A novel clustering based algorithm to mitigate the demand of forecasting errors for newly deployed LTE cells with insufficient historical data

Kranda Y. T., ŞAMLI R.

COMPUTER COMMUNICATIONS, vol.190, pp.190-200, 2022 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 190
  • Publication Date: 2022
  • Doi Number: 10.1016/j.comcom.2022.04.022
  • Journal Name: COMPUTER COMMUNICATIONS
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, PASCAL, Aerospace Database, Applied Science & Technology Source, Business Source Elite, Business Source Premier, Communication Abstracts, Compendex, Computer & Applied Sciences, INSPEC, Library, Information Science & Technology Abstracts (LISTA), Metadex, Civil Engineering Abstracts
  • Page Numbers: pp.190-200
  • Keywords: Mobile network capacity, Forecasting, Hierarchical clustering, Neural networks, Time series methods, STL-ETS, SARIMAX, LSTM networks
  • Istanbul University Affiliated: No

Abstract

This study presents a novel clustering-based algorithm to mitigate the demand of forecasting errors of newly deployed LTE (Long-Term Evolution) cells with insufficient historical data. The numbers and the usage of mobile networks are growing day by day. So, new base stations are set every day, and the newly deployed cells do not have enough historical data to forecast. We developed a clustering-based algorithm to overcome this problem. We compared our approach with different forecasting methods such as classical time series methods, time series decomposition-based methods, and deep NN (Neural Network) methods. We tested our clustering-based solution compared with other approaches using seventy LTE cells' daily historical performance data for two years. We collected this data from a Tier-1 Mobile Network Operator (MNO). We also analyzed the clustering features and benchmarked them for their contribution to the solution, and we measured the error rate by MAPE (Mean Absolute Percentage Error). As a result, we decreased the previous forecasting error rate from 133% to approximately 35%, showing that our novel algorithm is an efficient tool for this process.