The Use of Extreme Value Theory for Forecasting Long-Term Substation Maximum Electricity Demand

Citation Author(s):
Yun
Li
Submitted by:
Yun Li
Last updated:
Mon, 07/15/2019 - 22:28
DOI:
10.21227/f1yn-1523
Data Format:
License:
0
0 ratings - Please login to submit your rating.

Abstract 

This dataset contains daily maximum load data with the average demand, customer count and PV capacity at two substations Arkana and Muchea, Western Australia used in the accepted IEEE Transactions on Power Systemspaper titled “The Use of Extreme Value Theory for Forecasting Long-Term Substation Maximum Electricity Demand” by Li and Jones (2019).  The dataset spans from 01/01/2008 to 30/06/2022, part history (01/01/2008 to 16/09/2018) and part forecast (17/09/2018 to 30/06/2022).  The dataset is beneficial to various research such as long-term load forecast.

Instructions: 

The dataset contains two .CSV files. (1) The file “Arkana_daily_input_dat.csv” contains daily maximum load data with the average demand, customer count and PV capacity at Arkana substation. (2) The file “MUC_daily_input_dat.csv” contains daily maximum load data with the average demand, customer count and PV capacity at Muchea substation.

Comments

The major contribution of this paper is to propose a new method for forecasting substation long term maximum demand with two innovative features: 1) it ensures internal consistency, because it is fitted as a function of  trends in three common factors already required by utilities including customer count, average demand, and installed photovoltaic capacity and existing forecasts using extreme value theory, and 2) it is robust to changing network configurations (i.e., substation transfers).  The proposed approach is not only realistic and flexible to forecast maximum demand but also ensures consistent outcomes and messaging between the two outputs from energy consumption and maximum demand forecasts.

 

 

 

Submitted by Yun Li on Tue, 07/16/2019 - 00:08