Prediction method, prediction device, and prediction program
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current heat source demand prediction methods for air conditioning in large facilities are inaccurate due to neglecting the surrounding environment of air conditioning control regions, leading to inefficient energy usage and comfort issues, as they rely solely on external parameters and do not consider factors like human presence and air conditioner settings.
Innovation Solution
A prediction method that uses parameters related to the surrounding environment, such as weather data and people flow, along with air conditioner settings to estimate heat demand for each air conditioning control region, allowing for more precise heat source demand prediction and control.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If only external parameters (outside air temperature, outside humidity) are used for heat source demand prediction, then the prediction method is simple, but the prediction accuracy decreases when surrounding environment conditions vary
Solution Approach 1:
The patent divides the building into multiple air conditioning control regions and performs heat source demand prediction separately for each region. By segmenting the prediction process at the regional level rather than using a single building-wide prediction, the system can capture local environmental variations and occupancy patterns, thereby improving prediction accuracy without significantly increasing overall system complexity
Solution Approach 2:
The patent applies local quality by incorporating region-specific parameters such as surrounding environment conditions and air conditioner settings into the prediction model for each air conditioning control region. This allows the prediction system to adapt to local variations in occupancy, environment, and equipment configuration, resolving the contradiction between simple methodology and accurate prediction
2Loss of energy
If heat source demand is overpredicted, then energy saving performance is deteriorated due to acquisition of unnecessary heat quantity, but if underpredicted, then comfort is deteriorated due to shortage of heat quantity
Solution Approach 1:
The patent incorporates feedback mechanisms by using actual heat consumption data from each air conditioning control region to continuously refine and update the prediction model. This feedback loop enables the system to learn from past performance, adjust to changing conditions, and improve prediction accuracy over time, thereby balancing energy efficiency with comfort reliability
Solution Approach 2:
The patent dynamically adjusts prediction parameters based on varying conditions including surrounding environment, occupancy patterns, and air conditioner settings. By changing parameters according to actual conditions rather than using fixed values, the system can optimize heat source demand prediction to avoid both overprediction (wasting energy) and underprediction (compromising comfort)
Data Source
AI summary
A prediction method of performing heat source demand prediction in a space having a predetermined air conditioning control region, includes predicting a required heat quantity in the air conditioning control region by using a predetermined parameter related to a surrounding environment of the air conditioning control region and a setting value of an air conditioner set in the air conditioning control region as inputs, and predicting a heat source demand of the entire space from the predicted required heat quantity for each air conditioning control region.