Acquiring a user consumption pattern of domestic hot water and controlling domestic hot water production based thereon
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems for domestic hot water production and distribution lack accuracy in predicting consumption patterns, leading to inefficient energy use and increased environmental footprint, as they rely on fixed schedules and monitoring systems that do not account for individual user habits.
Innovation Solution
A computer-implemented method using a user-consumption-pattern-determination algorithm trained on historical data from multiple users, employing machine learning algorithms to accurately forecast domestic hot water consumption by analyzing heat storage tank data, allowing for adaptive control of water heating processes to match individual usage patterns.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If fixed schedules and monitoring systems are used to control domestic hot water production, then system operation is simplified, but prediction accuracy of consumption patterns deteriorates
Solution Approach 1:
The system transitions from static fixed schedules to dynamic adaptive control by continuously learning user consumption patterns through machine learning algorithms. The control parameters are dynamically adjusted based on real-time data analysis, enabling the system to adapt to changing user habits while maintaining operational simplicity.
Solution Approach 2:
The system performs self-learning and self-optimization by automatically analyzing consumption data and adjusting control strategies without requiring manual intervention. The machine learning model continuously improves prediction accuracy by learning from historical data, enabling the system to serve itself while enhancing performance.
2Reliability
If fixed minimum temperature is maintained throughout the day to ensure sufficient hot water, then user comfort is guaranteed, but energy consumption increases
Solution Approach 1:
The system performs preliminary heating actions based on predicted consumption patterns, pre-heating water before peak demand periods are anticipated. This allows the system to maintain user comfort by having hot water ready while avoiding continuous heating, thereby reducing overall energy consumption.
Solution Approach 2:
The system dynamically changes temperature parameters based on predicted user needs and ambient conditions. Instead of maintaining a fixed minimum temperature, the control strategy adjusts temperature setpoints according to forecasted consumption, enabling energy-efficient operation while ensuring comfort requirements are met when needed.
3Reliability
If more heat is stored in the tank to ensure sufficient hot water supply, then availability of hot water is improved, but energy efficiency deteriorates due to excessive heat storage
Solution Approach 1:
The system dynamically adjusts heat storage levels based on real-time consumption pattern analysis and predictions. Rather than maintaining excessive heat storage, the system optimizes storage capacity to match actual user needs, reducing thermal losses while ensuring adequate hot water availability during demand periods.
Solution Approach 2:
The system implements closed-loop feedback by continuously monitoring actual consumption against predicted patterns and adjusting heat storage strategies accordingly. This feedback mechanism enables the system to maintain optimal heat storage levels, avoiding both excessive storage (which wastes energy) and insufficient storage (which compromises availability).
Data Source
Figure 1
Figure 2~3
Figure 4
AI summary
The present disclosure relates to a computer-implemented method of acquiring a user consumption pattern (UCP) of domestic hot water, the method including: acquiring data representing an amount of heat ΣQT1 tapped from a heat storage tank 20 within a first time period T1, generating a first history H1 or data collection of data representing amount of heat ΣQ, in particular cumulative heat, tapped from the heat storage tank 20 over a number of first time periods T1, and acquiring a user consumption pattern of domestic hot water by applying a user-consumption-pattern-determination-algorithm to the generated first history H1 or data collection of data representing amount of heat tapped from the heat storage tank 20), wherein the user-consumption-pattern-determination-algorithm is an algorithm trained on history(ies) or data collection(s) representing amount of heat ΣQ tapped and defining user consumption patterns of domestic hot water using one or more machine-learning-algorithms. Moreover, the disclosure relates to a controller 1 and a system 100 for controlling domestic hot water production and/or distribution. The disclosure further relates to a computer program and a computer-readable medium having stored the computer program thereon.