ISAC-Accelerated Edge Intelligence: Framework, Optimization, and Analysis

Conventionally, the sensing and communication stages for edge intelligence systems are executed sequentially, leading to an excessive time of dataset generation and uploading. To combat the weakness, this paper proposes to accelerate edge intelligence via integrated sensing and communication (ISAC), where the sensing and communication stages are merged to make the best use of the wireless signals for the dual purpose of dataset generation and uploading. For the proposed ISAC-accelerated edge intelligence system, the resource allocation and beamforming should be jointly optimized to exploit the underlying ISAC benefits. We formulate a joint resource allocation and beamforming optimization problem. Despite the non-convexity, we obtain globally optimal solutions assuming that the constant maximal transmits power, and devise an alternating optimization algorithm for the original problem without such assumption. Furthermore, we analyze the ISAC acceleration gain of the proposed system over that of the conventional edge intelligence system. Both theoretic analysis and simulation results show that ISAC accelerates the conventional edge intelligence system when the duration of generating a sample is more than that of uploading a sample. Otherwise, the ISAC acceleration gain vanishes or even is negative. In this case, we derive a sufficient condition for positive ISAC acceleration gain.

[1]  Kaibin Huang,et al.  Integrated Sensing and Over-the-Air Computation: Dual-Functional MIMO Beamforming Design , 2022, 2022 1st International Conference on 6G Networking (6GNet).

[2]  James J. Q. Yu,et al.  Collision Avoidance Predictive Motion Planning Based on Integrated Perception and V2V Communication , 2022, IEEE Transactions on Intelligent Transportation Systems.

[3]  Haisheng Tan,et al.  An Indoor Environment Sensing and Localization System via mmWave Phased Array , 2022, J. Commun. Inf. Networks.

[4]  Derrick Wing Kwan Ng,et al.  Federated Deep Learning Meets Autonomous Vehicle Perception: Design and Verification , 2022, IEEE Network.

[5]  Yunfei Chen,et al.  Generalized Transceiver Beamforming for DFRC With MIMO Radar and MU-MIMO Communication , 2022, IEEE Journal on Selected Areas in Communications.

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

[7]  Rui Wang,et al.  Passive Motion Detection via mmWave Communication System , 2022, 2022 IEEE 95th Vehicular Technology Conference: (VTC2022-Spring).

[8]  Yonina C. Eldar,et al.  Integrated Sensing and Communications: Toward Dual-Functional Wireless Networks for 6G and Beyond , 2021, IEEE Journal on Selected Areas in Communications.

[9]  Guangxu Zhu,et al.  Accelerating Edge Intelligence via Integrated Sensing and Communication , 2021, ICC 2022 - IEEE International Conference on Communications.

[10]  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).

[11]  Derrick Wing Kwan Ng,et al.  Integrated Sensing and Communication-Assisted Orthogonal Time Frequency Space Transmission for Vehicular Networks , 2021, IEEE Journal of Selected Topics in Signal Processing.

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

[13]  Xiaojun Jing,et al.  Integrating Sensing and Communications for Ubiquitous IoT: Applications, Trends, and Challenges , 2021, IEEE Network.

[14]  T. Han,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).

[15]  F. Hutter,et al.  How Powerful are Performance Predictors in Neural Architecture Search? , 2021, NeurIPS.

[16]  Bruno Clerckx,et al.  Rate-Splitting Multiple Access for Multi-Antenna Joint Radar and Communications , 2021, IEEE Journal of Selected Topics in Signal Processing.

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

[18]  Yonina C. Eldar,et al.  Cramér-Rao Bound Optimization for Joint Radar-Communication Beamforming , 2021, IEEE Transactions on Signal Processing.

[19]  Shuai Yu,et al.  CEFL: Online Admission Control, Data Scheduling, and Accuracy Tuning for Cost-Efficient Federated Learning Across Edge Nodes , 2020, IEEE Internet of Things Journal.

[20]  Vuk Marojevic,et al.  Semi-Blind Post-Equalizer SINR Estimation and Dual CSI Feedback for Radar-Cellular Coexistence , 2020, IEEE Transactions on Vehicular Technology.

[21]  Xu Chen,et al.  HFEL: Joint Edge Association and Resource Allocation for Cost-Efficient Hierarchical Federated Edge Learning , 2020, IEEE Transactions on Wireless Communications.

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

[23]  Lajos Hanzo,et al.  Joint Radar and Communication Design: Applications, State-of-the-Art, and the Road Ahead , 2019, IEEE Transactions on Communications.

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

[25]  Giuseppe Caire,et al.  Joint State Sensing and Communication over Memoryless Multiple Access Channels , 2019, 2019 IEEE International Symposium on Information Theory (ISIT).

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

[27]  Christos Masouros,et al.  Interfering Channel Estimation in Radar-Cellular Coexistence: How Much Information Do We Need? , 2018, IEEE Transactions on Wireless Communications.

[28]  David Sontag,et al.  Why Is My Classifier Discriminatory? , 2018, NeurIPS.

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

[30]  Xiaojun Jing,et al.  Interference alignment based precoder-decoder design for radar-communication co-existence , 2017, 2017 51st Asilomar Conference on Signals, Systems, and Computers.

[31]  Braham Himed,et al.  Non-coherent PSK-based dual-function radar-communication systems , 2016, 2016 IEEE Radar Conference (RadarConf).

[32]  Jeffrey H. Reed,et al.  On the Co-Existence of TD-LTE and Radar Over 3.5 GHz Band: An Experimental Study , 2016, IEEE Wireless Communications Letters.

[33]  Yimin Zhang,et al.  Dual-Function Radar-Communications: Information Embedding Using Sidelobe Control and Waveform Diversity , 2016, IEEE Transactions on Signal Processing.

[34]  Ke Wu,et al.  Joint wireless communication and radar sensing systems - state of the art and future prospects , 2013 .

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

[36]  Arnold Neumaier,et al.  Introduction to Numerical Analysis , 2001 .

[37]  Sompolinsky,et al.  Statistical mechanics of learning from examples. , 1992, Physical review. A, Atomic, molecular, and optical physics.

[38]  Daniel Thalmann,et al.  A global human walking model with real-time kinematic personification , 1990, The Visual Computer.

[39]  Randall M. Mealey A Method for Calculating Error Probabilities in a Radar Communication System , 1963, IEEE Transactions on Space Electronics and Telemetry.

[40]  C. Zhong,et al.  Communication-efficient Federated Edge Learning via Optimal Probabilistic Device Scheduling , 2022, IEEE Transactions on Wireless Communications.

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

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

[43]  Begnaud Francis Hildebrand,et al.  Introduction to numerical analysis: 2nd edition , 1987 .

[44]  Kaibin Huang,et al.  Reconfigurable Intelligent Surface Assisted Mobile Edge Computing With Heterogeneous Learning Tasks , 2020, IEEE Transactions on Cognitive Communications and Networking.