An official website of the United States government
The primary source of nonlinear distortion in wireless transmitters is the power amplifier (PA). Conventional digital predistortion (DPD) schemes use high-order polynomials to accurately approximate and compensate for the nonlinearity of the PA. This is not practical for scaling to tens or hundreds of PAs in massive multiple-input multiple-output (MIMO) systems. There is more than one candidate precoding matrix in a massive MIMO system because of the excess degrees-of-freedom (DoFs), and each precoding matrix requires a different DPD polynomial order to compensate for the PA nonlinearity. This paper proposes a low-order DPD method achieved by exploiting massive DoFs of next-generation front ends. We propose a novel indirect learning structure which adapts the channel and PA distortion iteratively by cascading adaptive zero forcing precoding and DPD. Our solution uses a 3rd order polynomial to achieve the same performance as the conventional DPD using an 11th order polynomial for a 10010 massive MIMO configuration. Experimental results show a 70% reduction in computational complexity, enabling ultra-low latency communications.
more »
« less
Neural Network DPD via Backpropagation through a Neural Network Model of the PA
We demonstrate digital predistortion (DPD) using a novel, neural-network (NN) method to combat the nonlinearities in power amplifiers (PAs), which limit the power efficiency of mobile devices, increase the error vector magnitude, and cause inadequate spectral containment. DPD is commonly done with polynomial-based methods that use an indirect-learning architecture (ILA) which can be computationally intensive, especially for mobile devices, and overly sensitive to noise. Our approach using NNs avoids the problems associated with ILAs by first training a NN to model the PA then training a predistorter by backpropagating through the PA NN model. The NN DPD effectively learns the unique PA distortions, which may not easily fit a polynomial-based model, and hence may offer a favorable tradeoff between computation overhead and DPD performance. We demonstrate the performance of our NN method using two different power amplifier systems and investigate the complexity tradeoffs.
more »
« less
- Award ID(s):
- 1717218
- PAR ID:
- 10202730
- Date Published:
- Journal Name:
- 2019 IEEE 53rd Asilomar Conference on Signals, Systems and Computers
- Page Range / eLocation ID:
- 358 to 362
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Compression and efficient storage ofneural network (NN)parameters is critical for applications that run on resource-constrained devices. Despite the significant progress in NN model compression, there has been considerably less investigation in the actualphysicalstorage of NN parameters. Conventionally, model compression and physical storage are decoupled, as digital storage media witherror-correcting codes (ECCs)provide robust error-free storage. However, this decoupled approach is inefficient as it ignores the overparameterization present in most NNs and forces the memory device to allocate the same amount of resources to every bit of information regardless of its importance. In this work, we investigate analog memory devices as an alternative to digital media – one that naturally provides a way to add more protection for significant bits unlike its counterpart, but is noisy and may compromise the stored model’s performance if used naively. We develop a variety of robust coding strategies for NN weight storage on analog devices, and propose an approach to jointly optimize model compression and memory resource allocation. We then demonstrate the efficacy of our approach on models trained on MNIST, CIFAR-10, and ImageNet datasets for existing compression techniques. Compared to conventional error-free digital storage, our method reduces the memory footprint by up to one order of magnitude, without significantly compromising the stored model’s accuracy.more » « less
-
Assistive robotic devices are a particularly promising field of application for neural networks (NN) due to the need for personalization and hard-to-model human-machine interaction dynamics. However, NN based estimators and controllers may produce potentially unsafe outputs over previously unseen data points. In this paper, we introduce an algorithm for updating NN control policies to satisfy a given set of formal safety constraints, while also optimizing the original loss function. Given a set of mixed-integer linear constraints, we define the NN repair problem as a Mixed Integer Quadratic Program (MIQP). In extensive experiments, we demonstrate the efficacy of our repair method in generating safe policies for a lower-leg prosthesis.more » « less
-
The energy and latency demands of critical workload execution, such as object detection, in embedded systems vary based on the physical system state and other external factors. Many recent mobile and autonomous System-on-Chips (SoC) embed a diverse range of accelerators with unique power and performance characteristics. The execution flow of the critical workloads can be adjusted to span into multiple accelerators so that the trade-off between performance and energy fits to the dynamically changing physical factors. In this study, we propose running neural network (NN) inference on multiple accelerators of an SoC. Our goal is to enable an energy-performance trade-off with an by distributing layers in a NN between a performance- and a power-efficient accelerator. We first provide an empirical modeling methodology to characterize execution and inter-layer transition times. We then find an optimal layers-to-accelerator mapping by representing the trade-off as a linear programming optimization constraint. We evaluate our approach on the NVIDIA Xavier AGX SoC with commonly used NN models. We use the Z3 SMT solver to find schedules for different energy consumption targets, with up to 98% prediction accuracy.more » « less
-
Abstract Recent advances in machine learning have enabled Neural Network (NN) inference directly on constrained embedded devices. This local approach enhances the privacy of user data, as the inputs to the NN inference are not shared with third-party cloud providers over a communication network. At the same time, however, performing local NN inference on embedded devices opens up the possibility of Power Analysis attacks, which have recently been shown to be effective in recovering NN parameters, as well as their activations and structure. Knowledge of these NN characteristics constitutes a privacy threat, as it enables highly effective Membership Inference and Model Inversion attacks, which can recover information about the sensitive data that the NN model was trained on. In this paper we address the problem of securing sensitive NN inference parameters against Power Analysis attacks. Our approach employs masking , a countermeasure well-studied in the context of cryptographic algorithms. We design a set of gadgets , i.e., masked operations, tailored to NN inference. We prove our proposed gadgets secure against power attacks and show, both formally and experimentally, that they are composable, resulting in secure NN inference. We further propose optimizations that exploit intrinsic characteristics of NN inference to reduce the masking’s runtime and randomness requirements. We empirically evaluate the performance of our constructions, showing them to incur a slowdown by a factor of about 2–5.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/IEEECONF44664.2019.9048910
