scholarly journals Time-Series Prediction: Application to the Short-Term Electric Energy Demand

2004 ◽  
pp. 577-586 ◽  
Author(s):  
Alicia Troncoso Lora ◽  
Jesús Manuel Riquelme Santos ◽  
José Cristóbal Riquelme ◽  
Antonio Gómez Expósito ◽  
José Luís Martínez Ramos
Keyword(s):  
Time Series ◽  
Energy Demand ◽  
Time Series Prediction ◽  
Electric Energy ◽  
Short Term

scholarly journals Usage of the Pareto Fronts as a Tool to Select Data in the Forecasting Process—A Short-Term Electric Energy Demand Forecasting Case

Energies ◽  
2021 ◽  
Vol 14 (11) ◽  
pp. 3204
Author(s):  
Michał Sabat ◽  
Dariusz Baczyński
Keyword(s):  
Energy Demand ◽  
Demand Forecasting ◽  
Electric Energy ◽  
Forecasting Model ◽  
Short Term ◽  
Complex Evaluation ◽  
Proposed Model ◽  
Energy Demand Forecasting ◽  
Pareto Fronts ◽  
Naive Approach

Transmission, distribution, and micro-grid system operators are struggling with the increasing number of renewables and the changing nature of energy demand. This necessitates the use of prognostic methods based on ever shorter time series. This study depicted an attempt to develop an appropriate method by introducing a novel forecasting model based on the idea to use the Pareto fronts as a tool to select data in the forecasting process. The proposed model was implemented to forecast short-term electric energy demand in Poland using historical hourly demand values from Polish TSO. The study rather intended on implementing the range of different approaches—scenarios of Pareto fronts usage than on a complex evaluation of the obtained results. However, performance of proposed models was compared with a few benchmark forecasting models, including naïve approach, SARIMAX, kNN, and regression. For two scenarios, it has outperformed all other models by minimum 7.7%.

scholarly journals 2-D Convolutional Deep Neural Network for the Multivariate Prediction of Photovoltaic Time Series

Energies ◽  
2021 ◽  
Vol 14 (9) ◽  
pp. 2392
Author(s):  
Antonello Rosato ◽  
Rodolfo Araneo ◽  
Amedeo Andreotti ◽  
Federico Succetti ◽  
Massimo Panella
Keyword(s):  
Time Series ◽  
Short Term Memory ◽  
Time Series Prediction ◽  
Short Term ◽  
Neural Architecture ◽  
Network Layers ◽  
Learning Scheme ◽  
World Energy ◽  
Multivariate Prediction ◽  
Long Short Term Memory

Here, we propose a new deep learning scheme to solve the energy time series prediction problem. The model implementation is based on the use of Long Short-Term Memory networks and Convolutional Neural Networks. These techniques are combined in such a fashion that inter-dependencies among several different time series can be exploited and used for forecasting purposes by filtering and joining their samples. The resulting learning scheme can be summarized as a superposition of network layers, resulting in a stacked deep neural architecture. We proved the accuracy and robustness of the proposed approach by testing it on real-world energy problems.

Introduced flow variability and its propagation downstream of hydropower stations in Sweden

2021 ◽  
Author(s):  
Maria Elenius ◽  
Göran Lindström
Keyword(s):  
Time Series ◽  
Energy Demand ◽  
Ecological Impact ◽  
Ecological Impacts ◽  
Low Flow ◽  
Seasonal Forecasts ◽  
Short Term ◽  
Swedish Model ◽  
The Impact ◽  
Hydropower Stations

<p>Hydropower provides a low-carbon solution to a large portion of Sweden’s energy demand, which is increasingly important in order to combat climate change. However, associated flow regulations introduce variability of the flow on the daily, weekly and seasonal time scales, driven by the varying energy demand. Additional variability is introduced when compensating for the shifting wind energy production. The Water framework directive requires all EU member states to evaluate the ecological impact from anthropogenic activities, such as hydropower. Ecological impacts must also be assessed when all hydropower permissions in Sweden are renewed over the coming 20 years. Because different species are sensitive to different longevity of high- and low-flow periods, it is important to understand the introduced variability of flow in terms of its dominant periods, and how quickly these perturbations are attenuated downstream of regulations.</p><p>In this work, time-series of flow from hydrological simulations with HYPE are analyzed with the Fourier transform to examine the amplitudes of perturbations of different periods, and their decay downstream of hydropower stations. HYPE is a catchment-based model that simulates rainfall-runoff as well as water quality processes. The Swedish model application has been developed over the past decade and covers all of Sweden. Seasonal regulations are modeled with calibrated input parameters, whereas short-term regulations are introduced with station updates from observations that are available at or close to the majority of hydropower regulations. Very high accuracy has been proven between the updated sub-catchments. This, together with a verified model for natural flow, gives us a unique opportunity to study the impact of hydropower on dominant periods and their decay over the entire country, as well as the mechanisms that govern this decay.</p><p>In many sub-catchments, especially in large regulated rivers in northern Sweden, Fourier analysis of daily time series results in dominance of the 7-day period. The exponential decay rate of this and other modes is presented for all Sweden and analyzed in terms of land use and other parameters. Short periods decay faster than long ones. Periods of one month or longer are amplified in the downstream direction in most of Sweden.</p><p>Apart from aid in ecological assessments, our analysis can be used to introduce short-term regulations in hydrological simulators, for either deterministic forecasts (the 7-day mode typically has a minimum value on Sundays) or for stochastic seasonal forecasts where it will impact indicators such as the number of days below or above a threshold.</p>

scholarly journals Compound Autoregressive Network for Prediction of Multivariate Time Series

Complexity ◽  
2019 ◽  
Vol 2019 ◽  
pp. 1-11 ◽  
Author(s):  
Yuting Bai ◽  
Xuebo Jin ◽  
Xiaoyi Wang ◽  
Tingli Su ◽  
Jianlei Kong ◽  
...  
Keyword(s):  
Time Series ◽  
Time Series Prediction ◽  
Multivariate Time Series ◽  
Prediction Algorithm ◽  
Short Term ◽  
Advanced Control ◽  
Multiple Variables ◽  
Nonlinear Autoregressive Model ◽  
Interactive Relation ◽  
Nonlinear Autoregressive

The prediction information has effects on the emergency prevention and advanced control in various complex systems. There are obvious nonlinear, nonstationary, and complicated characteristics in the time series. Moreover, multiple variables in the time-series impact on each other to make the prediction more difficult. Then, a solution of time-series prediction for the multivariate was explored in this paper. Firstly, a compound neural network framework was designed with the primary and auxiliary networks. The framework attempted to extract the change features of the time series as well as the interactive relation of multiple related variables. Secondly, the structures of the primary and auxiliary networks were studied based on the nonlinear autoregressive model. The learning method was also introduced to obtain the available models. Thirdly, the prediction algorithm was concluded for the time series with multiple variables. Finally, the experiments on environment-monitoring data were conducted to verify the methods. The results prove that the proposed method can obtain the accurate prediction value in the short term.

scholarly journals Deep Learning with Long Short-Term Memory for Time Series Prediction

2019 ◽  
Vol 57 (6) ◽  
pp. 114-119 ◽  
Author(s):  
Yuxiu Hua ◽  
Zhifeng Zhao ◽  
Rongpeng Li ◽  
Xianfu Chen ◽  
Zhiming Liu ◽  
...  
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Short Term Memory ◽  
Time Series Prediction ◽  
Short Term ◽  
Term Memory ◽  
Long Short Term Memory

Trend-Based Time Series Prediction Algorithm

2010 ◽  
Vol 108-111 ◽  
pp. 1164-1169
Author(s):  
Xin Qi ◽  
Hong Liang ◽  
Zhen Li
Keyword(s):  
Time Series ◽  
Monitoring System ◽  
Time Series Prediction ◽  
Prediction Algorithm ◽  
Short Term ◽  
Grid Monitoring ◽  
Status Information ◽  
Term Performance ◽  
Improved Algorithm

According to the resources performance and status information provided by grid monitoring system, this paper adopts a trend-based time series prediction algorithm to predict short-term performance of the resources. Experiments show that the improved mixed trend-based prediction algorithm tracks the trend of data changes by giving more weight, simultaneously takes the different situations of data increases and decreases into account, so the improved algorithm is superior to the pre-improved and it improves the accuracy of the prediction effectively.

Sign in / Sign up

Export Citation Format

Share Document