The main dataset is constituted of 7 different datasets which contains EXIST (Energy Exchange Istanbul) Intraday Market variables’ data such as Weighted Average Price of exchanges in the market, Minimum and Maximum Prices of Bidding and Offer prices for electricity supply in the MWh scale.
Intraday Market is introduced due to the impossibility of predicting next day’s hourly consumption perfectly. Unlike Day Ahead Market, there is continuous trading at Intraday Market. It is much like a stock exchange. Prices can change in mere seconds or in higher frequency. It gives an opportunity to correct participants forecasts by trading their excess or missing MWhs.
The time range of the data covers the year 2019 from January 1 to December 31. This dataset is exciting for us because the system it is based on is something different than we could. It reminds an auction which happens every hour and day, exactly like stock exchange. With this dataset, we will find the opportunity to make the deductions about how producers and consumers are imperfect in prediction their future consumption. Also, we will list the reasons of fluctuation in hourly, daily, or monthly trading in Intraday Market.
You can access the data through EXIST Transparency Platform.
url <- "https://github.com/pjournal/boun01g-r-sizlar/blob/gh-pages/idm_data.csv?raw=true"
idm_data <- read.csv(url)
idm_data %>% glimpse()## Rows: 8,740
## Columns: 15
## $ Date.Time <chr> "2019-01-01", "2019-01-01", "2019-01-0...
## $ Hour <int> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,...
## $ Day.Week <chr> "Tue", "Tue", "Tue", "Tue", "Tue", "Tu...
## $ Month <int> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,...
## $ WAP..TL.MWh. <dbl> 100.23, 96.85, 80.25, 38.28, 11.67, 11...
## $ Clearing.Quantity..MWh. <chr> "331.20", "527.70", "196.70", "414.70"...
## $ Min.Bid.Price..TL.MWh. <dbl> 5.00, 5.00, 41.00, 1.00, 1.00, 1.00, 1...
## $ Max..Offer.Price..TL.MWh. <chr> "100.39", "296.29", "81.60", "45.00", ...
## $ Bid.Quantity..MWh. <chr> "392.50", "910.00", "576.70", "797.40"...
## $ Offer.Quantity..MWh. <chr> "509.40", "664.20", "349.60", "552.90"...
## $ Min..Matching.Price..TL.MWh. <dbl> 60.00, 93.82, 41.05, 4.00, 5.00, 5.00,...
## $ Max..Matching.Price..TL.MWh. <dbl> 100.39, 97.55, 81.60, 45.00, 11.52, 11...
## $ Trade.Value..TL. <chr> "33,182.96", "51,036.02", "15,652.36",...
## $ Max..Bid.Price..TL.MWh. <chr> "101.38", "97.55", "81.60", "45.00", "...
## $ Min..Offer.Price..TL.MWh. <dbl> 60.00, 93.82, 40.00, 4.00, 5.00, 5.00,...WAP: Shows the weighted average price of exchanges succeeded at contract under consideration.
Clearing Quantity: MWh amount which clears consumption/production plan from matching offers and market prices.
Bid Price: Price offered by the one wishing to sell electricity in TL/MWh.
Offer Price: Ask price offered by consumer/producer wishing to buy electricity in TL/MWh
Offer Quantity: The amount of offers in the MWh scale.
Matching Price: The best available price in the order which has a priority.
Trade Value: The sum of ask and bid quantities contract under consideration so far.
Cleaning and manipulating the data (Data Preprocessing)
Feature engineering the data
Visualizing the data
Revealing hidden values from the data
To be able to obey the plan, we will use some packages like:
– dplyr
– ggplot2
– shiny
– lubridate
– knitr
– data.table