Accelerating Edge Intelligence via Integrated Sensing and Communication

Realizing edge intelligence consists of sensing, communication, training, and inference stages. Conventionally, the sensing and communication stages are executed sequentially, which results in excessive amount of dataset generation and uploading time. This paper proposes to accelerate edge intelligence via integrated sensing and communication (ISAC). As such, the sensing and communication stages are merged so as to make the best use of the wireless signals for the dual purpose of dataset generation and uploading. However, ISAC also introduces additional interference between sensing and communication functionalities. To address this challenge, this paper proposes a classification error minimization formulation to design the ISAC beamforming and time allocation. The globally optimal solution is derived via the rank-1 guaranteed semidefinite relaxation, and performance analysis is performed to quantify the ISAC gain over that of conventional edge intelligence. Simulation results are provided to verify the effectiveness of the proposed ISAC-assisted edge intelligence system. Interestingly, we find that ISAC is always beneficial, when the duration of generating a sample is more than the duration of uploading a sample. Otherwise, the ISAC gain can vanish or even be negative. Nevertheless, we still derive a sufficient condition, under which a positive ISAC gain is feasible.

[1]  Jie Li,et al.  Wireless Sensing With Deep Spectrogram Network and Primitive Based Autoregressive Hybrid Channel Model , 2021, 2021 IEEE 22nd International Workshop on Signal Processing Advances in Wireless Communications (SPAWC).

[2]  E. Alsusa,et al.  A Dual-Function Massive MIMO Uplink OFDM Communication and Radar Architecture , 2022, IEEE Transactions on Cognitive Communications and Networking.

[3]  Zhong Zheng,et al.  Joint Waveform Design and Passive Beamforming for RIS-Assisted Dual-Functional Radar-Communication System , 2021, IEEE Transactions on Vehicular Technology.

[4]  Miaowen Wen,et al.  Edge Learning With Unmanned Ground Vehicle: Joint Path, Energy, and Sample Size Planning , 2020, IEEE Internet of Things Journal.

[5]  Zhi Zhou,et al.  Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computing , 2019, IEEE Transactions on Wireless Communications.

[6]  Shuai Wang,et al.  Learning Centric Wireless Resource Allocation for Edge Computing: Algorithm and Experiment , 2020, IEEE Transactions on Vehicular Technology.

[7]  Zhi Zhou,et al.  Boosting Edge Intelligence With Collaborative Cross-Edge Analytics , 2021, IEEE Internet of Things Journal.

[8]  Qiang Li,et al.  Cooperative Secure Beamforming for AF Relay Networks With Multiple Eavesdroppers , 2013, IEEE Signal Processing Letters.

[9]  Arkadi Nemirovski,et al.  Lectures on modern convex optimization - analysis, algorithms, and engineering applications , 2001, MPS-SIAM series on optimization.

[10]  Xu Chen,et al.  Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing , 2019, Proceedings of the IEEE.

[11]  Christos Masouros,et al.  Toward Dual-functional Radar-Communication Systems: Optimal Waveform Design , 2017, IEEE Transactions on Signal Processing.

[12]  Xu Chen,et al.  In-Edge AI: Intelligentizing Mobile Edge Computing, Caching and Communication by Federated Learning , 2018, IEEE Network.

[13]  Jinhong Yuan,et al.  Constrained Utility Maximization in Dual-Functional Radar-Communication Multi-UAV Networks , 2021, IEEE Transactions on Communications.

[14]  Kaibin Huang,et al.  Towards an Intelligent Edge: Wireless Communication Meets Machine Learning , 2018, ArXiv.

[15]  Daniel Pérez Palomar,et al.  Rank-Constrained Separable Semidefinite Programming With Applications to Optimal Beamforming , 2010, IEEE Transactions on Signal Processing.

[16]  Christos Masouros,et al.  Joint Localization and Predictive Beamforming in Vehicular Networks: Power Allocation Beyond Water-Filling , 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[17]  H. Vincent Poor,et al.  Machine Intelligence at the Edge With Learning Centric Power Allocation , 2020, IEEE Transactions on Wireless Communications.

[18]  Kaibin Huang,et al.  Broadband Analog Aggregation for Low-Latency Federated Edge Learning , 2018, IEEE Transactions on Wireless Communications.