Multi-task Learning-based Joint CSI Prediction and Predictive Transmitter Selection for Security

TL;DR

This paper introduces a multi-task learning approach using LSTM to jointly predict CSI and select transmitters for enhanced security in mobile communications, outperforming CNNs and sequential models.

Contribution

The paper presents a novel joint CSI prediction and transmitter selection framework using a single LSTM-based multi-task learning model, improving accuracy and efficiency.

Findings

LSTM-based MTL outperforms CNN in capturing temporal features.

Joint prediction improves secrecy performance under dynamic conditions.

Method reduces computational time by approximately 40%.

Abstract

In mobile communication scenarios, the acquired channel state information (CSI) rapidly becomes outdated due to fast-changing channels. Opportunistic transmitter selection based on current CSI for secrecy improvement may be outdated during actual transmission, negating the diversity benefit of transmitter selection. Motivated by this problem, we propose a joint CSI prediction and predictive selection of the optimal transmitter strategy based on historical CSI by exploiting the temporal correlation among CSIs. The proposed solution utilizes the multi-task learning (MTL) framework by employing a single Long Short-Term Memory (LSTM) network architecture that simultaneously learns two tasks of predicting the CSI and selecting the optimal transmitter in parallel instead of learning these tasks sequentially. The proposed LSTM architecture outperforms convolutional neural network (CNN) based architecture due to its superior ability to capture temporal features in the data. Compared to the sequential task learning models, the MTL architecture provides superior predicted secrecy performance for a large variation in the number of transmitters and the speed of mobile nodes. It also offers significant computational and memory efficiency, leading to a substantial saving in computational time by around 40 percent.