Power Consumption Estimation Using Regression and Reference Signals
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing power consumption estimation techniques for facilities in architectural structures have low accuracy due to assuming constant base power consumption, which varies with other equipment usage, and require additional systems to monitor population for facility without operation status data, increasing costs.
Innovation Solution
A power consumption estimation device that uses multiple regression analysis with time-series data of total power consumption and operation parameters of facilities, generating reference signals to simulate non-monitored power consumption and calculate facility-specific power usage without the need for individual meters or population monitoring systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If base power consumption is estimated as constant using total power consumption data when air conditioners are not operating, then the system complexity is reduced, but the estimation accuracy of power consumption deteriorates
Solution Approach 1:
The patent transforms the static constant base power model into a dynamic time-series model. The base power consumption is no longer fixed but varies over time according to the operational patterns of other facilities. This is achieved by using time-series regression analysis that captures the temporal variations in base power consumption, allowing the model to adapt to changing conditions while maintaining reasonable system complexity.
Solution Approach 2:
The patent changes the parameter representation of base power from a single constant value to a time-varying parameter. By introducing time-series data and using regression coefficients that capture temporal patterns, the model can represent base power consumption as a dynamic parameter rather than a static one, thereby improving estimation accuracy without requiring complex additional systems.
2Measurement precision
If individual electric power meters are provided for each facility, then the estimation accuracy of power consumption is improved, but the system cost increases
Solution Approach 1:
The patent extracts the estimation problem from the context of individual facility measurement. Instead of measuring each facility's power consumption directly with separate meters, the method extracts the base power consumption pattern from aggregate data and uses it to infer individual facility consumption through regression analysis. This extraction approach achieves accurate estimation without the need for expensive individual measurement systems.
Solution Approach 2:
The patent introduces base power consumption as an intermediary variable that mediates between total power consumption data and individual facility power consumption estimation. By using base power as a mediator in the regression model, the system can derive accurate individual facility consumption data from aggregate measurements, avoiding the need for direct individual measurement infrastructure.
3Adaptability or versatility
If population monitoring systems are introduced to estimate power consumption of facilities without operation status data, then the estimation capability is improved, but the system complexity and cost increase
Solution Approach 1:
The patent creates a universal regression-based estimation framework that can handle multiple types of facilities with different data availability. The same time-series regression model can estimate power consumption for facilities with monitored operation status, facilities without operation status data, and even predict base power consumption patterns. This multi-functional approach eliminates the need for separate population monitoring systems while maintaining versatile estimation capability.
Data Source
AI summary
A power consumption estimation device (10) which estimates power consumption of each of one object facility (100) or more whose operation statuses can be monitored includes: a total power vector generation unit (32) to acquire time-series data of total power consumption; a status matrix generation unit (34) to acquire time-series data of an operation parameter of the one object facility (100) or more; a reference signal generation unit (36) to generate one reference signal or more; a contribution degree estimation unit (38) to perform multiple regression analysis by taking the total power consumption as an objective variable, and the operation parameter of the one object facility (100) or more and a component value of the one reference signal or more, as explanatory variables, to thereby calculate a contribution degree of each of the one object facility (100) or more; and a breakdown calculation unit (42) to multiply the contribution degree of the object facility (100) and the operation parameter of the object facility (100), to thereby calculate power consumption of the object facility (100).