Theory Study and Application of the BP-ANN Method for Power Grid Short-Term Load Forecasting

Aiming at the low accuracy problem of power system short-term load forecasting by traditional methods, a back-propagation artificial neural network （BP-ANN） based method for short-term load forecasting is presented in this paper. The forecast points are related to prophase adjacent data as well as the periodical long-term historical load data. Then the short-term load forecasting model of Shanxi Power Grid （China） based on BP-ANN method and correlation analysis is established. The simulation model matches well with practical power system load, indicating the BP-ANN method is simple and with higher precision and practicality.

Investigating Periodic Dependencies to Improve Short-Term Load Forecasting

With a further increase in energy flexibility for customers,short-term load forecasting is essential to provide benchmarks for economic dispatch and real-time alerts in power grids.The electrical load series exhibit periodic patterns and share high associations with metrological data.However,current studies have merely focused on point-wise models and failed to sufficiently investigate the periodic patterns of load series,which hinders the further improvement of short-term load forecasting accuracy.Therefore,this paper improved Autoformer to extract the periodic patterns of load series and learn a representative feature from deep decomposition and reconstruction.In addition,a novel multi-factor attention mechanism was proposed to handle multi-source metrological and numerical weather prediction data and thus correct the forecasted electrical load.The paper also compared the proposed model with various competitive models.As the experimental results reveal,the proposed model outperforms the benchmark models and maintains stability on various types of load consumers.

Short-Term Power Load Forecasting with Hybrid TPA-BiLSTM Prediction Model Based on CSSA

Since the existing prediction methods have encountered difficulties in processing themultiple influencing factors in short-term power load forecasting,we propose a bidirectional long short-term memory(BiLSTM)neural network model based on the temporal pattern attention(TPA)mechanism.Firstly,based on the grey relational analysis,datasets similar to forecast day are obtained.Secondly,thebidirectional LSTM layermodels the data of thehistorical load,temperature,humidity,and date-type and extracts complex relationships between data from the hidden row vectors obtained by the BiLSTM network,so that the influencing factors(with different characteristics)can select relevant information from different time steps to reduce the prediction error of the model.Simultaneously,the complex and nonlinear dependencies between time steps and sequences are extracted by the TPA mechanism,so the attention weight vector is constructed for the hidden layer output of BiLSTM and the relevant variables at different time steps are weighted to influence the input.Finally,the chaotic sparrow search algorithm(CSSA)is used to optimize the hyperparameter selection of the model.The short-term power load forecasting on different data sets shows that the average absolute errors of short-termpower load forecasting based on our method are 0.876 and 4.238,respectively,which is lower than other forecastingmethods,demonstrating the accuracy and stability of our model.

A Levenberg–Marquardt Based Neural Network for Short-Term Load Forecasting

Short-term load forecasting (STLF) is part and parcel of theefficient working of power grid stations. Accurate forecasts help to detect thefault and enhance grid reliability for organizing sufficient energy transactions.STLF ranges from an hour ahead prediction to a day ahead prediction. Variouselectric load forecasting methods have been used in literature for electricitygeneration planning to meet future load demand. A perfect balance regardinggeneration and utilization is still lacking to avoid extra generation and misusageof electric load. Therefore, this paper utilizes Levenberg–Marquardt(LM) based Artificial Neural Network (ANN) technique to forecast theshort-term electricity load for smart grids in a much better, more precise,and more accurate manner. For proper load forecasting, we take the mostcritical weather parameters along with historical load data in the form of timeseries grouped into seasons, i.e., winter and summer. Further, the presentedmodel deals with each season’s load data by splitting it into weekdays andweekends. The historical load data of three years have been used to forecastweek-ahead and day-ahead load demand after every thirty minutes makingload forecast for a very short period. The proposed model is optimized usingthe Levenberg-Marquardt backpropagation algorithm to achieve results withcomparable statistics. Mean Absolute Percent Error (MAPE), Root MeanSquared Error (RMSE), R2, and R are used to evaluate the model. Comparedwith other recent machine learning-based mechanisms, our model presentsthe best experimental results with MAPE and R2 scores of 1.3 and 0.99,respectively. The results prove that the proposed LM-based ANN modelperforms much better in accuracy and has the lowest error rates as comparedto existing work.

Grid Power Optimization Based on Adapting Load Forecasting and Weather Forecasting for System Which Involves Wind Power Systems

This paper describes the performance, generated power flow distribution and redistribution for each power plant on the grid based on adapting load and weather forecasting data. Both load forecasting and weather forecasting are used for collecting predicting data which are required for optimizing the performance of the grid. The stability of each power systems on the grid highly affected by load varying, and with the presence of the wind power systems on the grid, the grid will be more exposed to lowering its performance and increase the instability to other power systems on the gird. This is because of the intermittence behavior of the generated power from wind turbines as they depend on the wind speed which is varying all the time. However, with a good prediction of the wind speed, a close to the actual power of the wind can be determined. Furthermore, with knowing the load characteristics in advance, the new load curve can be determined after being subtracted from the wind power. Thus, with having the knowledge of the new load curve, and data that collected from SACADA system of the status of all power plants, the power optimization, load distribution and redistribution of the power flows between power plants can be successfully achieved. That is, the improvement of performance, more reliable, and more stable power grid.

Short-Term Load Forecasting Using Radial Basis Function Neural Network

An accurate short-term forecasting method for load of electric power system can help the electric power system’s operator to reduce the risk of unreliability of electricity supply. This paper proposed a radial basis function (RBF) neural network method to forecast the short-term load of electric power system. To demonstrate the effectiveness of the proposed method, the method is tested on the practical load data information of the Tai power system. The good agreements between the realistic values and forecasting values are obtained;the numerical results show that the proposed forecasting method is accurate and reliable.

Overview of the Global Electricity System in Oman Considering Energy Demand Model Forecast

Lately,in modern smart power grids,energy demand for accurate forecast of electricity is gaining attention,with increased interest of research.This is due to the fact that a good energy demand forecast would lead to proper responses for electricity demand.In addition,proper energy demand forecast would ensure efficient planning of the electricity industry and is critical in the scheduling of the power grid capacity and management of the entire power network.As most power systems are been deregulated and with the rapid introduction and development of smart-metering technologies in Oman,new opportunities may arise considering the efficiency and reliability of the power system;like price-based demand response programs.These programs could either be a large scale for household,commercial or industrial users.However,excellent demand forecasting models are crucial for the deployment of these smart metering in the power grid based on good knowledge of the electricity market structure.Consequently,in this paper,an overview of the Oman regulatory regime,financial mechanism,price control,and distribution system security standard were presented.More so,the energy demand forecast in Oman was analysed,using the econometric model to forecasts its energy peak demand.The energy econometric analysis in this study describes the relationship between the growth of historical electricity consumption and macro-economic parameters(by region,and by tariff),considering a case study of Mazoon Electricity Distribution Company(MZEC),which is one of the major power distribution companies in Oman,for effective energy demand in the power grid.

基于误差幅空特性分析的空间负荷预测误差评价方法

对空间负荷预测误差进行有效评价是客观认识预测结果,指导预测结果合理应用的前提。然而,现有空间负荷预测误差评价的研究存在对误差的空间分布不考虑或考虑不充分导致评价不准确的问题。为此,提出一种基于误差幅空特性分析的空间负荷预测误差评价方法。首先,从空间负荷预测误差幅值大小和空间分布对电网规划影响的角度出发,对误差的幅空特性进行详细分析;其次,利用运输问题的数学模型来表征正负误差的幅空抵消特性,使用各空间邻近度–幅值误差值曲线与x轴围成面积之和来表征剩余未抵消误差的幅空叠加特性;然后,分别通过伏格尔法和各梯形面积累加公式来计算正负误差的幅空抵消影响值和剩余未抵消误差的幅空叠加影响值,并在此基础上构建空间负荷预测误差评价指标;最后,基于误差对电网规划的实际影响给出对误差评价指标性能的检验方法。算例分析表明,与传统方法相比,该文所提误差评价方法从幅值和空间两个维度实现了对空间负荷预测误差更为全面的评估,与误差对电网规划影响的实际情况贴近度更高。

园区受端新型电力系统电力电量再平衡方法

我国工业园区电能消耗占据了较高的比例,针对依托新型电力系统促进工业园区绿色低碳发展的需要,提出了一种面向工业园区受端新型电力系统的电力电量再平衡方法。首先,开展电力和电量需求预测并进行电力电量初平衡;然后,基于受端源网荷储协同作用并充分考虑园区节能、电能替代、各类分布式电源、储能和需求响应能力的作用进行电力电量再平衡,由此确定园区年度外调电和区内自产电的比例,进一步建立包含低碳效应和电力系统规模变化在内的量化指标评价体系,对电力电量再平衡带来的变配电容量缩减规模和降碳效用进行评价。以我国南方某工业园区新型电力系统的电力电量再平衡为例对以上方法进行了验证,结果表明:该园区2030年变配电规划容量可缩减10.1%,用电综合碳排放因子由0.60 kg/(kW·h)降至0.54 kg/(kW·h);2060年变配电规划容量可缩减9.57%,电能替代实现减碳5.85万t/a,可为受端新型电力系统的电力电量平衡提供有力的理论支撑。

基于深度学习的电网短期负荷预测

针对微电网短期负荷预测精度不够的问题,论文提出了一种基于双向长短时记忆(bidirectional long short-term memory,Bi-LSTM)深度学习的负荷预测方法。将影响家庭和商业负荷分布形成的参数为输入变量,以微电网的家庭和商业总负荷分布为目标,利用输入变量对Bi-STM网络进行训练,通过识别微电网的消费模式,对微电网负荷进行时预测。利用相关系数(R)、均方误差(MSE)和均方根误差(RMSE)等性能评价指标对预测结果进行分析。结果表明,Bi-LSTM方法具有较高的相关系数。

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。

基于支持向量机的网格化电网负荷预测算法设计

针对电网负荷预测算法预测能力较差、效率偏低的问题,文中提出了一种PCA-PSO-SVM算法。其在经典粒子群算法的基础上引入主元分析法,使模型具有降低数据维度及算法冗余度的特性。同时通过改进的PCA-PSO算法对SVM模型的内置参数进行最优选取,从而使改进后的SVM模型具有最佳的分类性能。在实验测试中,采用PCA算法选取了91%贡献度内的6项数据特征进行样本数据训练。结果表明,相较于其他对比算法,该文算法预测结果的RMSE、MAE与MAPE误差值均为最小,证明其可对网格化电网负荷加以预测。此外,该算法还能提升传统算法的准确度,为电力负荷分配提供有力支持。

云边协同背景下基于融合RF算法的电网数据资产综合处理技术

针对现有大多数方法难以充分挖掘出电网数据潜在价值的问题,提出了一种云边协同背景下基于随机森林算法结合BP神经网络的电网数据资产综合处理技术。该技术在靠近电网数据源一侧部署边缘计算节点,以构建云边协同环境下的电网数字化资产管理系统。利用随机森林算法设计分类器完成电网数据类型的划分,并将各类型数据输入至BP神经网络中进行学习,通过不断地迭代优化输出相应的综合处理结果。基于Python平台进行的实验分析结果表明,所提技术的分类准确率均超过了90%,能够有效提升电网数据资产的处理效率。

多模态马尔科夫决策泛在电力物联网大数据智能挖掘

针对泛在电力物联网结构复杂、数据多样且不确定的问题,提出了一种基于多模态马尔科夫决策的泛在电力物联网大数据智能挖掘方法。该方法构建了一种基于最大熵的马尔科夫决策算法,对电力泛在物联网进行故障诊断和负荷预测,具有标记样本需求量小、置信度高的特点。通过结合电气量信息及开关量信息来提取电网数据特征,从而充分利用多模态数据样本。仿真分析与实验结果表明,相比于传统方法,所提方法能够有效识别出包括信息畸变在内的电网故障,提升电网故障诊断的准确率和电网负荷预测的精度。

可解释机器学习在电网调控领域中的应用

数据驱动的机器学习是新一代人工智能的核心技术,尽管该技术已经在电网调控领域取得了显著成果,但是可解释性差,阻碍了其在对安全可靠性要求极高的电网调控领域的实际工程应用。因此,提升电网调控领域机器学习技术的可解释性对提高其实用性至关重要。首先,从电网调度运行人员的角度,分析了机器学习可解释性的定义、目标和意义;然后,提出考虑可解释性的机器学习在电网调控领域应用的流程,介绍了典型的机器学习解释技术及其在电力系统预测和稳定评估场景的应用,通过实际案例验证了该技术在电网调控领域应用的可行性;最后,对电网调控领域机器学习可解释技术面临的挑战进行了分析和展望。通过该研究,为解决电网调控领域机器学习应用的不可解释问题提供思路和参考,进一步促进机器学习技术在该领域的实际工程应用。

基于改进图时间卷积网络的农村地区电动汽车充电负荷预测及其对农网的影响

在新能源汽车下乡政策的有力引导下,电动汽车在农村地区的销量快速增长,然而农村电网地域分布广、供电线路长,充电负荷相对分散且难以预测。为此,提出了基于改进图时间卷积网络的农村地区电动汽车充电负荷预测模型。首先,基于图卷积网络构建农村电网图结构矩阵,以表征用户充电特征的空间信息并降低输入数据的维度。其次,引入时间卷积网络感知充电数据的时序信息,挖掘影响负荷预测的时序特征。然后,提出基于注意力机制的改进图时间卷积网络算法进行充电需求预测,对不同特征进行权重分配,提升模型对时空信息的融合学习能力。最后,基于算例结果验证所提方法在农村地区电动汽车充电负荷预测上的有效性,并进一步分析了不同电动汽车渗透率下充电负荷对农村电网的影响。

基于TVF-EMD-SVM-GRU混合模型的短期电网负荷预测

短期电网负荷表现出非规律的波动性和非稳定的周期性,对其进行准确预测是一项挑战。采用时变滤波的经验模态分解,对一维观测信号进行分解,得到具有不同尺度特征的固有模态函数。通过随机重构构造一个新的观测值,形成二维矩阵。引入支持向量机来替代门控循环单元最终输出层中的归一化指数函数,并将交叉熵函数替换为基于边缘的函数,从而进行基于混合模型的短期电网负荷预测。试验结果表明,与大间隔最近邻算法、卷积神经网络以及融合门控循环单元的支持向量机相比,混合模型的计算成本虽然稍高,但均方根误差和平均绝对误差都是最小的。因此,混合模型具有最好的预测性能,可用于短期电网负荷预测。

基于粒子群算法的电力负荷调度决策方法

新能源并网条件下,电力负荷调度效率低下,为此,基于粒子群算法设计电力负荷调度决策方法。结合粒子群算法建立电力负荷预测模型,在惯性权重因子的基础上补全所有缺失数据,结合不同的单元模型,设定激活函数,获取电力负荷的预测值,综合用电负荷和电力系统运行成本,制定电力负荷的决策变量,设置目标函数与约束条件,得到电力负荷调度决策结果。实验结果表明,该方法结合实际的电力负荷对火力发电以及蓄电池进行优化调度,运行成本由原本的13 618元降低至10 615元,可见该调度决策方法有效降低电力系统运行成本。

含分布式电源的智能电网负荷预测研究

随着能源结构的转变和环保要求的提高,分布式电源作为一种清洁、高效的能源,逐渐受到关注。分布式电源具有分散布局、灵活接入及高效利用等特点,能够与智能电网紧密结合,提高电力系统的供电质量和可靠性。文章主要研究基于分布式电源的智能电网负荷预测模型,通过介绍分布式电源的概念及其在智能电网中的应用,详细阐述基于分布式电源的智能电网负荷预测模型的构建过程,包括数据采集与预处理、特征提取与选择以及模型构建与优化等。实验结果表明,所提的负荷预测模型具有较高的预测精度和稳定性,能够为智能电网的调度和管理提供有力支持。

基于分布式光伏典型日曲线的负荷预测方法研究

分布式光伏电源大规模接入电网后,在实际运行的过程中很大程度上增强了电网系统的电源支撑,但也在一定程度上增加了电网负荷预测的难度。在电网实际运行的过程中,负荷预测是保障电力系统安全稳定经济运行极为重要的一项内容,因此需不断改进负荷预测工作,提升电网调度运行水平。分布式光伏在实际运行过程中,电力资源数据的采集具有一定的难度,因此需对分布式光伏典型日曲线的负荷预测方法进行探究分析,以此提升整体负荷预测的有效性及精准度。