This work presents a Long Short-Term Memory (LSTM) network for forecasting a monthly electricity demand time series with a one-year horizon. The novelty of this work is the use of pattern representation of the seasonal time series as an alternative to decomposition. Pattern representation simplifies the complex nonlinear and nonstationary time series, filtering out the trend and equalizing variance. Two types of patterns are defined: x-pattern and y-pattern. The former requires additional forecasting for the coding variables. The latter determines the coding variables from the process history. A hybrid approach based on x-patterns turned out to be more accurate than the standard LSTM approach based on a raw time series. In this combined approach an x-pattern is forecasted using a sequence-to-sequence LSTM network and the coding variables are forecasted using exponential smoothing. A simulation study performed on the monthly electricity demand time series for 35 European countries confirmed the high performance of the proposed model and its competitiveness to classical models such as ARIMA and exponential smoothing as well as the MLP neural network model.
Macroeconomic forecasting with LSTM and mixed frequency time series data
Faculty of Economics, Khon Kaen University(孔敬大学经济学院);Khon Kaen University(孔敬大学)
本文展示了长短期记忆(LSTM)在应用于不同频率采样的宏观经济时间序列数据时的潜力。我们首先介绍了当对所有低频输出和高频变量对应用相同的失配比时,传统的LSTM模型如何适应在混合频率下观察到的时间序列。为了将LSTM推广到多个失配率的情况,我们采用了无限制混合数据采样(U-MIDAS)方案(Foroni et al.,2015年)引入LSTM架构。我们评估通过bothMonte Carlo模拟和实证应用的样本预测性能。我们提出的模型优于限制MIDAS模型,即使在一个设置有利于MIDAS估计。对于现实世界的应用,我们研究预测泰国实际GDP的季度增长率,使用大量的宏观经济指标季度和月度。我们使用U-MIDAS方案的LSTM在所有范围内都轻松击败了简单的基准AR(1)模型,但仅在一个月和六个月的时间内优于强基准单变量LSTM。尽管如此,我们发现,我们提出的模型可能是非常有帮助的,在大的经济低迷时期的短期预测。模拟和实验结果似乎支持我们提出的LSTM with U-MIDAS方案用于临近预报应用。
Searth Transformer: A Transformer Architecture Incorporating Earth's Geospheric Physical Priors for Global Mid-Range Weather Forecasting
Institute of Atmospheric Physics, Chinese Academy of Sciences(中国科学院大气物理研究所);University of Chinese Academy of Sciences(中国科学院大学);Fudan University(复旦大学);Shanghai Academy of Artificial Intelligence for Science(上海科学智能研究院);Beijing Aviation Meteorological Institute(北京航空气象研究所);Meteorological Bureau of Shenzhen Municipality(深圳市气象局);Nanjing University of Information Science and Technology(南京信息工程大学);National Marine Environmental Forecasting Center(国家海洋环境预报中心);Beijing Meteorological Service Center(北京市气象服务中心);Beijing University of Posts and Telecommunications(北京邮电大学)
TgDLF2.0: Theory-guided deep-learning for electrical load forecasting via Transformer and transfer learning
Eastern Institute for Advanced Study(东方高等研究院);Yongriver Institute of Technology(甬江理工学院);Hefei University of Technology(合肥工业大学);Peng Cheng Laboratory(鹏城实验室);Southern University of Science and Technology(南方科技大学)
Weather-Informed Probabilistic Forecasting and Scenario Generation in Power Systems
H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology(工业与系统工程系,佐治亚理工学院);AI Institute for Advances in Optimization(优化前沿人工智能研究所)
An Error Correction Mid-term Electricity Load Forecasting Model Based on Seasonal Decomposition
Southwest University(西南大学);Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences(中国科学院重庆绿色智能技术研究院);University of Chinese Academy of Sciences(中国科学院大学)
Time series forecasting based on optimized LLM for fault prediction in distribution power grid insulators
Center of Technology and Systems (UNINOVA-CTS)(技术与系统中心(UNINOVA-CTS));Associated Lab of Intelligent Systems (LASI)(智能系统联合实验室(LASI));Faculty of Engineering and Applied Sciences, University of Regina(里贾纳大学工程与应用科学学院)
Heterogeneous Graph Neural Networks for Short-term State Forecasting in Power Systems across Domains and Time Scales: A Hydroelectric Power Plant Case Study
Intelligent Maintenance and Operations Systems (IMOS)(智能维护与运营系统)
Improving Short-Term Electricity Price Forecasting Using Day-Ahead LMP with ARIMA Models
短期电价预测已成为电力需求侧管理和发电调度的重要手段。特别是在电力市场竞争日益激烈的情况下,一个比独立系统运营商(ISO)公布的日前位置边际电价(DALMP)更准确的电价预测将有利于市场参与者增加利润或改善负荷需求调度。因此,本文的主要思想是使用自回归积分移动平均(ARIMA)模型,以获得一个更好的LMP预测比DALMP,利用公布的DALMP,历史实时LMP(RTLMP)和其他有用的信息。首先,一组季节性ARIMA(SARIMA)模型,利用DALMP和历史RTLMP的开发和比较自回归移动平均(ARMA)模型,使用DALMP和RTLMP之间的差异,其预测能力。广义自回归条件异方差(GARCH)模型的实施,以进一步提高预测占价格波动。这些模型使用Midcontinent Independent System Operator(MISO)地区的真实市场数据进行训练和评估。评价结果表明,当外生时间序列为周末时,ARMAX-GARCH模型提高了短期电价预测精度,优于其他ARIMA模型
Real Time State Estimation of Power Grids Using Convolutional Neural Networks and State Forecasting Via Recurrent Neural Networks
电网在向家庭、工业和其他需要电能的地方输送电能方面发挥着非常重要的作用。由于需求的增加,电网面临着电压变化的巨大挑战。这是由于各种能源消耗设备和电器的使用,如电动汽车,工业消费,能源需求的偶尔高峰等,对于这些需求的波动,监控电网运行的条件变得非常重要。一旦知道这些条件,就可以操纵能源生产来满足需求。现有的电力系统状态估计(PSSE)技术在产生最优性能方面可能并不好。此外,它们在计算处理方面也是昂贵的。为了解决这个问题,本研究提出了一种基于卷积神经网络(CNN)的电网状态估计方法。结果发现,该模型产生的RMSE为2.57 x 10-4,这比使用Prox线性模型(2.97 x 10-4)进行估计所涉及的先前研究之一相对准确。此外,研究还提出了电力系统状态预测,以提高系统的意识和弹性。预测采用递归神经网络(RNN)模型。该模型有助于解释数据中存在的长期非线性方面,并在此基础上进行预测。所提出的模型预测的RMSE为2.53 x 10-3,与上述先前的研究(2.59 x 10-3)相当。