ML-Based Wireless Network Switching for Live Event Streaming
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Live event data streaming over wireless networks at venues, such as Wi-Fi or cellular networks, often experiences high latency and instability due to large crowds, leading to poor streaming quality and potential interruptions, as users cannot reliably switch between networks without disrupting the data stream.
Innovation Solution
Implementing a machine learning algorithm on mobile devices to assess and automatically switch between Wi-Fi, cellular, and Bluetooth connections based on latency and stability parameters, ensuring real-time delivery of live event data by determining the optimal connection for continuous and high-quality streaming.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If users manually switch between wireless networks to improve streaming quality, then latency and stability may improve, but the data stream may be interrupted and the operation becomes complex
Solution Approach 1:
The mobile computing device automatically monitors network conditions and switches between wireless networks without user intervention. The system self-manages network selection by evaluating latency and stability parameters, eliminating the need for manual user action while maintaining continuous data stream delivery.
Solution Approach 2:
The system continuously monitors network performance parameters (latency and stability) and uses this feedback to dynamically switch between networks. The machine learning algorithm processes real-time network condition data to determine optimal network transitions, ensuring uninterrupted streaming while adapting to changing network environments.
2Measurement precision
If the system monitors multiple network connections continuously, then the optimal connection can be determined accurately, but the device complexity increases
Solution Approach 1:
A machine learning algorithm serves as an intermediary that processes network monitoring data and determines optimal connections. Instead of complex manual evaluation, the ML model acts as a mediator between raw network metrics and decision-making, simplifying the system architecture while maintaining precise assessment capabilities through learned patterns from network behavior data.
Data Source
AI summary
A method for real-time delivery of live event data to a first mobile computing device at a live event based on a machine learning algorithm includes receiving a first data representation of a live audio signal via a Wi-Fi network connection. The method also includes receiving a second data representation of the live audio signal via a cellular network connection. The method also includes receiving a third data representation of the live audio signal from a second mobile computing device at the live event via a Bluetooth connection. The method also includes determining whether the first data representation, the second data representation, or the third data representation is being received via an optimal connection using a machine learning algorithm. The method also includes processing the first data representation, the second data representation, or the third data representation into a live audio stream based on the determined optimal connection.