Energy Emission Management System Using Dual Prediction Correlation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current energy management systems for intensive energy consuming sites and sectors, such as manufacturing and industrial areas, primarily focus on energy consumption alone and lack comprehensive methods to effectively reduce greenhouse gas emissions, which are not sufficient for maximizing cost savings and environmental sustainability.
Innovation Solution
A system and method that utilize simultaneous prediction algorithms of Regression and Artificial Neural Networks to cross-verify energy use predictions, integrating energy consumption and greenhouse gas emission management, allowing for real-time monitoring and optimization of energy efficiency and emission reduction by comparing actual and predicted values.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If traditional energy management systems focus on energy consumption alone, then energy monitoring is simplified, but emission reduction effectiveness is insufficient
Solution Approach 1:
The patent combines energy consumption management and greenhouse gas emission management into a single integrated system. The E2M system simultaneously monitors both energy parameters (electricity, gas, oil consumption) and emission parameters (CO2, CH4, N2O emissions), allowing the system to achieve comprehensive emission reduction effectiveness without significantly increasing operational complexity. This merging approach ensures that energy efficiency improvements directly translate to emission reductions.
2Measurement precision
If multiple prediction techniques are used for energy estimation, then prediction accuracy is improved, but system complexity increases
Solution Approach 1:
The E2M system implements a feedback mechanism where multiple prediction techniques (regression analysis and artificial neural networks) generate predictions that are continuously compared against actual energy consumption data. The system uses correlation analysis to validate prediction accuracy and provides feedback signals when predictions deviate from actual values, allowing for continuous refinement of prediction models. This feedback loop ensures high prediction accuracy while maintaining manageable system complexity through automated validation processes.
3Productivity
If energy and emission data are integrated for comprehensive management, then cost savings are maximized, but data processing complexity increases
Solution Approach 1:
The E2M system is designed as a universal platform that handles multiple functions within a single integrated architecture. It simultaneously performs energy consumption monitoring, emission tracking, prediction analysis, correlation validation, and reporting functions. The system processes diverse data types (energy parameters, emission parameters, influencing variables) through a unified data processing framework, maximizing cost savings by identifying synergies between energy efficiency and emission reduction while managing data processing complexity through standardized multi-functional procedures.
Data Source
AI summary
A method of performing energy estimations operations in an intensive energy consuming site or system environment, the method comprising the steps of: (a) inputting a series of energy, emission and influencing data variables related to the intensive energy consuming site or system environment; (b) performing a first energy use prediction operation utilising a first prediction technique; (c) performing a second (simultaneous) similar energy use prediction operation utilising a second prediction technique; (d) correlating the results of the two techniques and; (e) providing a pass or fail signal depending on the level of correlation between the two techniques.