A Steam Load Forecasting Technique for Central Heating Plants

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. Thi...

Full description

Saved in:
Bibliographic Details
Main Authors: Lin, Mike C, Carnahan, James V
Format: Report
Language:English
Subjects:
Air Condition, Heating, Lighting & Ventilating
ARIMA MODELS
ARMY
ATMOSPHERIC TEMPERATURE
BOILERS
BOX JENKINS METHOD
BUILDINGS
CENTRAL HEATING PLANTS
EFFICIENCY
ERRORS
FORECASTING
HEAT TRANSFER
HEATING
HEATING PLANTS
IDENTIFICATION
PE4A161102
PREDICTIONS
SAVINGS
STEAM
TEMPERATURE
TIME SERIES ANALYSIS
TRANSFER FUNCTIONS
VARIATIONS
WEATHER
WUEA-EC0
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.