A novel recurrent neural network forecasting model for power intelligence center

In order to accurately forecast the load of power system and enhance the stability of the power network, a novel unascertained mathematics based recurrent neural network (UMRNN) for power intelligence center (PIC) was created through three steps. First, by combining with the general project uncertain element transmission theory (GPUET), the basic definitions of stochastic, fuzzy, and grey uncertain elements were given based on the principal types of uncertain information. Second, a power dynamic alliance including four sectors: generation sector, transmission sector, distribution sector and customers was established. The key factors were amended according to the four transmission topologies of uncertain elements, thus the new factors entered the power intelligence center as the input elements. Finally, in the intelligence handing background of PIC, by performing uncertain and recursive process to the input values of network, and combining unascertained mathematics, the novel load forecasting model was built. Three different approaches were put forward to forecast an eastern regional power grid load in China. The root mean square error (ERMS) demonstrates that the forecasting accuracy of the proposed model UMRNN is 3% higher than that of BP neural network (BPNN), and 5% higher than that of autoregressive integrated moving average (ARIMA). Besides, an example also shows that the average relative error of the first quarter of 2008 forecasted by UMRNN is only 2.59%, which has high precision.

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.

Unbalance Level Regulating Algorithm in Power Distribution Networks

The paper dwells on the unified power quality indexes characterizing the phenomenon of voltage unbalance in three-phase systems. Voltage unbalance is one of the commonest occurrences in the town mains of 0.38 kV voltage. The phenomenon describes as inequality of vector magnitude of phase voltage and shearing angle between them. Causes and consequences of the voltage unbalance in distribution networks have been considered. The algorithm, which allows switching one-phase load, has been developed as one of the methods of reducing the unbalance level. The algorithm is written in the function block diagram programming language. For determining the duration and magnitude of the unbalance level it is proposed to introduce the forecasting algorithm. The necessary data for forecasting are accumulated in the course of the algorithm based on the Function Block Diagram. The algorithm example is given for transforming substation of the urban electrical power supply system. The results of the economic efficiency assessment of the algorithm implementation are shown in conclusion. The use of automatic switching of the one-phase load for explored substation allows reducing energy losses (active electric energy by 7.63%;reactive energy by 8.37%). It also allows improving supply quality to a consumer. For explored substation the average zero-sequence unbalance factor has dropped from 3.59% to 2.13%, and the negative-sequence unbalance factor has dropped from 0.61% to 0.36%.

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.

The Online Assessment of Electric Distribution Network Load Capability

To improve the security and reliability of a distribution network, several issues, such as influences of operation con-strains, real-time load margin calculation, and online security level evaluation, are with great significance. In this pa-per, a mathematical model for load capability online assessment of a distribution network is established, and a repeti-tive power flow calculation algorithm is proposed to solve the problem as well. With assessment on three levels: the entire distribution network, a sub-area of the network and a load bus, the security level of current operation mode and load transfer capability during outage are thus obtained. The results can provide guidelines for prevention control, as well as restoration control. Simulation results show that the method is simple, fast and can be applied to distribution networks belonged to any voltage level while taking into account all of the operation constraints.

Long-Term Electricity Demand Forecasting for Malaysia Using Artificial Neural Networks in the Presence of Input and Model Uncertainties

Electricity demand is also known as load in electric power system.This article presents a Long-Term Load Forecasting(LTLF)approach for Malaysia.An Artificial Neural Network(ANN)of 5-layer Multi-Layered Perceptron(MLP)structure has been designed and tested for this purpose.Uncertainties of input variables and ANN model were introduced to obtain the prediction for years 2022 to 2030.Pearson correlation was used to examine the input variables for model construction.The analysis indicates that Primary Energy Supply(PES),population,Gross Domestic Product(GDP)and temperature are strongly correlated.The forecast results by the proposed method(henceforth referred to as UQ-SNN)were compared with the results obtained by a conventional Seasonal Auto-Regressive Integrated Moving Average(SARIMA)model.The R^(2)scores for UQ-SNN and SARIMA are 0.9994 and 0.9787,respectively,indicating that UQ-SNN is more accurate in capturing the non-linearity and the underlying relationships between the input and output variables.The proposed method can be easily extended to include other input variables to increase the model complexity and is suitable for LTLF.With the available input data,UQ-SNN predicts Malaysia will consume 207.22 TWh of electricity,with standard deviation(SD)of 6.10 TWh by 2030.

Load Distribution of Base Stations in User-Centric Heterogeneous UDN

In ultra-dense networks(UDN),multiple association can be regarded as a user-centric pattern in which a user can be served by multiple base stations(BSs).The data rate and quality of service can be improved.However,BSs in user-centric paradigm are required to serve more users due to this multiple association scheme.The improvement of system performance may be limited by the improving load of BSs.In this letter,we develope an analytical framework for the load distribution of BSs in heterogeneous user-centric UDN.Based on open loop power control(OLPC),a user-centric scheme is considered in which the clustered serving BSs can provide given signal to interference plus noise ratio(SINR)for any typical user.As for any BS in different tiers,by leveraging stochastic geometry,we derive the Probability Mass Function(PMF)of the number of the served users,the Cumulative Distribution Function(CDF)of total power consumption,and the CDF bounds of downlink sum data rate.The accuracy of the theoretical analysis is validated by numerical simulations,and the effect the system parameters on the load of BSs is also presented.

Day-Ahead Probabilistic Load Flow Analysis Considering Wind Power Forecast Error Correlation

Short-term power flow analysis has a significant influence on day-ahead generation schedule. This paper proposes a time series model and prediction error distribution model of wind power output. With the consideration of wind speed and wind power output forecast error’s correlation, the probabilistic distributions of transmission line flows during tomorrow’s 96 time intervals are obtained using cumulants combined Gram-Charlier expansion method. The probability density function and cumulative distribution function of transmission lines on each time interval could provide scheduling planners with more accurate and comprehensive information. Simulation in IEEE 39-bus system demonstrates effectiveness of the proposed model and algorithm.

Modeling Simulation Technology Research for Distribution Network Planning

This paper proposes to use the power system simulation software CYME to plan, model and simulate for an actual distribution network for improving the reliability and efficiency, enhancing the efficiency and capacity, simulating the abnormal condition of distribution network, and presenting operation program of safe, reliable and having simulation record statements. The modeling simulation results show that the software module has lots of advantages including high accuracy, ideal reliability, powerful practicality in simulation and analysis of distribution network, it only need to create once model, the model can sufficiently satisfy multifarious types of simulation analysis required for the distribution network planning.

A Method for Distributed Generator Dispatch Strategy in Distribution Network

Since a load of power system changes continuously,the generation also adjusted for supply-demand balance purpose.If there exist more distributed generators in the distribution network,the dispatch strategy becomes more crucial.The possibility of having numerous controllable microgrids,diesel generator(DG)units and loads for microgrids(MGs)system requires an efficient dispatch strategy in order to balance supply demand for reducing the total cost of the integrated system.In this paper,a method for the dispatch of the distributed generator in distributed power systems has been proposed.The dispatch strategy is such that it keeps a flat voltage profile,reduces the network losses,increases the maximum loading and voltage security margin of the system.The procedure is based on the analysis of continuous power flow.The method is executed on a 34-bus test system.The MATLAB based PSAT packages are used for simulation purpose.

A Clustering-tree Topology Control Based on the Energy Forecast for Heterogeneous Wireless Sensor Networks

How to design an energy-efficient algorithm to maximize the network lifetime in complicated scenarios is a critical problem for heterogeneous wireless sensor networks (HWSN). In this paper, a clustering-tree topology control algorithm based on the energy forecast (CTEF) is proposed for saving energy and ensuring network load balancing, while considering the link quality, packet loss rate, etc. In CTEF, the average energy of the network is accurately predicted per round (the lifetime of the network is denoted by rounds) in terms of the difference between the ideal and actual average residual energy using central limit theorem and normal distribution mechanism, simultaneously. On this basis, cluster heads are selected by cost function (including the energy, link quality and packet loss rate) and their distance. The non-cluster heads are determined to join the cluster through the energy, distance and link quality. Furthermore, several non-cluster heads in each cluster are chosen as the relay nodes for transmitting data through multi-hop communication to decrease the load of each cluster-head and prolong the lifetime of the network. The simulation results show the efficiency of CTEF. Compared with low-energy adaptive clustering hierarchy (LEACH), energy dissipation forecast and clustering management (EDFCM) and efficient and dynamic clustering scheme (EDCS) protocols, CTEF has longer network lifetime and receives more data packets at base station. © 2014 Chinese Association of Automation.

An Optimized Algorithm for Renewable Energy Forecasting Based on Machine Learning

The large-scale application of renewable energy power generation technology brings new challenges to the operation of traditional power grids andenergy management on the load side. Microgrid can effectively solve this problemby using its regulation and flexibility, and is considered to be an ideal platform.The traditional method of computing total transfer capability is difficult due tothe central integration of wind farms. As a result, the differential evolutionextreme learning machine is offered as a data mining approach for extractingoperating rules for the total transfer capability of tie-lines in wind-integratedpower systems. K-medoids clustering under the two-dimensional “wind power-load consumption” feature space is used to define representative operational scenarios initially. Then, using stochastic sampling and repetitive power flow, aknowledge base for total transfer capability operating rule mining is created.Then, a novel method is used to filter redundant characteristics and find featuresthat are closely associated to the total transfer capability in order to decrease theultra-high dimensionality of operational features. Finally, by feeding the trainingdata into the proposed algorithm, the total transfer capability operation rules arederived from the knowledge base. It can be seen that, the proposed algorithmcan optimize the system performance with good accuracy and generality, according to numerical data.

Very Short-Term Forecasting of Distributed PV Power Using GSTANN

Photovoltaic(PV)power forecasting is essential for secure operation of a power system.Effective prediction of PV power can improve new energy consumption capacity,help power system planning,promote development of smart grids,and ultimately support construction of smart energy cities.However,different from centralized PV power forecasts,three critical challenges are encountered in distributed PV power forecasting:1)lack of on-site meteorological observation,2)leveraging extraneous data to enhance forecasting performance,3)spatial-temporal modelling methods of meteorological information around the distributed PV stations.To address these issues,we propose a Graph Spatial-Temporal Attention Neural Network(GSTANN)to predict the very short-term power of distributed PV.First,we use satellite remote sensing data covering a specific geographical area to supplement meteorological information for all PV stations.Then,we apply the graph convolution block to model the non-Euclidean local and global spatial dependence and design an attention mechanism to simultaneously derive temporal and spatial correlations.Subsequently,we propose a data fusion module to solve the time misalignment between satellite remote sensing data and surrounding measured on-site data and design a power approximation block to map the conversion from solar irradiance to PV power.Experiments conducted with real-world case study datasets demonstrate that the prediction performance of GSTANN outperforms five state-of-the-art baselines.

Prospects of Shanghai City Network in 21~st Century

According to the population, area and economy development of Shanghai City, this paper introduces the load forecast of the city and points out that the development of urban power network should adapt the development of its economy. In this paper, the developing targets of Shanghai power network are also presented.

Coordinated control of coastal multi-source multi-load system with desalination load: a review

Traditional seawater desalination requires high amounts of energy, with correspondingly high costs and limited benefits, hindering wider applications of the process. To further improve the comprehensive economic benefits of seawater desalination, the desalination load can be combined with renewable energy sources such as solar energy, wind energy, and ocean energy or with the power grid to ensure its effective regulation. Utilizing energy internet(EI) technology, energy balance demand of the regional power grid, and coordinated control between coastal multi-source multi-load and regional distribution network with desalination load is reviewed herein. Several key technologies, including coordinated control of coastal multi-source multi-load system with seawater desalination load, flexible interaction between seawater desalination and regional distribution network, and combined control of coastal multi-source multi-load storage system with seawater desalination load, are discussed in detail. Adoption of the flexible interaction between seawater desalination and regional distribution networks is beneficial for solving water resource problems, improving the ability to dissipate distributed renewable energy, balancing and increasing grid loads, improving the safety and economy of coastal power grids, and achieving coordinated and comprehensive application of power grids, renewable energy sources, and coastal loads.

基于CNN-SAEDN-Res的短期电力负荷预测方法

基于深度学习的序列模型难以处理混有非时序因素的负荷数据,这导致预测精度不足。提出一种基于卷积神经网络(CNN)、自注意力编码解码网络(SAEDN)和残差优化(Res)的短期电力负荷预测方法。特征提取模块由二维卷积神经网络组成,用于挖掘数据间的局部相关性,获取高维特征。初始负荷预测模块由自注意力编码解码网络和前馈神经网络构成,利用自注意力机制对高维特征进行自注意力编码,获取数据间的全局相关性,从而模型能根据数据间的耦合关系保留混有非时序因素数据中的重要信息,通过解码模块进行自注意力解码,并利用前馈神经网络回归初始负荷。引入残差机制构建负荷优化模块,生成负荷残差,优化初始负荷。算例结果表明,所提方法在预测精度和预测稳定性方面具有优势。

基于CNN-BiGRU-Attention的短期电力负荷预测

针对目前电力负荷数据随机性强,影响因素复杂,传统单一预测模型精度低的问题,结合卷积神经网络(Convolutional neural network,CNN)、双向门控循环单元(Bi-directional gated recurrent unit,BiGRU)以及注意力机制(Attention)在短期电力负荷预测上的不同优点,提出一种基于CNN-BiGRU-Attention的混合预测模型。该方法首先通过CNN对历史负荷和气象数据进行初步特征提取,然后利用BiGRU进一步挖掘特征数据间时序关联,再引入注意力机制,对BiGRU输出状态给与不同权重,强化关键特征,最后完成负荷预测。试验结果表明,该模型的平均绝对百分比误差(Mean absolute percentage error,MAPE)、均方根误差(Root mean square error,RMSE)、判定系数(R-square,R~2)分别为0.167%、0.057%、0.993,三项指标明显优于其他模型,具有更高的预测精度和稳定性,验证了模型在短期负荷预测中的优势。

集中式馈线自动化配电网供电可靠性评估

计及集中式馈线自动化的配电网可靠性评估尚存在较多研究空白,且多数研究仅计及故障停电的影响,在考虑预安排检修容量约束的情况下,计及负荷转供影响,结合馈线自动化的类型及运行逻辑,依据馈线自动化相关技术指标,对恢复供电过程中出现的负荷点进行详细分类,推导出不同类型负荷期望恢复供电时间和配电网供电可靠性指标计算公式。结合算例进行分析可知,不同终端配置下馈线系统平均停电持续时间SAIDI可减少0.95~1.08 h/(用户·a),说明了优化终端配置可有效提高配电网供电可靠性,证明了所提评估方法的准确性和实用性,并比较了不同终端配置对可靠性的影响。

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。

城市中压配电网雪花格式网架结构初探

为适应新型电力系统建设需求,提出一种适合国情的雪花格式网架结构。首先,总结国内外典型城市中压配电网结构的特征与优缺点;然后,结合天津已有网架结构,提出雪花格式网架结构及其构建方法;其次,分析测算雪花网结构的负荷转移能力、可靠性与效率效益水平;最后,从结构形式、适合场景等方面给出雪花网结构与花瓣结构等的综合对比情况。结果表明,雪花格式网架结构具有一定综合比较优势,可为中压配电网远景目标网架规划提供指导。