Power IoT Security Identification for Trust-Based Error Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing Internet of Things (IoT) systems lack effective security protection methods, particularly in the context of power systems, which are vulnerable to data leakage and privacy breaches due to inadequate identification and management of security errors in data sources, channels, and storage.
Innovation Solution
An information identification-based power IoT protection method that performs security identification on data sources, channels, and storage, calculates fuzzy-uncertainty three-dimensional trapezoidal fuzzy sets for data transmission and storage scales, determines information gain and loss values, and constructs an objective function using an extreme learning machine method to obtain a target control input for minimizing errors and maximizing trust degrees.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If security identification is performed on data source, data channel, and data storage in power IoT systems, then data security and privacy protection are improved, but system complexity and computational overhead increase
Solution Approach 1:
The patent segments security identification into three distinct modules: data source identification, data channel identification, and data storage identification. Each module independently processes specific aspects of data security, allowing the complex security task to be divided into manageable components that can be processed separately while maintaining overall system security.
Solution Approach 2:
The patent introduces fuzzy-uncertainty three-dimensional trapezoidal fuzzy sets as an intermediary mechanism to bridge the gap between security identification requirements and system operation. These fuzzy sets serve as a mediator that transforms complex security parameters into controllable inputs for the extreme learning machine, reducing the direct complexity burden on the system.
2Measurement precision
If fuzzy-uncertainty three-dimensional trapezoidal fuzzy sets are calculated using statistical analysis method, then measurement precision of data transmission and storage is improved, but computational time and processing complexity increase
Solution Approach 1:
The patent changes the parameter representation from traditional crisp values to fuzzy-uncertainty three-dimensional trapezoidal fuzzy sets. This parameter transformation allows the system to capture measurement uncertainties and variations more accurately while providing a structured framework that can be processed efficiently by the extreme learning machine algorithm.
Solution Approach 2:
The patent replaces traditional mechanical statistical analysis methods with an extreme learning machine-based computational approach. The extreme learning machine substitutes conventional iterative optimization mechanisms with a more efficient single-pass learning algorithm, significantly reducing computational time while maintaining measurement precision.
3Productivity
If objective function is solved using extreme learning machine method to obtain target control input, then productivity of security optimization is improved, but algorithm complexity and training requirements increase
Solution Approach 1:
The patent performs preliminary action by pre-training the extreme learning machine algorithm with relevant security data and fuzzy set parameters before actual security optimization. This preliminary training phase prepares the algorithm to quickly process security identification results and generate optimal control inputs without requiring complex real-time iterations, thereby improving productivity while managing algorithm complexity.
4Reliability
If information gain value and information loss value are calculated to determine trust degree, then reliability of security assessment is improved, but computational overhead and processing complexity increase
Solution Approach 1:
The patent applies local quality by calculating information gain and information loss values for specific local aspects of data security (data source, data channel, data storage) rather than treating security as a monolithic concept. This localized calculation approach improves assessment reliability by capturing nuanced security characteristics while reducing overall processing complexity through modular computation.
Data Source
AI summary
The present disclosure provides an information identification-based power Internet of Things protection method, and the method includes that: the safety identification errors of a source network, a channel network and a storage network of a system and the safety identification errors of a place name, a user and a node corresponding to each network are respectively determined by using a statistical analysis method; an information loss value and an information gain value are calculated according to the safety identification errors, the trust degree is calculated according to the information loss value and the information gain value, and a target function is obtained by maximizing the credibility and minimizing the safety identification error to obtain target control input by using a baseline learning machine method, so that the electric power Internet of Things system is controlled according to the target control input.