电力系统短期负荷预测方法研究综述

根据负荷预测基本流程,分别对数据预处理、模型选取、模型优化分别进行了总结分析。首先对传统的数据处理方法进行了概述,并简要介绍了新的数据处理方法。其次,将现有的短期负荷预测方法分为经典方法、传统方法和智能方法,综合分析了现有预测方法的应用原理,详细分析和比较预测方法的优点和不足之处,为了提高预测的精度,一些新的方法就因运而生,目的在于提高预测精度和适应相应各种运行条件。再次,总结分析了传统的预测优化模型,并简要介绍了现有的一些新的优化模型,这些新的优化模型计算结果相比于传统的模型精确度较高,分析了新优化模型的优点和不足之处。文章最后对了未来电力系统负荷预测提出了展望,在进行短期负荷预测时应该考虑电力市场、新能源、电动汽车相关因素的影响。     

A hybrid robust system considering outliers for electric load series forecasting

Electric load forecasting has become crucial to the safe operation of power grids and cost reduction in the production of power. Although numerous electric load forecasting models have been proposed, most of them are still limited by poor effectiveness in the model training and a sensitivity to outliers. The limitations of current methods may lead to extra operational costs of a power system or even disrupt its power distribution and network safety. To this end, we propose a new hybrid load-forecasting model, which is based on a robust extreme-learning machine and an improved whale optimization algorithm. Specifically, Huber loss, which is insensitive to outliers, is proposed as the objective function in extreme learning machine (ELM) training. In addition, an improved whale optimization algorithm is designed for the robust ELM training, in which a cellular automaton mechanism is used to enhance the local search. To verify our improved whale optimization algorithm, some experiments were then conducted based on seven benchmark test functions. Due to the enhancement of the local search, the improved optimizer was around 7% superior to the basic. Finally, our proposed hybrid forecasting model was validated by two real electric load datasets (Nanjing and New South Wales), and the experimental results confirmed that the proposed hybrid load-forecasting model could achieve satisfying improvements in both datasets.

     

电力系统短期负荷预测的一种模糊建模方法

预测问题在科学技术领域有着广泛的应用背景。本文介绍了一种短期负荷预测的模糊建模方法，基于三角形隶属函数和卡尔曼滤波器，辨识出电力系统的动态模型，并把辨识模型的仿真结果与系统实测值相比较，以检验模糊模型的可靠性。仿真结果表明，这种新的模糊建模方法具有较高的精度，为高度复杂的非线性电力系统模型化提供了一条新途经。此方法利用河北省某一地区具体的数据进行检验．得到了满意的结果。     

A hybrid system for forecasting 24-h power load profile for Polish electric grid

We present a method of forecasting 24-h power load profile in state-wide power system in Poland. The presented method is based on a hybrid artificial intelligence system. It employs actual temperature forecasts prepared by Interdisciplinary Centre for Mathematical and Computational Modelling of Warsaw University. The machine learning part of the system consists of 24 instances of Hierarchical Estimator: a machine learning method that divides the problem into non-exclusive subproblems with the help of fuzzy clustering and combines results of fairly simple neural networks trained on those subproblems into one, possibly more accurate solution. The presented system also includes a part responsible for dealing with days that have distinct power load patterns, such as additional state holidays. That latter part uses 30 (or 33) appropriately arranged linear regressions.The proposed approach was tested on historical load data from Poland and a few other countries. The achieved MAPE varied from 1.08% to 2.26% in dependence on the country. Such errors are among the lowest achieved by the published methods.     

Short-term electric power load forecasting using feedforward neural networks

Abstract: This paper presents the results of a study on short‐term electric power load forecasting based on feedforward neural networks. The study investigates the design components that are critical in power load forecasting, which include the selection of the inputs and outputs from the data, the formation of the training and the testing sets, and the performance of the neural network models trained to forecast power load for the next hour and the next day. The experiments are used to identify the combination of the most significant parameters that can be used to form the inputs of the neural networks in order to reduce the prediction error. The prediction error is also reduced by predicting the difference between the power load of the next hour (day) and that of the present hour (day). This is a promising alternative to the commonly used approach of predicting the actual power load. The potential of the proposed method is revealed by its comparison with two existing approaches that utilize neural networks for electric power load forecasting.     

最大Lyapunov指数短期电力负荷预测模型仿真

已有的研究工作表明,针对Lyapunov指数预报模式的预测时限受负荷吸引子最大Lyapunov指数的限制,已提出的k△t间隔采样混沌模型在短期电力负荷预测中能有效的提高负荷预测精度,增加预测时限.对k-△t间隔采样混沌模型中求解最大Lyapunov指数的方法进行了改进,对小数据量法产生的数据,引入数据间隔差方法求出最佳拟和数据段.利用VC6.0设计了仿真软件,对某实际电网进行了短期负荷预测,试验结果表明,能有效提高负荷预测精度.     

Power system load forecasting using smoothing techniques

This paper deals with short-term load forecasting problem for a power system, The load demand at any particular instant is assumed to follow a time-Beries model. A predictor is developed which identifies the coefficients of the time series in an on-line fashion. The loads at previous instants are considered as delayed variables, and a smoothing estimation technique is made use of in conjunction with the concept of the two-stage estimator to simultaneously estimate the load and related parameters. The results of an actual study made on a receiving station in Northern India are presented to illustrate the proposed predictor.     

一种自适应选择样本的用电负荷预测方法

针对传统短期负荷预测中预测模型缺乏自适应性、预测影响因素复杂难于筛选的问题,提出一种结合自适应技术的岭回归预测模型。通过引入岭回归技术,能在预测中多方面考虑各种复杂因素而不会受到因素间多重共线性的影响;引入虚拟预测日,同时设置不同权重对相似历史样本进行自适应筛选并训练,能够对每一个预测日减小预测误差。算例分析表明,应用结合自适应技术的岭回归预测方法后,实际预测误差得到显著降低。     

一种整合多种计算方法的短期负荷预测模型

介绍了一种整合神经网络、专家系统和动态聚类多种智能方法为一体的短期／超短期预测模型,综合考虑了气象、节假日等负荷影响因素。     

短期电力负荷预测的灰色-小波网络组合模型

短期电力负荷数据具有离散、无规则波动的特点,先利用灰色预测弱化其波动性,然后将负荷原始检测数据与其相对应的灰色预测数据进行重构后作为小波网络的训练样本,在此基础上建立基于灰色-小波网络组合模型的短期电力负荷预测新方法。该方法有效整合了灰色理论、小波分析和人工神经网络的优点,与传统BP网络相比,收敛速度更快,预测精度更高。仿真试验表明了该方法用于短期电力负荷预测的可行性和有效性。     

Sliding window-based LightGBM model for electric load forecasting using anomaly repair

The Journal of Supercomputing - Smart grids have attracted much attention recently for their potential to reduce power system operating and management costs. Smart grid core components include...     

A neural-network-based nonlinear metamodeling approach to financial time series forecasting

In financial time series forecasting, the problem that we often encounter is how to increase the prediction accuracy as possible using the financial data with noise. In this study, we discuss the use of supervised neural networks as a meta-learning technique to design a financial time series forecasting system to solve this problem. In this system, some data sampling techniques are first used to generate different training subsets from the original datasets. In terms of these different training subsets, different neural networks with different initial conditions or training algorithms are then trained to formulate different prediction models, i.e., base models. Subsequently, to improve the efficiency of predictions of metamodeling, the principal component analysis (PCA) technique is used as a pruning tool to generate an optimal set of base models. Finally, a neural-network-based nonlinear metamodel can be produced by learning from the selected base models, so as to improve the prediction accuracy. For illustration and verification purposes, the proposed metamodel is conducted on four typical financial time series. Empirical results obtained reveal that the proposed neural-network-based nonlinear metamodeling technique is a very promising approach to financial time series forecasting.     

Optimal training subset in a support vector regression electric load forecasting model

This paper presents an optimal training subset for support vector regression (SVR) under deregulated power, which has a distinct advantage over SVR based on the full training set, since it solves the problem of large sample memory complexity O(N²) and prevents over-fitting during unbalanced data regression. To compute the proposed optimal training subset, an approximation convexity optimization framework is constructed through coupling a penalty term for the size of the optimal training subset to the mean absolute percentage error (MAPE) for the full training set prediction. Furthermore, a special method for finding the approximate solution of the optimization goal function is introduced, which enables us to extract maximum information from the full training set and increases the overall prediction accuracy. The applicability and superiority of the presented algorithm are shown by the half-hourly electric load data (48 data points per day) experiments in New South Wales under three different sample sizes. Especially, the benefit of the developed methods for large data sets is demonstrated by the significantly less CPU running time.     

Automatic time series analysis for electric load forecasting via support vector regression

In this work, a strategy for automatic lag selection in time series analysis is proposed. The method extends the ideas of feature selection with support vector regression, a powerful machine learning tool that can identify nonlinear patterns effectively thanks to the introduction of a kernel function. The proposed approach follows a backward variable elimination procedure based on gradient descent optimisation, iteratively adjusting the widths of an anisotropic Gaussian kernel. Experiments on four electricity demand forecasting datasets demonstrate the virtues of the proposed approach in terms of predictive performance and correct identification of relevant lags and seasonal patterns, compared to well-known strategies for time series analysis designed for energy load forecasting and state-of-the-art strategies for automatic model selection.     

冰蓄冷空调负荷预测的预估校正模型

为减小冰蓄冷空调系统的运行费用,降低空调系统的能耗,更精准地预测空调冷负荷,提出一种利用小波神经网络实现冰蓄冷空调负荷预测的方法,通过直接启发式动态规划实时优化模型参数,建立冰蓄冷空调系统的预估校正模型,解决传统神经网络预测收敛慢,易陷入局部最优,精度相对低的缺点,保证整个系统的运行稳定性。实验结果表明,该方法在冰蓄冷空调负荷预测中具有较高的准确性和鲁棒性,具有良好的应用价值。     

LSTM模型在电力系统负荷预测中的应用

为解决数据随时间变化的电力系统短期负荷预测问题,本文阐述、采用和总结线性回归,普通BP神经网络,GRU神经网络,LSTM神经网络在电力系统短期负荷预测中应用的理论基础和方法,分别针对神经网络的多种预测方法进行归纳总结.LSTM即长短期记忆网络,拥有门机制,可以选择性的遗忘和记忆过去的信息,特别能记忆一个序列时间段的信息...     

Short term electric load forecasting using a neural network with fuzzy hidden neurons

Short term electric load forecasting with a neural network based on fuzzy rules is presented. In this network, fuzzy membership functions are represented using combinations of two sigmoid functions. A new scheme for augmenting the rule base is proposed. The network employs outdoor temperature forecast as one of the input quantities. The influence of imprecision in this quantity is investigated. The model is shown to be capable of also making reasonable forecasts in exceptional weekdays. Forecasting simulations were made with three different time series of electric load. In addition, the neuro-fuzzy method was tested at two electricity works, where it was used to produce forecasts with 1–24 hour lead times. The results of these one month real world tests are represented. Comparative forecasts were also made with the conventional Holt-Winters exponential smoothing method. The main result of the study is that the neuro-fuzzy method requires stationarity from the time series with respect to training data in order to give clearly better forecasts than the Holt-Winters method.     

A methodology for short-term electric load forecasting based on specialized recursive digital filters

In this paper we propose a methodology for short-term electric load forecasting, which is adaptive and based on signal processing theory. The main interest here is to construct a next day predictor for the peak and hourly load. To this end the load data are organized into profiles according to day type and temperature interval. For each load profile, we use a specialized adaptive recursive digital filter, for which parameters are estimated on-line by using a recursive algorithm. As a result, the complete forecasting system is nonlinear and the prediction is computed based on the type and on the temperature interval of the next day. The effectiveness of the proposed methodology is illustrated by a numerical example, in which we compare performance of the proposed approach to a non-specialized and a naïve predictors, by using the Mean Absolute Percentage Error (MAPE) of the forecasting errors.     

数据驱动下的综合能源系统短期多元负荷预测

精准可靠的多元负荷预测对于综合能源系统规划运行具有重要的实用价值,针对园区综合能源系统多元负荷预测问题,提出一种数据驱动下的短期多元负荷预测方法。概述园区综合能源系统多能耦合的运行特点,提出适用于多元负荷相关性分析方法。基于长短时记忆网络(longshort-term memory,LSTM)、极端梯度提升(extreme gradient boosting,XGboost)模型,采用误差倒数法对LSTM、XGboost模型预测结果进行加权组合构建短期多元负荷预测模型。采用园区实际运行数据验证了组合模型的有效性,实验结果表明,相较其它两种单一预测模型,LSTM-XGboost组合模型的预测精度更高。     

基于自适应神经网络模糊推理的负荷预测

针对中长期负荷预测,本文将模糊理论与神经网络相结合,提出了基于高木-关野自适应神经网络模糊推理系统的中长期负荷预测模型.该模型采取神经网络技术对模糊信息进行处理.使得模糊推理系统的模糊规则和模糊隶属度函数能通过学习功能自动生成,从而有效地解决了模糊理论中必须根据专家经验人为制定规则和隶属度函数的瓶颈及采用神经网络所获得的输入/输出关系不易被人接受的问题;并以湖南省安乡县经济发展指标和全社会用电量为基础数据,通过高木--关野自适应神经网络模糊推理系统对安乡县预测年份全社会用电量水平的进行预测分析.算例表明,该推理系统计算快捷.准确性高,在电网规划中长期负荷预测中有较强的实用价值.