Building System Selective Data Forecasting

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Building energy managers face challenges in generating accurate energy forecasts due to the use of inaccurate data from external services, which can lead to incorrect predictions and inefficient energy management.

Innovation Solution

A building system that identifies inaccurate data points by comparing historical prediction values with actual values, replacing them with predetermined values, and using these updated sets to train prediction models for more accurate energy output predictions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If external services are used to provide forecast data, then the building system can obtain weather and occupancy predictions, but the accuracy of the forecast data deteriorates due to inaccurate external predictions

Engineering Contradiction:

Improveability to obtain forecast dataVSAvoidaccuracy of forecast data

Core Design Contradiction:

Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

The patent introduces an intermediary validation mechanism that sits between external forecast services and the building management system. This intermediary layer compares external predictions with actual historical data, identifies accurate versus inaccurate time-steps, and selectively filters which external forecasts to trust. This resolves the contradiction by maintaining the ability to use external services while filtering out inaccurate predictions through a mediating validation process.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system implements feedback by continuously comparing external forecast predictions with actual historical measurements. The accuracy determination module uses this feedback loop to learn which external services and time-steps are reliable, then adjusts its selection of external forecasts accordingly. This feedback mechanism resolves the contradiction by using past performance information to improve future forecast accuracy while maintaining adaptability to use external services.

Inventive Principle:

Principle #23Feedback

2Device complexity

If all external forecast data is used without differentiation, then the building system can maintain simple processing, but the energy forecast accuracy deteriorates due to inclusion of inaccurate data

Engineering Contradiction:

Improvedata processing complexityVSAvoidenergy forecast accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The patent segments the external forecast data into distinct time-step categories: accurate time-steps and inaccurate time-steps. Rather than treating all external data uniformly, the system divides the data stream and applies different handling rules to each segment. This segmentation approach resolves the contradiction by adding targeted complexity only where needed (in accuracy determination) while maintaining simple processing for the majority of reliable data.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system applies local quality by treating different time-steps of external forecast data differently based on their demonstrated accuracy. Instead of applying a uniform quality standard to all data, the system identifies and applies higher scrutiny only to specific time-steps that have shown inaccuracy patterns. This resolves the contradiction by localizing the complexity of validation to only where it is needed, maintaining overall processing simplicity.

Inventive Principle:

Principle #3Local quality

3Measurement precision

If historical data is analyzed to identify accurate time-steps, then the accuracy of energy forecasts improves, but the processing time and computational resources increase

Engineering Contradiction:

Improveenergy forecast accuracyVSAvoiddata processing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary action by pre-analyzing historical forecast data during off-peak periods to establish accuracy profiles for different external services and time-steps. This preliminary analysis creates lookup tables or confidence scores that can be quickly referenced during real-time operations. This resolves the contradiction by moving the computationally intensive historical analysis to advance preparation, reducing real-time processing time while maintaining high forecast accuracy through pre-computed accuracy information.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS11636310B2Building system with selective use of data for probabilistic forecasting

Publication Date: 2023.04.25 TYCO FIRE & SECURITY GMBH

AI summary

A building system for generating input forecast data. The building system comprising one or more memory devices configured to store instructions thereon that, when executed by one or more processors, cause the one or more processors to retrieve a current prediction set of measurements comprising current values associated with a plurality of time-steps; identify time-steps of the plurality of time-steps for which historical prediction values of a historical prediction set of measurements are outside of a tolerance of corresponding historical actual values of a historical actual set of measurements; replace each current value of the current prediction set of measurements that is associated with the identified time-steps with a predetermined value to generate an updated prediction set of measurements; and provide the updated prediction set of measurements to a prediction model.