scholarly journals Electrical Load Forecast by Means of LSTM: The Impact of Data Quality

Forecasting ◽  
2021 ◽  
Vol 3 (1) ◽  
pp. 91-101
Author(s):  
Alfredo Nespoli ◽  
Emanuele Ogliari ◽  
Silvia Pretto ◽  
Michele Gavazzeni ◽  
Sonia Vigani ◽  
...  
Keyword(s):  
Forecast Accuracy ◽  
Electric Load ◽  
Electrical Load ◽  
Autocorrelation Analysis ◽  
Load Forecast ◽  
Error Metrics ◽  
Input Dataset ◽  
Accurate Forecast ◽  
The Impact

Accurate forecast of aggregate end-users electric load profiles is becoming a hot topic in research for those main issues addressed in many fields such as the electricity services market. Hence, load forecast is an extremely important task which should be understood more in depth. In this research paper, the dependency of the day-ahead load forecast accuracy on the basis of the data typology employed in the training of LSTM has been inspected. A real case study of an Italian industrial load with samples recorded every 15 min for the year 2017 and 2018 was studied. The effect in the load forecast accuracy of different dataset cleaning approaches was investigated. In addition, the Generalised Extreme Studentized Deviate hypothesis testing was introduced to identify the outliers present in the dataset. The populations were constructed on the basis of an autocorrelation analysis that allowed for identifying a weekly correlation of the samples. The accuracy of the prediction obtained from different input dataset has been therefore investigated by calculating the most commonly used error metrics, showing the importance of data processing before employing them for load forecast.

Long Term Forecast of Electric Load in Beijing

2012 ◽  
Vol 516-517 ◽  
pp. 1490-1495
Author(s):  
Qing You Yan ◽  
Zhi Yu Liu ◽  
Si Qi He
Keyword(s):  
Economic Development ◽  
Electric Power ◽  
Future Development ◽  
Power Supply ◽  
Power Grid ◽  
Electric Load ◽  
Load Forecast ◽  
Term Forecast ◽  
Accurate Forecast

Accurate forecast of electric load provides scientific grounds for national departments to plan how to produce electric power or how to use it and it also benefits the maintenance and construction plan of power grid to improve power supply security. Now the demand of electric power in Beijing increases yearly due to sustained economic development, the electric-load-forecast is practical for Beijing to prepare future development of its electric power. This paper selected 1973~2008 data of Beijing to test the causality between economy and electric load. Then it established equation based on cointegration theory to forecast electric load in future years.

scholarly journals Using a Software Tool in Forecasting: a Case Study of Sales Forecasting Taking into Account Data Uncertainty

2016 ◽  
Vol 6 (1) ◽  
Author(s):  
Jana Fabianová ◽  
Peter Kačmáry ◽  
Vieroslav Molnár ◽  
Peter Michalik
Keyword(s):  
Input Data ◽  
Impact Analysis ◽  
Forecast Error ◽  
Forecast Accuracy ◽  
Software Tool ◽  
Data Uncertainty ◽  
Business Outcomes ◽  
Starting Point ◽  
The Impact

Abstract Forecasting is one of the logistics activities and a sales forecast is the starting point for the elaboration of business plans. Forecast accuracy affects the business outcomes and ultimately may significantly affect the economic stability of the company. The accuracy of the prediction depends on the suitability of the use of forecasting methods, experience, quality of input data, time period and other factors. The input data are usually not deterministic but they are often of random nature. They are affected by uncertainties of the market environment, and many other factors. Taking into account the input data uncertainty, the forecast error can by reduced. This article deals with the use of the software tool for incorporating data uncertainty into forecasting. Proposals are presented of a forecasting approach and simulation of the impact of uncertain input parameters to the target forecasted value by this case study model. The statistical analysis and risk analysis of the forecast results is carried out including sensitivity analysis and variables impact analysis.

scholarly journals Electric Load Forecast Using Combined Models with HP Filter-SARIMA and ARMAX Optimized by Regression Analysis Algorithm

2015 ◽  
Vol 2015 ◽  
pp. 1-14
Author(s):  
Cui Herui ◽  
Peng Xu ◽  
Mu Yupei
Keyword(s):  
Electric Load ◽  
Combined Model ◽  
Load Forecast ◽  
Proposed Model ◽  
Forecasting Method ◽  
Armax Model ◽  
Combined Models ◽  
Hp Filter ◽  
Cyclical Trend

Electric load in summer has a significant cyclical trend with temperature effects. In general, the parameters of the SARIMA and the SMA turn out to be nonsignificant in most cases. To address this issue, the hybrid time series model is utilized to extract the spectrum sequences with different frequencies. The original electric load series are first decomposed into the trend sequence “G” and the cycle sequence “C.” After that, a revised ARMAX model is proposed to deal with the two divided sequences. Finally, the combined models are tested by case study. The case study on electric load forecast in one city from China shows that the proposed model outperforms other four comparative models in terms of prediction accuracy. It proves that the combined model proposed by the authors is more accurate than those based on a single forecasting method.

The impact of digitalization on business processes: case study: Kosovo SMEs

2018 ◽  
Author(s):  
Ylber Limani ◽  
Edmond Hajrizi ◽  
Rina Sadriu
Keyword(s):  
Business Processes ◽  
The Impact
Sign in / Sign up

Export Citation Format

Share Document