{"id":910,"date":"2024-10-14T10:11:09","date_gmt":"2024-10-14T10:11:09","guid":{"rendered":"https:\/\/blogs.kcl.ac.uk\/kclip\/?p=910"},"modified":"2024-10-14T10:12:56","modified_gmt":"2024-10-14T10:12:56","slug":"neuromorphic-wireless-split-computing-with-wake-up-radios-architecture-and-design-via-digital-twinning","status":"publish","type":"post","link":"https:\/\/blogs.kcl.ac.uk\/kclip\/2024\/10\/14\/neuromorphic-wireless-split-computing-with-wake-up-radios-architecture-and-design-via-digital-twinning\/","title":{"rendered":"Neuromorphic Wireless Split Computing with Wake-Up Radios"},"content":{"rendered":"

Context and Motivations<\/strong><\/h3>\n

Neuromorphic processing units (NPUs), such as Intel’s Loihi or BrainChip’s Akida, leverage the sparsity of temporal data to reduce processing energy by activating a small subset of neurons and synapses at each time step. When deployed for split computing<\/em> in edge-based systems, remote NPUs, each carrying out part of the computation, can reduce the communication power budget by communicating asynchronously using sparse impulse radio<\/em> (IR) waveforms [1-2], a form of ultra-wide bandwidth (UWB) spread-spectrum signaling.<\/p>\n

\"\"<\/p>\n

However, the power savings afforded by sparse transmitted signals are limited to the transmitter’s side, which can transmit impulsive waveforms only at the times of synaptic activations. The main contributor to the overall energy consumption remains the power required to maintain the main radio on.<\/p>\n

Architecture<\/h3>\n

To address this architectural problem, as seen in the figure above, our recent work<\/a> [3-4] proposes a novel architecture that integrates a wake-up radio<\/em> mechanism within a split computing system consisting of remote, wirelessly connected, NPUs. In the proposed architecture, the NPU at the transmitter side remains idle until a signal of interest is detected by the signal detection module. Subsequently, a wake-up signal (WUS) is transmitted by the wake-up transmitter over the channel to the wake-up receiver, which activates the main receiver. The IR transmitter modulates the encoded signals from the NPU, and sends them to the main receiver. The NPU at the receiver side then decodes the received signals and make an inference decision.<\/p>\n

Digital twin-aided design methodology with reliability guarantee<\/h3>\n

A key challenge in the design of a wake-up radios is the selection of thresholds for sensing and WUS detection, and decision making (three \u03bb’s<\/span> in the figure above). A conventional solution would be to calibrate the thresholds via on-air<\/em> testing, trying out different thresholds via testing on the actual physical system. On-air calibration would be expensive in terms of spectral resources, and there is generally no guarantee that the selected thresholds would provide desirable performance levels for the end application.<\/p>\n

To address this design problem, as illustrated in the figure below, this work proposes a novel methodology, dubbed DT-LTT,\u00a0 that leverages the use of a digital twin<\/em>, i.e., a simulator, of the physical system, coupled with a sequential statistical testing approach that provides theoretical reliability guarantees. Specifically, the digital twin is leveraged to pre-select a sequence of hyperparameters to be tested using on-air calibration via Learn then Test (LTT) [5]. The proposed DT-LTT calibration procedure is proved to guarantee reliability of the receiver’s decisions irrespective of the fidelity of digital twin and of the data distribution.<\/p>\n

\"\"<\/p>\n

Experiment<\/h3>\n

We compare the proposed DT-LTT calibration method with conventional neuromorphic wireless communications without wake-up radio, conventional LTT without a digital twin, and DT-LTT with an always-on main radio system. As shown in the figure below, the conventional calibration scheme fails to meet the reliability requirement, while the basic LTT scheme selects conservative hyperparameters, often including all classes in the predicted set, which results in zero expected loss. In contrast, the proposed DT-LTT schemes are guaranteed to meet the probabilistic reliability requirement.<\/p>\n

\"\"<\/p>\n

References<\/h3>\n

[1] J. Chen, N. Skatchkovsky and O. Simeone, “Neuromorphic Wireless Cognition: Event-Driven Semantic Communications for Remote Inference,” in\u00a0IEEE Transactions on Cognitive Communications and Networking<\/em>, vol. 9, no. 2, pp. 252-265, April 2023,.<\/p>\n

[2] J. Chen, N. Skatchkovsky and O. Simeone, “Neuromorphic Integrated Sensing and Communications,” in\u00a0IEEE Wireless Communications Letters<\/em>, vol. 12, no. 3, pp. 476-480, March 2023.<\/p>\n

[3] J. Chen, S. Park, P. Popovski, H. V. Poor and O. Simeone, “Neuromorphic Split Computing with Wake-Up Radios: Architecture and Design via Digital Twinning,” in\u00a0IEEE Transactions on Signal Processing<\/em>, Early Access, 2024.<\/p>\n

[4] J. Chen, S. Park, P. Popovski, H. V. Poor and O. Simeone, “Neuromorphic Semantic Communications with Wake-Up Radios,” Proc. IEEE 25th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC)<\/em>, Lucca, Italy, pp. 91-95, 2024.<\/p>\n

[5] Angelopoulos, Anastasios N., et al. “Learn then test: Calibrating predictive algorithms to achieve risk control,”\u00a0arXiv preprint arXiv:2110.01052, 2021.<\/em><\/p>\n","protected":false},"excerpt":{"rendered":"

Context and Motivations Neuromorphic processing units (NPUs), such as Intel’s Loihi or BrainChip’s Akida, leverage the sparsity of temporal data to reduce processing energy by activating a small subset of neurons and synapses at each time step. When deployed for split computing in edge-based systems, remote NPUs, each carrying out part of the computation, can […]<\/p>\n","protected":false},"author":1243,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-910","post","type-post","status-publish","format-standard","hentry","category-uncategorized","post-preview"],"_links":{"self":[{"href":"https:\/\/blogs.kcl.ac.uk\/kclip\/wp-json\/wp\/v2\/posts\/910","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/blogs.kcl.ac.uk\/kclip\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/blogs.kcl.ac.uk\/kclip\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/blogs.kcl.ac.uk\/kclip\/wp-json\/wp\/v2\/users\/1243"}],"replies":[{"embeddable":true,"href":"https:\/\/blogs.kcl.ac.uk\/kclip\/wp-json\/wp\/v2\/comments?post=910"}],"version-history":[{"count":6,"href":"https:\/\/blogs.kcl.ac.uk\/kclip\/wp-json\/wp\/v2\/posts\/910\/revisions"}],"predecessor-version":[{"id":919,"href":"https:\/\/blogs.kcl.ac.uk\/kclip\/wp-json\/wp\/v2\/posts\/910\/revisions\/919"}],"wp:attachment":[{"href":"https:\/\/blogs.kcl.ac.uk\/kclip\/wp-json\/wp\/v2\/media?parent=910"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/blogs.kcl.ac.uk\/kclip\/wp-json\/wp\/v2\/categories?post=910"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/blogs.kcl.ac.uk\/kclip\/wp-json\/wp\/v2\/tags?post=910"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}