Telecommunications call volume forecasting with a block-diagonal recurrent fuzzy neural network

• Published in: Telecommunication systems Vol. 63; no. 1; pp. 15 - 25
• Main Authors: Mastorocostas, Paris A., Hilas, Constantinos S., Varsamis, Dimitris N., Dova, Stergiani C.
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.09.2016; Springer Nature B.V
• Subjects: Analysis; Artificial Intelligence; Artificial neural networks; Business and Management; Call centers; Communications networks; Computation; Computer Communication Networks; Feedback; Forecasting; Fuzzy; Fuzzy logic; Intelligence; Internet service providers; IT in Business; Mathematical models; Methods; Neural networks; Probability Theory and Stochastic Processes; Seasonal variations; Studies; Telecommunications; Telecommunications systems; Time series; Traffic flow; Trends; Telecommunications data volume forecasting; Fuzzy modelling; Block-diagonal recurrent neural network
• ISSN: 1018-4864; 1572-9451
• DOI: 10.1007/s11235-015-9968-x

An application of computational intelligence to the problem of telecommunications call volume forecasting is proposed in this work. In particular, the forecasting system is a recurrent fuzzy-neural model. The premise and defuzzification parts of the model’s fuzzy rules are static, while the consequent parts of the fuzzy rules are small block-diagonal recurrent neural networks with internal feedback, thus enabling the overall system to discover the temporal dependencies of the telecommunications time-series and perform forecasting without requiring prior knowledge of the exact order of the time-series. The forecasting performance is evaluated by using real-world telecommunications data. An extensive comparative analysis with a series of existing forecasters is conducted, including both traditional models as well as computational intelligence’s approaches. The simulation results confirm the modelling potential of the proposed scheme, since the latter outperforms its competing rivals in terms of three appropriate metrics, in all kinds of calls.