Carrier Resource Adjustment for KPI-Safe Network Energy Saving
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing energy saving methods for network devices result in compromised key performance indicators (KPIs) due to fluctuating service data volumes, failing to meet user quality of service requirements.
Innovation Solution
A method that predicts service data volume and KPIs, uses models to select resource combinations minimizing energy consumption without affecting KPIs, by adjusting carrier resources based on predicted data and resource information combinations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Use of energy by stationary object
If carrier resources are disabled for energy saving when service data volume is low, then energy consumption is reduced, but key performance indicators (KPIs) are affected and quality of service cannot be satisfied
Solution Approach 1:
The system performs preliminary actions by predicting future service data volumes and KPIs before making resource adjustment decisions. Multiple future time points are predicted in advance, allowing the system to proactively adjust carrier resources based on forecasted conditions rather than reacting to current state, thus preventing KPI degradation while achieving energy savings
Solution Approach 2:
The system implements a closed-loop feedback mechanism where predicted KPIs are continuously compared with target KPIs, and resource adjustment decisions are made based on this comparison. The feedback loop ensures that any potential KPI degradation is detected and corrected, allowing the system to maintain reliability while optimizing energy consumption through iterative adjustments
2Reliability
If all carriers remain in operating state to ensure service quality, then key performance indicators are maintained, but energy consumption increases during low service data volume periods
Solution Approach 1:
The system dynamically adjusts carrier resource states based on predicted service conditions. Carriers transition between operating and disabled states according to forecasted data volumes and KPI requirements, making the system adaptable to varying load conditions. This dynamic approach allows energy savings during low-demand periods while maintaining service quality when needed
Solution Approach 2:
The system changes the operational parameters of carrier resources (enabled/disabled states) based on predicted service conditions. By adjusting these parameters proactively according to forecasts, the system optimizes the balance between energy consumption and service quality, disabling carriers when predictions indicate low demand that won't impact KPIs
Data Source
AI summary
A network device is configured to predict the service data volume of the target time period so that a determined target key performance indicator (KPI) can satisfy an actual KPI. The network device may further input the service data volume of the target time period and various resource information combinations into a prediction model group and a resource energy consumption model, predict the KPI and the energy consumption of each resource information combination by using the model, and select a resource information combination that does not affect the KPI and that has low energy consumption to adjust a carrier resource of the second network device. As a result, an energy saving effect can be achieved, thereby remedy a defect in the existing energy saving technology that a target KPI cannot be guaranteed.