Teitl: Data supporting "Predicting the energy demand of buildings during triad peaks in GB"

Dyfyniad
Marmaras C, Javed A, Cipcigan LM (2017). Data supporting "Predicting the energy demand of buildings during triad peaks in GB". Cardiff University. https://doi.org/10.17035/d.2017.0032657812

Manylion y Set Ddata

Cyhoeddwr: Cardiff University

Dyddiad (y flwyddyn) pryd y daeth y data ar gael i'r cyhoedd: 2017

Fformat y data: .xlsx

Amcangyfrif o gyfanswm maint storio'r set ddata: Llai na 100 megabeit

Nifer y ffeiliau yn y set ddata: 2

DOI : 10.17035/d.2017.0032657812

DOI URL: http://doi.org/10.17035/d.2017.0032657812

Disgrifiad

Paper abstract:

A model-based approach is described to forecast triad periods for commercial buildings, using a multi-staged analysis that takes a number of different data sources into account, with each stage adding more accuracy to the model. In the first stage, a stochastic model is developed to calculate the probability of having a “triad” on a daily and half-hourly basis and to generate an alert to the building manager if a triad is detected. In the second stage, weather data is analysed and included in the model to increase its forecasting accuracy. In the third stage, an ANN forecasting model is developed to predict the power demand of the building at the periods when a “triad” peak is more likely to occur. The stochastic model has been trained on “triad” peak data from 1990 onwards, and validated against the actual UK “triad” dates and times over the period 2014/2015. The ANN forecasting model was trained on electricity demand data from six commercial buildings at a business park for one year. Local weather data for the same period were analysed and included to improve model accuracy. The electricity demand of each building on an actual “triad” peak date and time was predicted successfully, and an overall forecasting accuracy of 97.6% was demonstrated for the buildings being considered in the study. This measurement based study can be generalised and the proposed methodology can be translated to other similar built environments.

2 datasets are provided (in .xlsx file format) with the data used in this publication.

File "input_data.xlsx" contains the triad peak demand data, the building energy demand data and the weather data in separate tabs. These data were used as inputs to the model described in this publication.

The Triads are the three half-hour settlement periods with highest system demand and are used by National Grid to determine charges for demand customers with half-hour metering and payments to licence exempt distributed generation. The triad peak demand data contain information about the dates, times and magnitude (in MW) of the 3 demand peaks of GB electricity system demand from 1990 to 2014.

The building energy demand data is the daily energy consumption of 6 commercial buildings in Manchester in kWh for the years 2012-2013.

The weather data are daily values of 10 weather attributes for the years 2012-2013. The attributes are:

1. Cloud Total Amount (in octas)

2. Cloud Base (in DM)

3. Wind Mean Speed (in knots)

4. Hourly Mean Wind Direction (in degrees)

5. Max Gust (in knots)

6. Air Temperature (in degrees Celsius)

7. Rainfall (in mm)

8. Hourly Global Radiation (in kj/sq.meter)

9. Relative Humidity (in %)

10. Sunshine Hours (in %)

File "output_data.xlsx" contains the model results, as presented in this publication. The Mean Absolute Percentage Error (MAPE) data, Mean Absolute Error (MAE) data, triad forecast data and power demand forecast data are presented in separate tabs.

The MAPE and MAE data (in %) are the forecast accuracy evaluation indices for the 11 different forecast scenarios and 6 buildings (as described in the paper).

The triad forecast data are the probability values (absolute) calculated with the triad probability assessment model described in the paper. Data from three different cases are provided, the daily interval case, the 5-day interval case and the half-hourly interval case.

The power demand forecast data contain information about the actual maximum power demand (in KW) and the forecasted maximum power demand (in KW) in each one of the considered commercial buildings. The forecasted power demand data were calculated with the model described in the paper.

Research results based upon these data are published at https://doi.org/10.1016/j.enbuild.2017.02.046