Optical Signal Power Estimation Using Deep Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current transmission network equipment struggles to predict and maintain optimal optical signal power due to complex factors like optical cable length, patch sections, and equipment type, leading to excessive power output and potential signal distortion.
Innovation Solution
A method and apparatus using a deep learning model to estimate optimal optical signal transmission power by inputting transmission network facility information and adjusting data to ensure the signal remains within a suitable range (−18 to −8 dBm) for effective amplification and reception.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If maximum power is output from the transmitter, then the optical signal can be received at sufficient strength, but excessive power is wasted and energy efficiency decreases
Solution Approach 1:
The system performs preliminary calculation of natural attenuation using a pre-trained deep learning model that considers cable length, patch sections, and equipment type. This allows the transmitter to output power that is precisely sufficient for the specific link conditions, avoiding the need to output maximum power and waste energy.
Solution Approach 2:
The system changes the transmission power parameter dynamically based on calculated attenuation values. Instead of using a fixed maximum power setting, the transmission power is adjusted to match the specific requirements of each optical link, thereby improving energy efficiency while maintaining reliable signal reception.
2Reliability
If transmission power is increased to overcome natural attenuation, then signal reception is improved, but signal distortion occurs and reliability decreases
Solution Approach 1:
The system calculates the natural attenuation value before transmission using a pre-trained deep learning model that considers cable length, patch sections, and equipment type. This preliminary calculation allows the transmitter to set the appropriate power level in advance, preventing both insufficient and excessive power output that could cause signal distortion.
Solution Approach 2:
The system uses feedback from the deep learning model's prediction of natural attenuation to adjust transmission power. By continuously monitoring link conditions and adjusting power accordingly, the system maintains optimal signal levels without distortion while ensuring reliable reception.
3Ease of operation
If maximum power is always output, then the system is simple to operate, but complex factors like cable length and equipment type cannot be considered
Solution Approach 1:
The system performs self-service by automatically calculating natural attenuation and determining optimal transmission power using a pre-trained deep learning model. The system inputs link parameters (cable length, patch sections, equipment type) and automatically adjusts transmission power without requiring manual configuration or expert intervention, maintaining ease of operation while adapting to complex environmental factors.
Solution Approach 2:
The system dynamically changes transmission power parameters based on environmental factors such as cable length, number of patch sections, and equipment type. The deep learning model processes these parameters and automatically adjusts the transmission power to match the specific conditions of each optical link.
4Reliability
If attenuators are connected at the receiver to reduce excessive power, then signal reception quality is improved, but the system complexity increases
Solution Approach 1:
The system performs preliminary calculation of natural attenuation and determines the optimal transmission power before the signal reaches the receiver. By setting the correct power level in advance, the system eliminates the need for attenuators at the receiver, thereby maintaining signal reception quality without increasing system complexity.
Solution Approach 2:
Instead of reducing power at the receiver using attenuators, the system inverts the approach by controlling and setting the appropriate power level at the transmitter. This inversion eliminates the need for additional receiver-side components while achieving the same goal of optimal signal reception quality.
Data Source
AI summary
Provided are a method and apparatus for estimating an optimal optical signal transmission power. The method may include: generating an estimation data including an estimated optical signal transmission power and transmission network facility information; inputting the estimation data into a pre-trained model; calculating an optical signal reception power based on the estimation data; and estimating an optimal optical signal transmission power based on the calculated optical signal reception power.