Cost-adaptive Neural Networks for Peak Volume Prediction with EMM Filtering
As the emergence of the Internet of Things (IoT) and the growing number of IoT devices, a stable connection service has become one of the key factors concerning the Quality of Service (QoS) provision. How to anticipate the peak trafﬁc volume is essential. If the resource allocation is under provisioned, the service becomes susceptible to failure or security breach. Unfortunately, peak volumes are not captured in the systematic components of data and as a result conventional trend prediction methods have proven insufﬁcient. We propose a framework that implements neural networks with ﬁltering and a cost-adaptive loss function to improve the ability to predict peak volumes. Implementing this method on a real Domain Name Server (DNS) trafﬁc data, we observe not only the improvement in the prediction performance but also a shorter lag time to predict peak values, which demonstrates our proposed method.
2019 IEEE International Conference on Big Data, Los Angeles, CA, USA, December 9-12, 2019
no SHERPA/RoMEO policy available
Open Access Status
Yu, B., Graciani, G., Nascimento, A., Hu, J., & Clara, S. (2019). Cost-adaptive Neural Networks for Peak Volume Prediction with EMM Filtering. 2019 IEEE International Conference on Big Data, Los Angeles, CA, USA, December 9-12, 2019, 6. https://doi.org/10.1109/BigData47090.2019.9006188