Long term and short term forecasting of horticultural produce based on the LSTM network model

2022 ◽  
Author(s):  
Tumpa Banerjee ◽  
Shreyashee Sinha ◽  
Prasenjit Choudhury
Keyword(s):  
Network Model ◽  
Short Term ◽  
Lstm Network ◽  
Short Term Forecasting

Long-term inference based on short-term forecasting models

1993 ◽  
pp. 9-25 ◽  
Author(s):  
P. Newbold ◽  
C. Agiakloglou ◽  
J. Miller
Keyword(s):  
Short Term ◽  
Forecasting Models ◽  
Short Term Forecasting

Short-Term Forecasting Method of Maximum Usable Frequency for HF Communication Based on Oblique Sounder

2013 ◽  
Vol 336-338 ◽  
pp. 1676-1681
Author(s):  
Jin Hai Hou ◽  
Jian Wang ◽  
Li Qiang Wu ◽  
Sheng Yun Ji ◽  
Dan Jun Chen
Keyword(s):  
Critical Frequency ◽  
Short Term ◽  
System A ◽  
Maximum Usable Frequency ◽  
Forecasting Method ◽  
Short Term Forecasting ◽  
Frequency Management ◽  
Ray Path ◽  
Long Term Prediction

Based on oblique sounding system, a short-term forecasting method of maximum usable frequency for HF communication was presented. The method include four steps: firstly, maximum usable frequency of oblique sounding circuit was forecasted based on its sounding data; secondly, the critical frequency of sounding path midpoint was determined from the oblique sounding data and its forecast data by using ray-path theory; thirdly, the critical frequency was reconstructed for forecast circuit; in the end, maximum usable frequency for HF communication circuit was given. Using the oblique sounding data during March 2012, the accuracy and practicability of the method was validated. The root-mean-square error of the short-term forecast is 1.56 MHz, and is reduced 0.40MHz contrast to that of the long-term prediction. The research provides the important reference for frequency selection and frequency management of HF communication.

Defining the Long-Term Wave Resource at Wave Hub: The Role of Measurements and Models

2008 ◽  
Author(s):  
Joseph Phillips ◽  
Joao Cruz ◽  
Rob Holbrow ◽  
Jeremy Parkes ◽  
Rob Rawlinson-Smith
Keyword(s):  
Wave Energy ◽  
Resource Assessment ◽  
Wave Climate ◽  
Short Term ◽  
Wave Data ◽  
Wave Measurements ◽  
Operations And Maintenance ◽  
South West Coast ◽  
Short Term Forecasting

Wave measurements made on the site of a potential wave energy project can be of high value to developers. Such data can be used to define both long-term and short-term wave energy resources available to devices as well as the optimal operations and maintenance strategy which should be employed for the project. All three of these applications are addressed in an ongoing study commissioned by the npower Juice Fund for the Wave Hub project which is planned off the South West coast of England. The aim of this work is to extract best value from the historical and future wave measurements from the project site. The programme of this project is outlined here with a technical description of activity in the three parallel strands of the study; wave resource assessment, short-term forecasting and O&M modelling. The focus of this paper is on a key aspect of the ongoing work programme - that relates to the use of measured and modelled wave data to derive a prediction of the long-term wave climate at the Wave Hub site. In particular, various candidate methodologies for correlating short-term measured wave data and long-term modelled data are explored in the context of a Measure-Correlate-Predict (MCP) analysis. This work has also included consideration of the inter-annual variability of wave resource in order to examine the uncertainty associated with assuming that a finite historical reference period is representative of the long-term wave climate.

scholarly journals Short-term forecasting of available parking space using wavelet neural network model

2015 ◽  
Vol 9 (2) ◽  
pp. 202-209 ◽  
Author(s):  
Yanjie Ji ◽  
Phil Blythe ◽  
Weihong Guo ◽  
Wei Wang ◽  
Dounan Tang
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Wavelet Neural Network ◽  
Parking Space ◽  
Short Term ◽  
Short Term Forecasting

Crude oil price prediction based on LSTM network and GM (1,1) model

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Tianxiang Yao ◽  
Zihan Wang
Keyword(s):  
Crude Oil ◽  
Oil Price ◽  
Crude Oil Price ◽  
Short Term ◽  
Content Type ◽  
Forecasting Models ◽  
Price Series ◽  
Mode Decomposition ◽  
Lstm Network

PurposeAccording to the problem of crude oil price forecasting, the purpose of this paper is to propose a multi-step prediction method based on the empirical mode decomposition, long short-term memory network and GM (1,1) model.Design/methodology/approachFirst, the empirical mode decomposition method is used to decompose the crude oil price series into several components with different frequencies. Then, each subsequence is classified and synthesized based on the specific periodicity and other properties to obtain several components with different significant characteristics. Finally, all components are substituted into a suitable prediction model for fitting. LSTM models with different parameters are constructed for predicting specific components, which approximately and respectively represent short-term market disturbance and long-term influences. Rolling GM (1,1) model is constructed to simulate a series representing the development trend of oil price. Eventually, all results obtained from forecasting models are summarized to evaluate the performance of the model.FindingsThe model is respectively applied to simulate daily, weekly and monthly WTI crude oil price sequences. The results show that the model has high accuracy on the prediction, especially in terms of series representing long-term influences with lower frequency. GM (1,1) model has excellent performance on fitting the trend of crude oil price.Originality/valueThis paper combines GM (1,1) model with LSTM network to forecast WTI crude oil price series. According to the different characteristics of different sequences, suitable forecasting models are constructed to simulate the components.

The Second Century Papers: Looking Ahead in Aeronautics—18

1969 ◽  
Vol 73 (701) ◽  
pp. 369-382
Author(s):  
Alan H. Stratford
Keyword(s):  
Composite Materials ◽  
Research And Development ◽  
Financial Support ◽  
Noise Control ◽  
Second Century ◽  
Short Term ◽  
Dominant Position ◽  
Deep Conviction ◽  
Short Term Forecasting

“It is need, rather than discovery which stimulates progress, and the key to industrial success is the choice of application rather than priority in research” Sir Robert Cockburn, Director of RAE, 1968 At the first meeting of our Society in January 1866, James Glaisher advised us to “exclude any matter that may seem useless in forwarding the science, or that has the slightest chance of giving rise to ridicule …” this warning was timely and relevant to this theme for to consider the long-term future with as much rationality as is required for short-term forecasting and planning studies, is a valuable exercise in restraint as well as in imagination. So many avenues of possible development are technologically interesting, but in economic terms are sterile and unrewarding. One emerges with a deep conviction that certain areas of research and development may be in a dominant position in their influence on future aviation growth. Two of these are noise control and the evolution of composite materials. Although fairly obvious it seems important that they and some others be given the financial support which they deserve.

scholarly journals A Nonintrusive Load Monitoring Method for Microgrid EMS Using Bi-LSTM Algorithm

Complexity ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Dongguo Zhou ◽  
Yangjie Wu ◽  
Hong Zhou
Keyword(s):  
Evaluation Method ◽  
Feature Matching ◽  
Short Term Memory ◽  
Load Identification ◽  
Short Term ◽  
Monitoring Method ◽  
Term Memory ◽  
Load Monitoring ◽  
Lstm Network

Nonintrusive load monitoring in smart microgrids aims to obtain the energy consumption of individual appliances from the aggregated energy data, which is generally confronted with the error identification of the load type for energy disaggregation in microgrid energy management system (EMS). This paper proposes a classification strategy for the nonintrusive load identification scheme based on the bilateral long-term and short-term memory network (Bi-LSTM) algorithm. The sliding window algorithm is used to extract the detected load event features and obtain the load features of data samples. In order to accurately identify these load features, the steady state information is combined as the input of the Bi-LSTM model during training. Comprising long-term and short-term memory (LSTM) network and recurrent neural network (RNN), Bi-LSTM has the advantages of stronger recognition ability. Finally, precision (P), recall (R), accuracy (A), and F1 values are used as the evaluation method for nonintrusive load identification. The experimental results show the accuracy of the Bi-LSTM identification method for load start and stop state feature matching; moreover, the method can identify relatively low-power and multistate appliances.

scholarly journals Short-term wind speed forecasting system using deep learning for wind turbine applications

2020 ◽  
Vol 10 (6) ◽  
pp. 5779
Author(s):  
Gokhan Erdemir ◽  
Aydin Tarik Zengin ◽  
Tahir Cetin Akinci
Keyword(s):  
Deep Learning ◽  
Wind Speed ◽  
Wind Turbine ◽  
Wind Turbines ◽  
Learning Algorithm ◽  
Integrated System ◽  
Short Term ◽  
Wind Speed Forecasting ◽  
Short Term Forecasting

It is very important to accurately detect wind direction and speed for wind energy that is one of the essential sustainable energy sources. Studies on the wind speed forecasting are generally carried out for long-term predictions. One of the main reasons for the long-term forecasts is the correct planning of the area where the wind turbine will be built due to the high investment costs and long-term returns. Besides that, short-term forecasting is another important point for the efficient use of wind turbines. In addition to estimating only average values, making instant and dynamic short-term forecasts are necessary to control wind turbines. In this study, short-term forecasting of the changes in wind speed between 1-20 minutes using deep learning was performed. Wind speed data was obtained instantaneously from the feedback of the emulated wind turbine's generator. These dynamically changing data was used as an input of the deep learning algorithm. Each new data from the generator was used as both test and training input in the proposed approach. In this way, the model accuracy and enhancement were provided simultaneously. The proposed approach was turned into a modular independent integrated system to work in various wind turbine applications. It was observed that the system can predict wind speed dynamically with around 3% error in the applications in the test setup applications.

Sign in / Sign up

Export Citation Format

Share Document