Disruption-Tolerant Network Scheduling With Predicted Connection Windows
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing disruption-tolerant networks face challenges in maintaining data integrity and energy efficiency due to intermittent connectivity, leading to packet loss and excessive energy consumption in IoT devices, particularly in scenarios where direct connections are unreliable and latency is high.
Innovation Solution
A predictive method using lookup tables and machine learning algorithms, specifically long-short-term memory (LSTM) neural networks, to determine optimal time windows for data transmission, minimizing packet loss and optimizing energy usage by activating devices only during predicted connection windows.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If data packets are continuously transmitted in disruption-tolerant networks, then data delivery attempts are maintained, but packet loss increases and energy consumption rises
Solution Approach 1:
The system performs preliminary actions by predicting future connection windows before they occur. The electronic computing device uses machine learning models to forecast when connections will be available, allowing the end device to prepare and transmit data proactively during these predicted windows, rather than continuously attempting transmission
Solution Approach 2:
Instead of continuous transmission attempts, the system implements periodic action by scheduling data transmissions only during predicted connection windows. The machine learning model identifies recurring patterns in network availability, enabling the system to transmit data periodically when connections are expected to be available, reducing unnecessary energy consumption
2Reliability
If the end device continuously monitors and transmits data packets, then data integrity is maintained, but energy consumption increases significantly
Solution Approach 1:
The system implements feedback mechanisms where the electronic computing device receives acknowledgments about successfully received packets and uses this information to adjust future transmission strategies. The machine learning model is continuously refined based on actual connection outcomes, improving prediction accuracy over time and enabling more energy-efficient transmission decisions
Solution Approach 2:
The end device leverages the predictive capabilities provided by the electronic computing device to autonomously determine when to transmit data. Rather than continuously monitoring the network, the device can enter low-power states between predicted connection windows, using the predicted schedule to self-manage its transmission activities efficiently
3Productivity
If packet transmission is attempted during all time windows, then data delivery probability is maximized, but unnecessary transmission attempts increase energy waste
Solution Approach 1:
The system dynamically changes transmission parameters based on predicted connection characteristics. The machine learning model provides information about the likelihood and quality of upcoming connections, allowing the system to adjust transmission timing, data volume, and power state to optimize the balance between delivery probability and energy consumption for each specific time window
Data Source
Figure 1~2
Figure 3~4
AI summary
Method for operating a fault-resistant network between an electronic computing device and an end device by means of a network system, computer program product, computer-readable storage medium and network system. Method for operating a fault-resistant network (16), comprising the steps of: transmitting data packets (18) from the end device (12) to an electronic computing device (14), wherein each data packet (18) is assigned a respective timestamp (20) and a respective packet number (22) by means of the end device (12); receiving at least a part of the multitude of transmitted data packets (18); determining non-received data packets (18) based on the respective packet number (22); determining at least one time window (24) in which the non-received data packets (18) were sent, based on the timestamps (20) of the received data packets (18);Generating an information message (26) with the at least one determined time window (24); and transmitting the information message (26) to the terminal device (12) for future transmission of data packets (18) via the interference-resistant network (16). The invention further relates to a computer program product, a computer-readable storage medium, and a network system (10).