改进KNN的时间序列分析方法

近年来,随着数据挖掘和机器学习的兴起,基于时间序列分析方法的研究愈加丰富.作为机器学习的经典方法,KNN(K-Nearest Neighbor)因其简单、准确度高等特性被广泛应用于时间序列分析的各个领域.然而,使用原始的KNN回归方法预测时间序列具有一定的局限性,直接使用欧氏距离作为相似度度量方法的预测效果并不理想,无法适应具有整体趋势变化的时间序列的预测场景.文中提出一种拟合时间序列趋势的KNN算法TSTF-KNN(Time Series Trend Fitting KNN)算法,该方法通过对每个时刻的特征序列进行归一化处理,改进了KNN相似度度量的效果,使之可以更有效地搜索相似的特征序列.由于序列预测前进行了归一化,文中通过为预测结果添加误差项来还原序列特征,使之可以有效地预测结果.为了验证方法的有效性,从kaggle公开数据集中选取了4个数据集,并通过对这4个数据集分别进行预处理获得5个时间序列以供实验.通过使用TSTF-KNN、KNN、单层LSTM(Long Short-Term Memory)神经网络和ANN(Artificial Neural Network)在处理后的5个时间序列上进行预测实验,分析预测结果,并对比均方误差(Mean Square Error,MSE),验证了该方法的有效性.实验结果表明,该方法能有效提高KNN回归方法对时间序列预测的准确度和稳定性,使之可以更好地适应具有整体趋势变化的时间序列的预测场景.     

基于混合人工神经网络的电力市场短期电价研究与分析

由于电力市场价格的不确定性,供需侧管理在电力市场中遇到了许多困难。电力供应商可以通过了解电力市场价格变化的信息,在短期预测其合理报价时获得更多优势。因此,近年来,电力市场对价格预测的研究变得更加重要。根据预测框架,预测技术可分为三类,即统计模型、时间序列方法和基于人工智能(AI)的方法。因此,为解决上述问题,提出一种基于混合人工神经网络的短期电价预测混合方法。同时,本研究开发了一种基于互信息(MI)和神经网络(NN)相结合的特征选择技术,用于选择输入变量子集,这些子集对电价预测具有重要影响。通过结合人工协同搜索算法(ACS)和人工神经网络(ANN)进行,进一步提高了预测的精度。通过比较所提出的混合预测方法与混合SVM和混合ANN方法的相关性和精度,并通过粒子群优化(PSO)CSA算法对混合SVM和混合ANN方法的参数进行了优化。开发的ANN-ACS模型在电力市场具有鲁棒性。在电价预测的情况下,它提供了比其他AI方法更高的预测精度和简单性,在冬季、春季、夏季和秋季的MAPE值分别为4.58%、1.2%、2.62%和3.79%。     

基于自适应动态规划的系统边际电价预测

针对目前电价预测算法的局限性,提出一种基于自适应动态规划方法的自学习、自适应智能算法。按照Bellman最优化基本原理,使用Agent逐步与环境的交互作用来寻求预测电价和实际电价的误差最小值,得到系统边际电价的最优解。采用美国加州电力市场的数据进行电价预测仿真。与常规方法相比,该方法的拟合精度和平均绝对百分误差均有很大提高。     

基于大数据分析技术的电力市场短期电价预测

为了提升电力市场短期电价预测精度，提出大数据分析的电力市场短期电价预测模型。首先收集电力市场短期电价历史数据，然后采用大数据分析中的最小二乘支持向量机算法对电力市场短期电价变化趋势进行拟合和分析，建立最优的电力市场短期电价预测模型，最后采用具体实例分析了设计的电力市场短期电价预测模型的性能，结果表明，所提模型能够准确描述指标与电力市场短期电价之间的变化关系，获得较高精度的理想电力市场短期电价预测结果，电力市场短期电价预测效率高，具有一定的实际应用价值。     

基于周期性截断灰色系统的电力负荷预测

电力负荷预测是电力系统调度和电力生产计划制定的重要依据;电力负荷时间序列有着明显的周期性特征;传统的电力负荷预测主要侧重于预测方法的研究,而忽略了电力负荷数据周期性特性的分析,影响了预测的准确性;针对电力负荷时间序列的周期性特征,提出了一种基于周期性截断的灰色系统模型来进行电力负荷预测;该模型利用周期性截断来反映负荷数据的周期性特征,提高了预测的精度;仿真采用EUNITE Network的公开负荷数据进行算法性能的测试,并与一些主流的电力负荷预测算法:BP神经网络、极限学习机、自回归模型以及传统的灰色系统模型做比较;仿真结果表明,周期性截断的灰色系统负荷预测的归一化均方误差和绝对平均误差是最小的;周期性截断的灰色系统为电力系统负荷预测提供了一种新的有效方法。     

一种基于小波变换和ARIMA的短期电价混合预测模型

为在实时电价情况下预测未来24小时电价, 提出一种基于小波变换和差分自回归移动平均(ARIMA)的短期电价混合预测模型。该模型分别根据是否受到需求量影响使用ARIMA模型对多尺度小波变换分解后的时间序列进行预测。同时提出一种电价突变点发现和处理算法。使用澳大利亚新南威尔士州2012年真实数据验证表明, 相对ARIMA预测, 改进后的混合模型在不考虑需求量影响时预测精度更高; 电价突变点发现和处理算法能够准确处理电价异常点, 提高预测精度。     

基于长短期记忆网络的超短期负荷预测

负荷预测的准确率会影响电力生产和经济发展,根据目前广东电力现货市场的出清机制,超短期负荷预测的准确度对未来电力现货市场出清电价有着重大影响。文章采用数据横向纵向修正法对历史负荷数据进行修正,通过长短期记忆网络（Long Short Term Memory Network,LSTM）的预测方法,同时考虑现货市场实际运行时间间隔,对未来15 min的负荷进行预测。根据应用情况表明,该方法简单实用,能满足现货市场实际运行出清时的负荷预测要求。     

电力大数据下的短期电力负荷预测

电力产业是国民工业系统中重要的产业。在电网运行管理中,对于负荷预测具有非常重要的作用。更加准确的电力负荷预测可以为电网的安全稳定运行、实时进行电网负荷的调度提供了重要依据。特别是在经济方面,精确的电力负荷预测可以优化发、用电电网调度计划,合理调度和分配资源,从而起到使社会效益、经济效益最大化的作用。然而随着中国经济的飞速发展,对电力的需求不断增长,电力负荷本身受诸多因素以及政策影响比如日期、天气、气候、市场等其他因素,这些因素更大大加大了准确进行电力负荷预测的困难性。一直以来,人们一直都致力于提高电力负荷预测的准确性,人工神经网络算法具有泛化、学习能力强等优点,现在该算法已在电力负荷预测领域中得到了广泛应用,并且取得了良好的效果。近年来,人工神经网络领域取得重大突破,涌现出一个新的深度学习研究领域。本文就是基于最新发展的人工神经网络算法,结合实际地区电网数据研究了短期电力负荷预测的相关问题。     

基于时间序列与BP-ANN的短时交通流速度预测模型研究

针对现有的交通流速度预测模型使用唯一数据集且模型单一的问题,提出一种时间序列与人工神经网络相结合的预测模型。该模型通过时间序列分别对实时数据和历史数据建模预测,并应用人工神经网络调整实时数据和历史数据的预测值。实验结果表明该预测模型能够将预测误差控制在7%以内,且能够对不同输入参数下的短时交通流速度进行有效预测。     

一种改进的KNN案例推理检索算法

案例推理作为人工智能领域中通过已知知识解决问题的方法,其核心之一是检索算法。为了改善案例推理检索算法的预测结果质量,提出一种改进的KNN案例推理检索算法。首先,利用遗传模拟退火-模糊C均值聚类算法对案例库聚类,形成多个类簇;其次,通过改进的粒子群优化混合算法优化各类簇近邻K值;然后提出最优原则检索策略,确定检索子案例库及近邻K值;最后使用Mackey-Glass混沌时间序列数据进行仿真预测。实验结果表明,相较于传统KNN案例推理检索算法,改进的KNN案例推理检索算法预测结果的精度显著提高。     

人工神经网络在证券价格预测中的应用

证券市场中成功的交易模式是可以模仿及学习的.证券价格走势实质是一种复杂时序函数.人工神经网络是在模仿人脑处理问题过程中发展起来的新型智能信息处理系统,人工神经网络可以通过调节连接权值以任意精度逼近任何连续函数,因此也可以逼近证券价格随时间变换这种函数.文中采用基于BP模型的神经网络,用BP算法和遗传算法来训练网络权值,同时也采用了动量法和学习率自适应调整相结合的策略,对证券市场的价格进行建模和预测,结果表明,此模型具有较好的学习、泛化能力,对股票市场或其他类似的非线性经济系统的走势预测决策具有较好的效果.     

基于混合贝叶斯SVM的电价分类与预测

电价的分类与预测是电力市场电价理论研究中的重要内容。该文提出了混合贝叶斯支持向量机方法(BE-SVM)，通过贝叶斯统计方法对电价进行分类，挖掘有效的数据信息，并结合支持向量机(SVM)技术预测现货电价数据，贝叶斯前验分布和后验分布用来估计SVM中的参数。通过比较模型BE-SVM、SVM 和神经网络(ANN)的预测结果，表明该文提出的BE-SVM方法提高了电价的预测精度，是一种有效的方法。     

Improved estimation of electricity demand function by using of artificial neural network,principal component analysis and data envelopment analysis

Due to various seasonal and monthly changes in electricity consumption and difficulties in modeling it with the conventional methods, a novel algorithm is proposed in this paper. This study presents an approach that uses Artificial Neural Network (ANN), Principal Component Analysis (PCA), Data Envelopment Analysis (DEA) and ANOVA methods to estimate and predict electricity demand for seasonal and monthly changes in electricity consumption. Pre-processing and post-processing techniques in the data mining field are used in the present study. We analyze the impact of the data pre-processing and post-processing on the ANN performance and a 680 ANN-MLP is constructed for this purpose. DEA is used to compare the constructed ANN models as well as ANN learning algorithm performance. The average, minimum, maximum and standard deviation of mean absolute percentage error (MAPE) of each constructed ANN are used as the DEA inputs. The DEA helps the user to use an appropriate ANN model as an acceptable forecasting tool. In the other words, various error calculation methods are used to find a robust ANN learning algorithm. Moreover, PCA is used as an input selection method, and a preferred time series model is chosen from the linear (ARIMA) and nonlinear models. After selecting the preferred ARIMA model, the Mcleod–Li test is applied to determine the nonlinearity condition. Once the nonlinearity condition is satisfied, the preferred nonlinear model is selected and compared with the preferred ARIMA model, and the best time series model is selected. Then, a new algorithm is developed for the time series estimation; in each case an ANN or conventional time series model is selected for the estimation and prediction. To show the applicability and superiority of the proposed ANN-PCA-DEA-ANOVA algorithm, the data regarding the Iranian electricity consumption from April 1992 to February 2004 are used. The results show that the proposed algorithm provides an accurate solution for the problem of estimating electricity consumption.     

A novel model: Dynamic choice artificial neural network (DCANN) for an electricity price forecasting system

Big data mining, analysis, and forecasting always play a vital role in modern economic and industrial fields. Thus, how to select an optimization model to improve the forecasting accuracy of electricity price is not only an extremely challenging problem but also a concerned problem for different participants in an electricity market due to our society becoming heavily reliant on electricity. Many researchers developed hybrid models through the use of optimization methods, classical statistical models, artificial intelligence approaches and de-noising methods. However, few researchers aim to select reasonable samples and determine appropriate features when forecasting electricity price. Based on the Index of Bad Samples Matrix (IBSM), a novel method to dynamically confirm bad training samples, and the Optimization Algorithm (OA), DCANN and Updated DCANN are proposed in this paper for forecasting the day-ahead electricity price. This model is a hybrid system of supervised and unsupervised learning and creatively applies the idea of deleting bad samples and searching quality inputs to develop and learn, which is unlike BPANN, RBFN, SVM and LSSVM. Numerical results show that the proposed model is not only able to approximate the actual electricity price (normal or high volatility) but also an effective tool for h-step-ahead forecasting (h is less than 10) compared to benchmarks.     

A soft computing system for day-ahead electricity price forecasting

Hourly energy prices in a competitive electricity market are volatile. Forecast of energy price is key information to help producers and purchasers involved in electricity market to prepare their corresponding bidding strategies so as to maximize their profits. It is difficult to forecast all the hourly prices with only one model for different behaviors of different hourly prices. Neither will it get excellent results with 24 different models to forecast the 24 hourly prices respectively, for there are always not sufficient data to train the models, especially the peak price in summer. This paper proposes a novel technique to forecast day-ahead electricity prices based on Self-Organizing Map neural network (SOM) and Support Vector Machine (SVM) models. SOM is used to cluster the data automatically according to their similarity to resolve the problem of insufficient training data. SVM models for regression are built on the categories clustered by SOM separately. Parameters of the SVM models are chosen by Particle Swarm Optimization (PSO) algorithm automatically to avoid the arbitrary parameters decision of the tester, improving the forecasting accuracy. The comparison suggests that SOM–SVM–PSO has considerable value in forecasting day-ahead price in Pennsylvania–New Jersey–Maryland (PJM) market, especially for summer peak prices.     

A new adaptive fuzzy inference system for electricity consumption forecasting with hike in prices

Large increase or hike in energy prices has proven to impact electricity consumption in a way which cannot be drawn from historical data, especially when price elasticity of demand is not significant. This paper proposes an integrated adaptive fuzzy inference system (FIS) to estimate and forecast long-term electricity consumption when prices experience large increase. To this end, first a novel procedure for construction and adaptation of Takagi–Sugeno fuzzy inference system (TS-FIS) is suggested. Logarithmic linear regressions are estimated with historical data and used to construct an initial first-order TS-FIS. Then, in the adaptation phase, expert knowledge is used to define new fuzzy rules which form a new secondary FIS for electricity forecasting. To show the applicability and usefulness of the proposed model, it is applied for forecasting of annual electricity consumption in Iran where removing energy subsidies has resulted in a hike in electricity prices. Gross domestic product (GDP), population and electricity price are three inputs for the initial TS-FIS. A questionnaire survey was conducted to collect the expert estimation on possible change in electricity per capita, change in electricity intensity and the ratio of GDP elasticity to population elasticity when price hikes. Based on the information collected, a fuzzy rule base is formed and used to construct the secondary FIS which is used for electricity forecasting until 2016. Furthermore, the performance of the proposed model of this paper is compared with three other models namely ANFIS, ANN and one-stage regression in terms of their mean absolute percentage error. The comparison shows a superior performance for the proposed FIS model.     

An investigation and comparison of artificial neural network and time series models for Chinese food grain price forecasting

This paper compares the predictive performance of ARIMA, artificial neural network and the linear combination models for forecasting wheat price in Chinese market. Empirical results show that the combined model can improve the forecasting performance significantly in contrast with its counterparts in terms of the error evaluation measurements. However, as far as turning points and profit criterions are concerned, the ANN model is best as well as at capturing a significant number of turning points. The results are conflicting when implementing dissimilar forecasting criteria (the quantitative and the turning points measurements) to evaluate the performance of three models. The ANN model is overall the best model, and can be used as an alternative method to model Chinese future food grain price.     

A comparative study of artificial neural networks,and decision trees for digital game content stocks price prediction

Precise prediction of stock prices is difficult chiefly because of the many intervening factors. Unpredictability is particularly notable in the aftermath of the global financial crisis. Data mining may however be used to discover highly correlated estimation models. This study looks at artificial neural networks (ANN), decision trees and the hybrid model of ANN and decision trees (hybrid model), the three common algorithm methods used for numerical analysis, to forecast stock prices. The author compared the stock price forecasting models derived from the three methods, and applied the models on 10 different stocks in 320 data sets in an empirical forecast. Average accuracy of ANN is 15.31%, the highest, in terms of match with real market stock prices, followed by decision trees, at 14.06%; hybrid model is 13.75%. The study also discovers that compared to the other two methods, ANN is a more stable method for predicting stock prices in the volatile post-crisis stock market.