Source traffic prediction is one of the main challenges of enabling
predictive resource allocation in machine type communications (MTC). In this
paper, a Long Short-Term Memory (LSTM) based deep learning approach is proposed
for event-driven source traffic prediction. The source traffic prediction
problem can be formulated as a sequence generation task where the main focus is
predicting the transmission states of machine-type devices (MTDs) based on
their past transmission data. This is done by restructuring the transmission
data in a way that the LSTM network can identify the causal relationship
between the devices. Knowledge of such a causal relationship can enable
event-driven traffic prediction. The performance of the proposed approach is
studied using data regarding events from MTDs with different ranges of entropy.
Our model outperforms existing baseline solutions in saving resources and
accuracy with a margin of around 9%. Reduction in Random Access (RA) requests
by our model is also analyzed to demonstrate the low amount of signaling
required as a result of our proposed LSTM based source traffic prediction
approach.

提出了一种基于 LSTM 的深度学习方法，用于事件驱动的源流量预测，该方法可以有效地预测机器类型设备的传输状态，较现有基准解决方案具有更高的资源节约和准确性。

LSTM 网络在机器通信中基于事件的源流量预测

Event-Driven Source Traffic Prediction in Machine-Type Communications  Using LSTM Networks

The notion of a fast uplink grant is emerging as a promising solution for
enabling massive machine type communications (MTCs) in the Internet of Things
over cellular networks. By using the fast uplink grant, machine type devices
(MTD) will no longer require random access (RA) channels to send scheduling
requests. Instead, uplink resources can be actively allocated to MTDs by the
base station. In this paper, the challenges and opportunities for adopting the
fast uplink grant to support MTCs are investigated. First, the fundamentals of
fast uplink grant and its advantages over conventional access schemes: i) fully
scheduled with RA process and ii) uncoordinated access, are presented. Then,
the key challenges that include the prediction of set of MTDs with data to
transmit, as well as the optimal scheduling of MTDs, are exposed. To overcome
these challenges, a two-stage approach that includes traffic prediction and
optimized scheduling is proposed. For this approach, various solutions for
source traffic prediction for periodic MTD traffic are reviewed and novel
methods for event-driven traffic prediction are proposed. For optimal
allocation of uplink grants, new solutions based on advanced machine learning
methods are presented. By using the proposed solutions, the fast uplink grant
has the potential to enable cellular networks to support massive MTCs and
effectively reduce the signaling overhead and overcome the delay and congestion
challenges of conventional RA schemes.

探究了采用快速上行授权以支持大规模机器类型通信的挑战和机会，提出了一个两阶段的方法，包括交通预测和优化调度。通过使用提出的解决方案，快速上行授权有潜力使蜂窝网络支持大规模机器类型通信，并有效减少信令开销和克服传统的随机接入方案的延迟和拥塞挑战。