TY - GEN
T1 - Telecommunication Traffic Forecasting via Multi-task Learning
AU - Gou, Xiaochuan
AU - Zhang, Xiangliang
N1 - Funding Information:
The research reported in this paper was supported by funding from King Abdullah University of Science and Technology (KAUST).
Publisher Copyright:
© 2023 ACM.
PY - 2023/2/27
Y1 - 2023/2/27
N2 - Accurate telecommunication time series forecasting is critical for smart management systems of cellular networks, and has a special challenge in predicting different types of time series simultaneously at one base station (BS), e.g., the SMS, Calls, and Internet. Unlike the well-studied single target forecasting problem for one BS, this distributed multi-target forecasting problem should take advantage of both the intra-BS dependence of different types of time series at the same BS and the inter-BS dependence of time series at different BS. To this end, we first propose a model to learn the inter-BS dependence by aggregating the multi-view dependence, e.g., from the viewpoint of SMS, Calls, and Internet. To incorporate the interBS dependence in time series forecasting, we then propose a Graph Gate LSTM (GGLSTM) model that includes a graph-based gate mechanism to unite those base stations with a strong dependence on learning a collaboratively strengthened prediction model. We also extract the intra-BS dependence by an attention network and use it in the final prediction. Our proposed approach is evaluated on two real-world datasets. Experiment results demonstrate the effectiveness of our model in predicting multiple types of telecom traffic at the distributed base stations.
AB - Accurate telecommunication time series forecasting is critical for smart management systems of cellular networks, and has a special challenge in predicting different types of time series simultaneously at one base station (BS), e.g., the SMS, Calls, and Internet. Unlike the well-studied single target forecasting problem for one BS, this distributed multi-target forecasting problem should take advantage of both the intra-BS dependence of different types of time series at the same BS and the inter-BS dependence of time series at different BS. To this end, we first propose a model to learn the inter-BS dependence by aggregating the multi-view dependence, e.g., from the viewpoint of SMS, Calls, and Internet. To incorporate the interBS dependence in time series forecasting, we then propose a Graph Gate LSTM (GGLSTM) model that includes a graph-based gate mechanism to unite those base stations with a strong dependence on learning a collaboratively strengthened prediction model. We also extract the intra-BS dependence by an attention network and use it in the final prediction. Our proposed approach is evaluated on two real-world datasets. Experiment results demonstrate the effectiveness of our model in predicting multiple types of telecom traffic at the distributed base stations.
KW - multi-source time series forecasting
KW - multi-task learning
KW - telecommunication traffic forecasting
UR - http://www.scopus.com/inward/record.url?scp=85149660900&partnerID=8YFLogxK
U2 - 10.1145/3539597.3570440
DO - 10.1145/3539597.3570440
M3 - Conference contribution
AN - SCOPUS:85149660900
T3 - WSDM 2023 - Proceedings of the 16th ACM International Conference on Web Search and Data Mining
SP - 859
EP - 867
BT - WSDM 2023 - Proceedings of the 16th ACM International Conference on Web Search and Data Mining
PB - Association for Computing Machinery, Inc
T2 - 16th ACM International Conference on Web Search and Data Mining, WSDM 2023
Y2 - 27 February 2023 through 3 March 2023
ER -