Forecaster Power

Highlights

Forecaster is the application designed to meet the needs of short- and medium-term forecasting for the energy market. Provides demand forecasting with hourly detail for each point of delivery or aggregates,  on different time frames, according to the need of energy market. It provides functions to examine the energy demand forecasting in order to verify the quality of the result and to operate by exceptions only on points that do not perform in an optimal way.

Business Context

The energy market has peculiar demand forecasting problems, such as the need to submit detailed forecasts to grid operators, or the need to operate on the day ahead market. Measures come from thousands of meter devices, producing hourly or even more detailed time series. Customer behaviors are very different from one another: industrial electricity usage is driven by production schedules, while domestic usage is sensitive to temperature, so different load curves need to be treated in the most appropriate way, in order to take all the different patterns into account. A poorly accurate load forecast can produce very expensive unbalancing.

ì4C Application

Forecaster is the Advanced Analytics Application designed to meet the needs of short- and medium-term forecasting for the energy market. In addition to providing load forecasts with hourly detail for each point of delivery or aggregates,  on different time frames, it provides a wide range of functions to monitor the performance typical of the energy market, such as unbalancing. The forecasting software uses the hourly detail to guarantee a forecast which is extremely sensitive to portfolio variations, heat factors or sudden variations in the production patterns of each single PoD measured on an hourly basis. Each point is assigned to a suitable forecasting class on the basis of the data available. The automated process follows the point in time and allocates it to a different, more suitable class when the appropriate data is available. This method combines the benefit of point per point forecasting – sensitivity, reactivity, level and profile accuracy – with the quick processing of clusters.

Business Pain – Key Features

  • Take into account Energy Market peculiarities
  • Market zones
  • Market schedules
  • Profiles for new customers
  • Unbalancing Economics KPI
  • Forecast management for market zones and PoD
  • Produce accurate forecasts to reduce unbalancing
  • State-of-the-art statistical forecasting methods
  • Arima, ARMAX, AREG, Exponential Smoothing
  • Forecasts at any level of detail
  • Flexible forecasting horizon
  • Statistical KPI’s
  • Minimize the statistical know-how required
  • Automated modeling for less confident users
  • Stepwise selection, self-identification
  • Modeling logic based on meter clustering
  • KPI driven intervention strategy
  • Not a black box: advanced users have free access to models
  • Reduce management effort
  • All operations can be scheduled
  • Picker for data acquisition
  • KPI for accuracy assessment
  • Alerts