WSN Anomaly Traffic Isolation Using AI Detection and 5G Slicing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
IoT networks face security risks due to open platforms that increase the risk of anomaly traffic, which can compromise the integrity and efficiency of the network.
Innovation Solution
Implementing AI/ML-based detection and classification models in a WSN smart base station (WSBS) to identify anomaly traffic, reconfigure the WSN topology, and utilize 5G network slicing to segregate anomaly traffic into a dedicated network slice instance (NSI) for secure forwarding through firewall services.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the IoT platform is opened to different application providers and devices, then the usability and reach of IoT applications are improved, but security risks and exposure to anomaly traffic increase
Solution Approach 1:
The patent segments the network traffic into normal traffic and anomaly traffic, routing them through different paths. The WSN is divided into normal communication channels and specialized anomaly handling paths, allowing the platform to maintain openness while isolating security risks through structural segmentation of traffic flows
Solution Approach 2:
The patent introduces intermediary components including a detection model at the central office, classification models at the WSBS, and dedicated anomaly traffic paths. These intermediaries act as mediators between the open platform and the core network, filtering and directing anomaly traffic to prevent direct exposure to vulnerable systems
2Reliability
If anomaly traffic is detected and a special path is created to segregate it, then security risks are reduced, but network complexity and resource allocation overhead increase
Solution Approach 1:
The patent implements dynamic network configuration where the WSN topology and resource allocation are automatically adjusted based on real-time anomaly detection. The system transitions from static network configuration to dynamic reconfiguration, creating special paths only when anomaly traffic is detected and removing them when not needed, thereby managing complexity through adaptability rather than permanent structural changes
Solution Approach 2:
The patent establishes a feedback loop where the detection model continuously monitors traffic, triggers reconfiguration when anomalies are detected, and allows for dynamic adjustment of security measures. This feedback mechanism enables the system to respond to security threats in real-time while automatically managing the complexity of network configuration through closed-loop control
3Measurement precision
If AI/ML detection models are deployed at the WSBS and central office, then anomaly detection capability is improved, but processing overhead and energy consumption increase
Solution Approach 1:
The patent segments the AI/ML processing workload between the central office and the WSBS. The detection model runs at the central office for comprehensive analysis, while classification models are deployed at the WSBS for local traffic categorization. This segmentation distributes computational energy consumption across different network nodes, reducing the burden on any single device while maintaining high detection accuracy
Solution Approach 2:
The patent applies local quality by deploying different types of AI/ML models at different locations based on their specific needs. Lightweight classification models are placed at the WSBS for immediate local decision-making, while more comprehensive detection models run at the central office with better computational resources. This localized approach optimizes energy usage by matching processing capability to operational requirements at each node
Data Source
AI summary
Security protocols and techniques are provided to reduce security risks posed by anomaly traffic in a WSN. The WSN includes a WSN base station that communicates with one or more IoT servers over a 5G network or other backbone network. The WSN is managed by a WSN Central Office. The WSN base station monitors IoT traffic based on a detection model trained at a central office and detects the presence of anomaly traffic. Responsive to the detection of the anomaly traffic, the WSBS triggers a reconfiguration of the WSN to create a special path for the anomaly traffic to minimize the impact of the anomaly traffic on the WSN. Additionally, the central office can request the 5G network to update the NSI allocation to dedicate a network slice instance (NSI) for the anomaly traffic to segregate the anomaly traffic from the normal IoT traffic in the 5G network.