Retail Forecasting Solutions
Return to Energy Forecasting
If you are an energy retailer responsible for buying power or natural gas to meet
your customers' energy requirements, you need timely and accurate forecasts. Accurate
forecasts are the cornerstone of scheduling strategies, and will help you avoid
unnecessary imbalance charges and penalties. Itron's Retail Forecasting System will
help you develop accurate forecasts when you need them, so you have the time to
make the right decisions.
Itron's Retail Forecasting System is designed to generate forecasts for portfolios
of retail customers, where the portfolios can change on a daily basis. These forecasts
support scheduling of loads in day-ahead and balancing markets, as well as planning
for the longer term. For mass market customers, the system is configured to model
the profiling methods that are employed in each market area. Forecasts are then
scaled to represent the customers in that area.
For large interval metered customers, the forecasting system supports the use of
individual models and forecasts for each customer. Employing MetrixND® as the forecast engine, Itron's system allows
you to assign preconfigured modelling templates to each forecasting task, or develop
a customised model for a specific forecast element. This technique allows simple
models to be used for calendar-driven loads, while more complex models are used
for loads driven by weather, price, or other factors. Whether you operate in one
market region or multiple markets, Itron's Retail Forecasting System can be configured
and scaled to meet your needs.
Typical applications for Itron's Retail Forecasting Systems include:
- Portfolio forecasting for load profiled customers
- Individual customer forecasting for Interval metered customers
- Short-term forecasting for energy scheduling
- Long-term or life-of-contract forecasting for planning
Itron's Retail Forecasting System automates the forecasting process. The system
can be configured to forecast sub-hourly, hourly or daily loads for the balance-of-the-current
day, the next few days, or several years out. The system can import, via the Internet,
weather forecasts from one or more weather stations and one or more weather service
providers with all weather concepts supported. Built-in validation routines flag
errors in weather and load data, providing error trapping automatically for the
user. Mass market and individual customer forecasts can be reviewed individually
or in aggregate by scheduling point. A variety of on-line Quick Edit tools are available
to refine and adjust the model forecasts. The forecasting system is easily integrated
with upstream and downstream systems, providing automated real-time forecasting
capabilities.
Itron's Retail Forecasting System uses MetrixND to estimate statistical models of
customer load patterns and to calculate forecasts using these models. MetrixND is
a flexible modelling tool, widely used by energy forecasters throughout the world.
MetrixND puts the most advanced modelling techniques at your fingertips: an advanced
neural network, regression, exponential smoothing, and ARIMA. Designed to take advantage
of advanced Windows capabilities, the intuitive user interface and drag-and-drop
architecture streamlines the development of forecasting variables and models. Evaluation
graphs, statistics, and reports are readily available to assist in analyzing forecasts.
This interactive design strategy allows the forecast analyst to quickly evaluate
alternative models and select the model that works best for their particular data.
Accurate forecasts can provide a quick payback on your investment, so why wait?
Act now and have a system in place before your peak season. Call us at +31 20 60
65 225 or send an email to forecasting@itron.com
for more information or to schedule a live software demonstration.
System Features
Customised Configurations
Configured for retail forecasting with profile models, individual customer models,
or both. These forecasts can be mapped to one or more scheduling points. It can
be configured to forecast wholesale loads for individual delivery points or groups
of delivery points. The system can also be scheduled to update as needed during
the day.
Profiling Flexibility
The system can be configured to model the profiling method used in each market region.
These profile forecasts are then scaled to account for the portfolio of mass market
customers served on that day. These profile forecasts can also be adjusted to account
for losses.
Modelling Flexibility
The user manages lists of customers. Customers may be modelled individually, or
the customer loads can be aggregated into a meter group, allowing forecast models
to be applied to the group as a whole. A wide range of modelling methods is available
and there is no limit to the types of explanatory variables that can be used.
Built-in Scoring Algorithm
For interval metered customer loads, included is a built-in scoring algorithm to
help identify the best model type for each customer. The scoring statistics quantify
load variability and the importance of calendar effects, daily weather and price
sensitivity. As an option, rules can be implemented to automatically assign methods
to each forecast element.
Rapid Model Estimation
Once a method is selected either manually or by automatic assignment, the model
is populated with data from the meter or profile database tables, model weather
data for the appropriate weather zone, the forecast model coefficients are estimated,
and the estimated model is saved for use in forecast generation. These steps take
a few seconds for each model that needs to be estimated. Estimated models can be
exported for detailed analysis and development of refinements to the specification.
Rapid Forecast Execution
Estimated models are used to generate forecasts on a scheduled basis or on demand.
Forecast execution takes a few seconds per modelled item. If recent data are available
for calibration, forecasts are adjusted based on this recent history, using the
dynamic learning algorithm.
Flexible Forecast Schedules
Model forecasts for individual customers, groups of customers, or profile segments
are mapped to schedules for aggregation purposes. Typically one schedule will be
defined for each transmission zone or control area in the portfolio.
Weather Forecasts
Import via the Internet, weather forecasts from one or more weather stations and
one or more weather service providers. All weather concepts are supported including
temperature, humidity, dew point, cloud cover, wind speed, and precipitation.
Prior Hour Loads
The system can be configured to use real-time meter reads to drive the forecast.
Error Trapping
Built-in validation routines flag errors in weather and load data.
On-line Review
A variety of on-line Quick Edit tools are available for refining the model forecasts.
Publishing
Forecast results and corresponding weather data can be published by the forecast
operator to a variety of file formats including custom formats to support downstream
applications.
Integrates with Existing Databases
Tailored to work with your existing databases, including Access®, MV-90, MV-Star,
ORACLE®, SQL Server®, and SAP®.
Call us at +31 20 60 65 225 or send an email to forecasting@itron.com for more information or to schedule
a live software demonstration.
More Information
