Development progress of power prediction robot and platform: Its world level very long term prototyping example

Burak Omer SARACOGLU

doi:https://doi.org/10.30521/jes.1021838

Makale detayları

Development progress of power prediction robot and platform: Its world level very long term prototyping example

Yazarlar:

Burak Omer SARACOGLU

Yayıncı:

Erol KURT

Ana Başlıklar:

Veri işleme & bilgisayar bilimi

Dergi:

Journal of Energy Systems 2022 Vol.6 Issue 2, pp.253-289

Belge Tipi:

Makale

Yayın Tarihi:

6/2022

Belge Dili:

İngilizce

Document ID (Org No.):

2000505607

Sıklık:

Aylık

eISSN:

2602-2052

DOI:

https://doi.org/10.30521/jes.1021838

Özet:

 

Global Power Prediction Systems prototype version 2021 is presented with its system decomposition, scope, geographical/administrative/power grid decompositions, and similar. “Welcome”, “sign-up”, “log-in”, and “non-registered user main” web-interfaces are designed as draft on Quant UX. Map canvas is given as world political map with/without world power grid layers on QGIS 3.16.7-Hannover. Data input file is prepared based on several sources (1971-2018). It includes minimum and maximum values due to source value differences. 70/30 principle is applied for train/test splitting (training/testing sets: 1971-2003/2004-2018). 10 models are prepared on R version 4.1.1 with RStudio 2021.09.0+351. These are R::base(lm), R::base(glm), R::tidymodels::parsnip(engine("lm")), R::tidymodels::parsnip(engine("glmnet")) with lasso regularization, R::tidymodels::parsnip(engine("glmnet")) with ridge regularization, R::forecast(auto.arima) auto autoregressive integrated moving average (ARIMA), R::forecast(arima) ARIMA(1,1,2), and ARIMA(1,1,8). Electricity demand in kilowatt-hours at the World level zone for up to 500-years (2019-2519) prediction period with only 1-year interval is forecasted. The best model is the auto ARIMA (mean absolute percentage error MAPE and symmetric mean absolute percentage error SMAPE for minimum and maximum electricity consumption respectively 1,1652; 6,6471; 1,1622; 6,9043). Ex-post and ex-ante plots with 80%-95% confidence intervals are prepared in R::tidyverse::ggplot2. There are 3 alternative scripts (long, short, RStudio Cloud). Their respective runtimes are 41,45; 25,44; and 43,33 seconds. Ex-ante 500-year period (2019-2519) is indicative and informative.

Makale detayları

Development progress of power prediction robot and platform: Its world level very long term prototyping example

Yazarlar: Burak Omer SARACOGLU

Yayıncı: Erol KURT

Ana Başlıklar: Veri işleme & bilgisayar bilimi

Dergi: Journal of Energy Systems 2022 Vol.6 Issue 2, pp.253-289

Belge Tipi: Makale

Yayın Tarihi: 6/2022

Belge Dili: İngilizce

Document ID (Org No.): 2000505607

Sıklık: Aylık

eISSN: 2602-2052

DOI: https://doi.org/10.30521/jes.1021838

Sayı

Yazarlar:

Burak Omer SARACOGLU

Yayıncı:

Erol KURT

Ana Başlıklar:

Veri işleme & bilgisayar bilimi

Dergi:

Journal of Energy Systems 2022 Vol.6 Issue 2, pp.253-289

Belge Tipi:

Makale

Yayın Tarihi:

6/2022

Belge Dili:

İngilizce

Document ID (Org No.):

2000505607

Sıklık:

Aylık

eISSN:

2602-2052

DOI:

https://doi.org/10.30521/jes.1021838