Electronic device and control method thereof
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing air conditioning systems face challenges in efficiently controlling energy consumption, as initial setting values provided by manufacturers are often inappropriate for non-peak load conditions, and coordinating different air conditioning devices from various manufacturers is difficult.
Innovation Solution
An electronic device equipped with a communicator, processor, and memory, which applies target information to a learning network model to generate control information for air conditioning devices. The learning network model identifies errors in energy consumption estimation, generates virtual data, and is retrained to optimize setting values and minimize energy consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Use of energy by moving object
If initial setting values provided by the manufacturer are used, then the air conditioning system can be operated, but energy consumption is not optimized for non-peak load conditions
Solution Approach 1:
The patent implements dynamic adjustment of air conditioning setting values based on real-time monitoring of load conditions. The system continuously adapts operational parameters such as temperature setpoints and equipment runtime according to actual cooling/heating demands, transitioning from static manufacturer defaults to dynamic optimization that responds to changing environmental conditions and occupancy patterns.
Solution Approach 2:
The system incorporates feedback mechanisms that monitor energy consumption, indoor environmental quality, and load conditions, then use this information to adjust setting values. The feedback loop enables the system to learn from past performance and continuously refine operational parameters to minimize energy consumption while maintaining comfort standards across varying load conditions.
2Productivity
If each air conditioning device is controlled independently by different manufacturers, then device-specific optimization is achieved, but comprehensive system-wide control is difficult
Solution Approach 1:
The patent merges control functions into a centralized system that coordinates multiple air conditioning devices from different manufacturers. The control server aggregates data from various devices and issues coordinated control commands, enabling system-wide optimization while maintaining compatibility with diverse device protocols and interfaces, thus reducing overall control complexity.
Solution Approach 2:
The control system implements universal communication protocols and standardized interfaces that enable it to work with air conditioning devices from multiple manufacturers. The system performs multiple functions including data collection, analysis, decision-making, and command distribution across heterogeneous devices, creating a multi-functional platform that simplifies comprehensive control.
3Measurement precision
If the learning network model uses only existing learning data, then the model can be trained, but accuracy is insufficient when errors are present in energy consumption estimation
Solution Approach 1:
The system creates virtual data that replicates the structure and characteristics of real learning data but is synthetically generated to correct estimation errors. These virtual copies are designed to represent scenarios where energy consumption patterns should follow physical laws, providing the model with additional training examples that reinforce accurate estimation without requiring proportional increases in real-world data collection.
Solution Approach 2:
The patent transforms existing learning data by applying parameter changes that correct systematic errors in energy consumption estimation. The virtual data generation process modifies key parameters such as energy consumption values to align with physical reality while maintaining consistency with observed operational patterns, thereby improving model accuracy through parameter adjustment rather than raw data accumulation.
Data Source
Figure 1~2
Figure 3~4
Figure 5a~5b
AI summary
An electronic device is provided. The electronic device includes a communicator comprising a circuitry, a processor electronically connected to the communicator and controlling the communicator, and a memory electrically connected to the processor. The memory is configured to store instructions to control the processor to transmit control information acquired by applying target information of an air conditioning system to a learning network model to a plurality of air conditioning devices included in the air conditioning system via the communicator. The learning network model is a learning network model configured to, based on identifying that an error is present in an estimation result of energy consumption acquired based on a learning data, generate virtual data and be retrained based on the generated virtual data.