利用改进MOPSO-BP模型对电力负荷预测的效果最好,可以为现场短期电力负荷预测提供理论依据与借鉴。 相似文献
11.
针对传统数据挖掘算法(神经网络和支持向量机)进行短期负荷预测容易陷入局部最优,模型难以确定等问题,提出一种模糊聚类技术与随机森林回归算法结合的短期负荷预测方法。基于模糊聚类技术选取相似日的方法,考虑负荷的周期性变化特征,利用样本输入进行样本聚类,选取同类数据作训练样本,建立随机森林负荷预测模型。实例中负荷数据采用安徽省某地的历史负荷,用上述方法对该地区的日24小时负荷进行预测,并与传统的支持向量机和BP神经网络方法进行比较,验证了该方法的有效性。 相似文献
12.
13.
《International Journal of Electrical Power & Energy Systems》2013,44(1):99-108
Power load forecasting is an essential tool for energy management systems. Accurate load forecasting supports power companies to make unit commitment decisions and schedule maintenance plans appropriately. In addition to minimizing the power generation costs, it is also important for the reliability of energy systems. This research study presents the implementation of a novel fuzzy wavelet neural network model on an hourly basis, and validates its performance on the prediction of electricity consumption of the power system of the Greek Island of Crete. In the proposed framework, a multiplication wavelet neural network has replaced the classic linear model, which usually appears in the consequent part of a neurofuzzy scheme, while subtractive clustering with the aid of the Expectation–Maximization algorithm is being utilized in the definition of fuzzy rules. The results related to the minimum and maximum load using metered data obtained from the power system of the Greek Island of Crete indicate that the proposed forecasting model provides significantly better forecasts, compared to conventional neural networks models applied on the same dataset. 相似文献
14.
15.
16.
Kwang-Ho Kim Hyoung-Sun Youn Yong-Cheol Kang 《Power Systems, IEEE Transactions on》2000,15(2):559-565
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% 相似文献
17.
Kyung-Bin Song Young-Sik Baek Dug Hun Hong Jang G. 《Power Systems, IEEE Transactions on》2005,20(1):96-101
Average load forecasting errors for the holidays are much higher than those for weekdays. So far, many studies on the short-term load forecasting have been made to improve the prediction accuracy using various methods such as deterministic, stochastic, artificial neural net (ANN) and neural network-fuzzy methods. In order to reduce the load forecasting error of the 24 hourly loads for the holidays, the concept of fuzzy regression analysis is employed in the short-term load forecasting problem. According to the historical load data, the same type of holiday showed a similar trend of load profile as in previous years. The fuzzy linear regression model is made from the load data of the previous three years and the coefficients of the model are found by solving the mixed linear programming problem. The proposed algorithm shows good accuracy, and the average maximum percentage error is 3.57% in the load forecasting of the holidays for the years of 1996-1997. 相似文献
18.
This paper presents a new time series modeling for short term load forecasting, which can model the valuable experiences of the expert operators. This approach can accurately forecast the hourly loads of weekdays, as well as, of weekends and public holidays. It is shown that the proposed method can provide more accurate results than the conventional techniques, such as artificial neural networks or Box-Jenkins models. In addition to hourly loads, daily peak load is an important problem for dispatching centers of a power network. Most of the common load forecasting approaches do not consider this problem. It is shown that the proposed method can exactly forecast the daily peak load of a power system. Obtained results from extensive testing on the Iran's power system network confirm the validity of the developed approach 相似文献
19.
提出一种基于改进相似度的模糊聚类算法的光伏阵列短期功率预测方法,通过通径分析得到气象因子对光伏阵列日发电功率的影响权重。根据各个因子的权重自定义综合了加权相似系数和加权距离系数的统计量-相似度,建立模糊相似矩阵将历史日样本划分为若干类。然后通过分类识别获得与预测日最相似的一类历史日样本集,将其与预测日的气象因素作为预测模型的输入样本建立BP神经网络发电预测模型,并利用差分进化算法对构建的BP神经网络的参数进行了全局寻优。以实际数据对所提模型进行了验证,并与传统的基于相似日选取的光伏功率预测模型进行了对比,结果表明该模型具有更高的预测精度,有利于光伏发电系统并网运行和电网安全经济调度。 相似文献