5 January 2024 in Intelligent Computing
With the widespread deployment of 5G networks and the proliferation of mobile devices, mobile network operators are confronted not only with massive data growth in mobile traffic, but also with highly complex and dynamic traffic patterns. Given these challenges to network operation, cellular traffic prediction is becoming an essential network capability for ensuring quality of service and reducing costs. Accurate and timely cellular traffic prediction is essential for resource allocation, base station energy conservation, and network optimization. Recent years have seen widespread adoption of deep-learning-based models for cellular traffic prediction, with notable performance improvements. This survey encompasses representative data, model architectures, and state-of-the-art performance to provide a comprehensive account of deep learning techniques for cellular traffic prediction. After defining the problem of cellular traffic prediction and describing the available data, we describe in detail how deep learning techniques are used to capture the most crucial temporal and spatial dependencies of cellular traffic. We then summarize the state-of-the-art performance on 2 popular open datasets with multiple data settings to facilitate the comparison of deep-learning-based methods. Finally, we briefly outline the applications of cellular traffic prediction and discuss the remaining challenges and future research directions.
23 January 2025 in IEEE Transactions on Mobile Computing
App usage prediction aims to predict the next app most likely to be used based on historical behaviors, which is beneficial for smartphone system optimization, such as system resource management, battery energy optimization, and user experience enhancement. Existing studies have treated it as a simple time series prediction problem and overlooked the sessionization characteristic of mobile app usage, i.e., neglecting the intent context in which the user interacts with apps. In this paper, we explore the context of user intents and incorporate app sessionization features into prediction models to improve prediction accuracy. Specifically, we first extract the semantic meaning of spatio-temporal contextual information of app usage by constructing an urban knowledge graph. Second, we devise a hypergraph-based embedding model to extract the hyper-relations of intra-session apps. Third, we utilize a self-attention mechanism to fuse intra-session apps' representations and combine spatio-temporal contextual embedding to form the session representation. We further leverage a transformer for inter-session intent transition modeling to extract users' dynamic intent (i.e., the semantic meaning of sessions) for app usage. Finally, we jointly fuse dynamic intent and recently used app features using the MLP model for the prediction. The novelty of our method is that we are the first to leverage dynamic hypergraphs for modeling sessionization features, and we model both inter-session and intra-session relations. We evaluate our model based on two real-world datasets collected in Shanghai and Nanchang. In terms of prediction accuracy, mean reciprocal rank, and normalized discounted cumulative gain, our proposed framework outperforms state-of-the-art baselines by more than 30% in the Shanghai dataset and 20% in the Nanchang dataset, respectively. The code is available at https://github.com/tsinghua-fib-lab/Mobileappusagepredict-dynamicgraph
30 May 2026 in SSRN Electronic Journal
Multivariate time series long-term forecasting plays an important role in various real-world scenarios. Recent deep learning methods for long-term multivariate time series forecasting tend to capture the intricate patterns of time series by decomposition-based or pretrained methods. However, the real-world time series are usually intricate which are influenced by multiple factors and can be hardly disentangled. The pretrained methods predominantly transform time series into alternative representations and rely on powerful models from other domains to capture patterns of time series, which overlook the intrinsic properties specific to time series data. To capture the intrinsic patterns of time series, we propose a novel deep learning network architecture, named Multi-resolution Periodic Pattern Network (MPPN), for long-term multivariate time series forecasting. We first construct context-aware multi-resolution semantic units of time series and employ multi-periodic pattern mining to capture the key patterns of time series. Then, we propose a channel adaptive module to capture the multivariate perceptions towards different patterns. In addition, we adopt three distinct decoders, namely linear, convolutional, and Transformer decoders, to serve for long-term time series forecasting. Our experimental evaluation on nine real-world benchmarks demonstrated that MPPN significantly outperforms the state-of-the-art Transformer-based, linear-based and convolution-based methods for long-term multivariate time series forecasting.