Action optimization device, method and program

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current optimization systems for controlling environments in buildings, such as air conditioning and cleaning, face challenges with time lags in responding to non-optimal conditions and inability to account for medium-term and long-term changes in people flow, leading to suboptimal energy consumption and comfort issues.

Innovation Solution

An action optimization device and method that uses an environment reproduction model trained with time/space-interpolated data to predict changes in environmental states and an exploration model to explore optimal actions, allowing for flexible and reliable control across various conditions, including heat accumulation and energy management.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If feedback-type optimization systems are used to control environment operations, then optimization can be achieved based on actual measurements, but time lags occur until non-optimal states are detected and corrected

Engineering Contradiction:
Improveoptimization reliabilityVSAvoidtime lag
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent implements feedforward control by predicting future environmental states and people flow patterns before they actually occur. The system uses learned models to anticipate changes in temperature, humidity, and occupancy, allowing the air conditioning system to adjust in advance rather than reacting after deviations are detected, thereby eliminating time lags while maintaining optimization reliability.

Inventive Principle:
Principle #10Preliminary action

2Productivity

If simple people flow ratio multiplication is used to predict people flow, then calculation is simple, but medium-term and long-term changes in people flow cannot be accounted for

Engineering Contradiction:
Improvecalculation efficiencyVSAvoidpeople flow prediction accuracy
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The patent transforms the people flow prediction approach by changing from simple ratio multiplication to a learned prediction model that processes multiple input parameters including historical people flow data, event information, weather conditions, and temporal patterns. This allows the system to capture medium-term and long-term changes in people flow while maintaining computational efficiency through the learned model's optimized parameters.

Inventive Principle:
Principle #35Parameter changes

3Loss of energy

If upper limit of energy consumption is simply adjusted without estimating control change effects, then energy saving can be pursued, but interaction effects such as heat accumulation and cold/hot air flow are not considered

Engineering Contradiction:
Improveenergy consumptionVSAvoidcontrol optimization reliability
Core Design Contradiction:
Loss of energyVSReliability

Solution Approach 1:

The patent implements a comprehensive feedback mechanism where the learned model continuously predicts the effects of control changes on environmental parameters including temperature distribution, heat accumulation, and air flow patterns. The system uses these predictions to adjust energy consumption limits dynamically, considering interaction effects between different spatial zones and temporal patterns, thereby achieving reliable control optimization that balances energy saving with environmental comfort.

Inventive Principle:
Principle #23Feedback

Data Source

PatentEP3832556B1Action optimization device, method and program
Publication Date: 2023.12.13 NIPPON TELEGRAPH & TELEPHONE CORP
  • EP3832556B1 patent drawingFigure 1
  • EP3832556B1 patent drawingFigure 2
  • EP3832556B1 patent drawingFigure 3

AI summary

Provided is a highly reliable technology for optimizing an action for controlling an environment in a target space. An action optimization device for optimizing an action for controlling an environment: acquires environmental data related to a state of the environment; performs time/space interpolation on the acquired environmental data; trains an environment reproduction model, based on the time/space-interpolated environmental data, such that, when a state of an environment and an action for controlling the environment are input, a correct answer value for an environmental state after the action is output; trains an exploration model such that an action to be taken next is output when an environmental state output from the environment reproduction model is input; predicts a second environmental state corresponding to a first environmental state and a first action by using the trained environment reproduction model; explores for a second action to be taken for the second environmental state; and outputs a result of the exploration.