Do you have questions about Data Science?

We’d love to hear from you. 

Contact

Case study: Energy quantity forecast in the gas industry

A service provider in the energy industry has asked COSMO CONSULT to develop a model for forecasting short-term energy needs to automate planning processes and achieve savings in energy purchasing. The company thus improved its forecast accuracy by about five percent and saved about half a million euros.

Key facts

  • Forecasting gas quantities with different features
  • Considering specific behaviors of the gas forecasting time series
  • Incorporating and modeling seasonal volatility
  • Achieving forecasting quality up to 94%

Initial situation

In the energy industry, short-term energy forecasts are standard practices used to ensure that the purchasing of quantities is as cost-effective as possible. A service provider for smaller public utilities and providers calculated the forecast based on a simple mathematical formula. The disadvantage: The forecast formula could not respond to short-term trends or shifts in the price levels. The forecast was therefore error-prone especially during certain seasons.

COSMO CONSULT was commissioned to improve that basic energy quantity forecast in order to automate planning processes and achieve savings in energy purchasing.

Approach

As a first step, the project team eliminated the outliers and then constructed specific features using nonlinear optimization techniques. In addition to trend and seasonal components, the seasonal variance and calendar effects were taken into account. The weather data, on the other hand, were discarded because they would have not systematically improved the results. To determine the trend and seasonal component, classical forecasting methods such as ARIMA and exponential smoothing were used. Machine learning methods such as gradient boosting were also used to model the stochastic component. The corresponding R code was contained in a DLL file and was easily integrated into the customer's system. The developed algorithm can automatically remove outliers and perform forecasting with the optimized model, so the results can be displayed in the desired form.

Additional benefit

The service provider achieved a drastic improvement in forecast accuracy of about 5% with simultaneous savings of approximately € 500,000. In addition, planning processes were improved and energy purchasing became more efficient.

Do you have questions about Data Science?

We’d love to hear from you. 

Contact

Ask our experts

COSMO CONSULT has many years of experience in providing digital solutions in the field of data science. Our services are based on a clear approach, detailed knowledge of business processes, and excellent product expertise. Our experts will be happy to advise you on the unique possibilities available to you when you use modern software technologies. Please give us a call! We look forward to talking with you on how your business can enter the digital age.

Contact Us!

COSMO CONSULT International

COSMO CONSULT SI GmbH
Lothringerstraße 14
1030 Wien
E-Mail
COSMO CONSULT
201 rue Carnot
94120 Fontenay-sous-Bois
+33 1 83010360
E-Mail
COSMO CONSULT
Schoenebergerstr. 15
10963 Berlin
+49 30 343815-0
+49 30 343815-111
E-Mail
COSMO CONSULT S.L.
Vallespir, 19 4ª Módulo 2
08173 Sant Cugat del Vallès, Barcelona
+34 902820242
+34 943313002
E-Mail
COSMO CONSULT AB
Ralambsvaegen 17
11259 Stockholm
+46 8 7998660
E-Mail
COSMO CONSULT
Ruetistrasse 13
8952 Schlieren
+41 44 8306465
E-Mail
COSMO CONSULT Business S.L.
Presidente Riesco 5711, Oficina 802b
Las Condes, Santiago de Chile
+569 73769126
E-Mail
COSMO CONSULT Business S.L.
Avenida Cra. 45 # 114-78, Piso 6
Bogotá - Colombia
+57 320 7935148
E-Mail
COSMO CONSULT Business S.L
Checoslovaquia E10-105 y Eloy Alfaro
Quito, Ecuador
‪+593 99 608 4180
E-Mail
COSMO CONSULT Business S.L.
Rodolfo Gaona 81 Piso 7
Colonia Lomas de Sotelo
México, D.F. 11200
+52 55 2452-9200
E-Mail
Edificio Magel, Segundo Piso
Ave Samuel Lewis, Urb. Obarrio,
Ciudad de Panamá, República de Panamá
+507 62800343
E-Mail