Steam-load-forecasting technique for central-heating plants. Final report
Because boilers generally are most efficient at full loads, the Army could achieve significant savings by running fewer boilers at high loads rather than more boilers at low loads. A reliable load prediction technique could help ensure that only those boilers required to meet demand are on line. This report presents the results of an investigation into the feasibility of forecasting heat plant steam loads from historical patterns and weather information. Using steam flow data collected at Fort Benjamin Harrison, IN, a Box-Jenkins transfer function model with an acceptably small prediction error was initially identified. Initial investigation of forecast model development appeared successful. Dynamic regression methods using actual ambient temperatures yielded the best results. Box-Jenkins univariate models' results appeared slightly less accurate. Since temperature information was not needed for model building and forecasting, however, it is recommended that Box-Jenkins models be considered prime candidates for load forecasting due to their simpler mathematics.
- Research Organization:
- Army Construction Engineering Research Lab., Champaign, IL (United States)
- OSTI ID:
- 6959361
- Report Number(s):
- AD-A-255455/8/XAB; CERL-TR-E--92/08
- Country of Publication:
- United States
- Language:
- English
Similar Records
Bayesian forecasting for adaptive seasonal short-term load forecasting models with a comparative study
Automatic load forecasting. Final report
Related Subjects
320603* -- Energy Conservation
Consumption
& Utilization-- Municipalities & Community Systems-- Public Utilities-- (1980-)
BOILERS
BUILDINGS
CENTRAL HEATING PLANTS
EFFICIENCY
ENERGY CONSERVATION
ENERGY TRANSFER
ERRORS
FORECASTING
HEAT TRANSFER
LOAD ANALYSIS
LOAD MANAGEMENT
MANAGEMENT
MATHEMATICAL MODELS
MATHEMATICS
MILITARY FACILITIES
REGRESSION ANALYSIS
STATISTICS
STEAM
STEAM GENERATION
VARIATIONS
WEATHER