Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2306.05989 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912103744405504 |
|---|---|
| author | Isaac, Ebenezer RHP Singh, Bulbul |
| author_facet | Isaac, Ebenezer RHP Singh, Bulbul |
| contents | Forecasting time series patterns, such as cell key performance indicators (KPIs) of radio access networks (RAN), plays a vital role in enhancing service quality and operational efficiency. State-of-the-art forecasting approaches prioritize accuracy at the expense of computational performance, rendering them less suitable for data-intensive applications encompassing systems with a multitude of time series variables. They also do not capture the effect of dynamic operating ranges that vary with time. To address this issue, we introduce QBSD, a live single-step forecasting approach tailored to optimize the trade-off between accuracy and computational complexity. The method has shown significant success with our real network RAN KPI datasets of over several thousand cells. In this article, we showcase the performance of QBSD in comparison to other forecasting approaches on a dataset we have made publicly available. The results demonstrate that the proposed method excels in runtime efficiency compared to the leading algorithms available while maintaining competitive forecast accuracy that rivals neural forecasting methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2306_05989 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | QBSD: Quartile-Based Seasonality Decomposition for Cost-Effective RAN KPI Forecasting Isaac, Ebenezer RHP Singh, Bulbul Machine Learning Forecasting time series patterns, such as cell key performance indicators (KPIs) of radio access networks (RAN), plays a vital role in enhancing service quality and operational efficiency. State-of-the-art forecasting approaches prioritize accuracy at the expense of computational performance, rendering them less suitable for data-intensive applications encompassing systems with a multitude of time series variables. They also do not capture the effect of dynamic operating ranges that vary with time. To address this issue, we introduce QBSD, a live single-step forecasting approach tailored to optimize the trade-off between accuracy and computational complexity. The method has shown significant success with our real network RAN KPI datasets of over several thousand cells. In this article, we showcase the performance of QBSD in comparison to other forecasting approaches on a dataset we have made publicly available. The results demonstrate that the proposed method excels in runtime efficiency compared to the leading algorithms available while maintaining competitive forecast accuracy that rivals neural forecasting methods. |
| title | QBSD: Quartile-Based Seasonality Decomposition for Cost-Effective RAN KPI Forecasting |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2306.05989 |