Forecast Potential System Demands Based On Historical Data
Accurate gas load forecasting is an essential practice for increasing revenue and meeting the demands of your pipeline customers.
- Can your pipeline handle the increased demand resulting from a record breaking cold holiday?
- What is the optimal day of the week and time of the day to schedule much needed maintenance on a pipeline?
- Do you need to determine a true forecast of your pipeline system supply?
- Do you have access to historical data for your pipeline network?
LoadForecaster is an application Gregg Engineering has developed to give operators the ability to forecast potential demands on their gas pipeline systems based on historical consumption data such as weather, day of the week, holidays, or essentially any type of statistical information. Using high tech and state-of-the-art Neural Networks (artificial intelligence), Regression and Genetic Algorithms, LoadForecaster performs a constant analysis to account for a multitude of transient conditional changes in the supply and demand of a pipeline system. Which means, by utilizing Neural Networks, LoadForecaster will get even smarter (and more accurate) as time goes by for predicting pipeline loads. And regardless of the software that you may currently be using for your hydraulic simulation modeling, the data from LoadForecaster will integrate seamlessly as a standalone application or fully integrate with NextGen. So with a little info from the past coupled with advanced technology, you can increase future revenues and be better prepared to meet the demands of your pipeline customers.
LoadForecaster will enable you to:
- Calculate a “forecast” of demand in order to maximize revenue by utilizing historical data to predict future values.
- Use virtually any historical parameter to calculate future predictions.
- Perform analyses to account for a multitude of transient conditional changes in the supply and demand of a pipeline system.
- Perform short, medium and long term load forecasting.
- Access forecast data simultaneously from multiple secure log-ins.