Scalable Empirical Dynamic Modeling With Parallel Computing and Approximate k-NN Search

Empirical Dynamic Modeling (EDM) is a mathematical framework for modeling and predicting non-linear time series data. Although EDM is increasingly adopted in various research fields, its application to large-scale data has been limited due to its high computational cost. This article presents kEDM, a high-performance implementation of EDM for analyzing large-scale time series datasets. kEDM adopts the Kokkos performance-portable programming model to efficiently run on both CPU and GPU while sharing a single code base. We also conduct hardware-specific optimization of performance-critical kernels. kEDM achieved up to 6.58× speedup in pairwise causal inference of real-world biology datasets compared to an existing EDM implementation. Furthermore, we integrate multiple approximate k-NN search algorithms into EDM to enable the analysis of extremely large datasets that were intractable with conventional EDM based on exhaustive k-NN search. EDM-based time series forecast enhanced with approximate k-NN search demonstrated up to 790× speedup compared to conventional Simplex projection with less than 1% increase in MAPE.

View this article on IEEE Xplore


RL-Based Cache Replacement: A Modern Interpretation of Belady’s Algorithm With Bypass Mechanism and Access Type Analysis

Belady’s algorithm is widely known as an optimal cache replacement policy. It has been the foundation of numerous recent studies on cache replacement policies, and most studies assume this as an upper limit. Despite its widespread adoption, we discovered opportunities to unleash the headroom by addressing cache access types and implementing cache bypass. In this study, we propose Stormbird, a cache replacement policy that synergistically integrates the extensions of Belady’s algorithm and the power of reinforcement learning. Reinforcement learning is well-suited for cache replacement policy problems owing to its ability to interact dynamically with the environment, adapt to changing access patterns, and optimize the maximum cumulative rewards. Stormbird utilizes several selected features from the reinforcement learning model to enhance the instructions per cycle efficiency while maintaining a low hardware area overhead. Furthermore, it considers cache access types and integrates dynamic set dueling techniques to improve the cache performance. For 2 MB last-level cache per core, Stormbird achieves an average instructions per cycle improvement of 0.13% over the previous state-of-the-art on a single-core system and 0.02% on a four-core system while simultaneously reducing hardware overhead by 62.5%. Stormbird incurs a low hardware overhead of only 10.5 KB for 2 MB last-level cache and can be implemented without using program counter values.

View this article on IEEE Xplore

 

Machine Learning Based Transient Stability Emulation and Dynamic System Equivalencing of Large-Scale AC-DC Grids for Faster-Than-Real-Time Digital Twin

Modern power systems have been expanding significantly including the integration of high voltage direct current (HVDC) systems, bringing a tremendous computational challenge to transient stability simulation for dynamic security assessment (DSA). In this work, a practical method for energy control center with the machine learning (ML) based synchronous generator model (SGM) and dynamic equivalent model (DEM) is proposed to reduce the computational burden of the traditional transient stability (TS) simulation. The proposed ML-based models are deployed on the field programmable gate arrays (FPGAs) for faster-than-real-time (FTRT) digital twin hardware emulation of the real power system. The Gated Recurrent Unit (GRU) algorithm is adopted to train the SGM and DEM, where the training and testing datasets are obtained from the off-line simulation tool DSAToolsTM/TSAT®. A test system containing 15 ACTIVSg 500-bus systems interconnected by a 15-terminal DC grid is established for validating the accuracy of the proposed FTRT digital twin emulation platform. Due to the complexity of emulating large-scale AC-DC grid, multiple FPGA boards are applied, and a proper interface strategy is also proposed for data synchronization. As a result, the efficacy of the hardware emulation is demonstrated by two case studies, where an FTRT ratio of more than 684 is achieved by applying the GRU-SGM, while it reaches over 208 times for hybrid computational-ML based digital twin of AC-DC grid.

*Published in the IEEE Power & Energy Society Section within IEEE Access.

View this article on IEEE Xplore

 

Doppler Spectrum Measurement Platform for Narrowband V2V Channels

This paper describes the implementation of a Doppler spectrum measurement platform for narrowband frequency-dispersive vehicle-to-vehicle (V2V) channels. The platform is based on a continuous-wave (CW) channel sounding approach widely used for path-loss and large-scale fading measurements, but whose effectiveness to measure the Doppler spectrum of V2V channels is not equally known. This channel sounding method is implemented using general-purpose hardware in a configuration that is easy to replicate and that enables a partial characterization of frequency-dispersive V2V channels at a fraction of the cost of a dedicated channel sounder. The platform was assessed in a series of field experiments that collected empirical data of the instantaneous Doppler spectrum, the mean Doppler shift, the Doppler spread, the path-loss profile, and the large-scale fading distribution of V2V channels under realistic driving conditions. These experiments were conducted in a highway scenario near San Luis Potosí, México, at two different carrier frequencies, one at 760MHz and the other at 2,500MHz. The transmitting and receiving vehicles were moving in the same direction at varying speeds, ranging from 20 to 130km/h and dictated by the unpredictable traffic conditions. The obtained results demonstrate that the presented measurement platform enables the spectral characterization of narrowband V2V channels and the identification of their Doppler signatures in relevant road-safety scenarios, such as those involving overtaking maneuvers and rapid vehicles approaching the transmitter and receiver in the opposite direction.

*Published in the IEEE Vehicular Society Section within IEEE Access.

View this article on IEEE Xplore

 

Most Popular Article of 2017: 5G Cellular User Equipment: From Theory to Practical Hardware Design

Research and development on the next generation wireless systems, namely 5G, has experienced explosive growth in recent years. In the physical layer, the massive multiple-input-multiple output (MIMO) technique and the use of high GHz frequency bands are two promising trends for adoption. Millimeter-wave (mmWave) bands, such as 28, 38, 64, and 71 GHz, which were previously considered not suitable for commercial cellular networks, will play an important role in 5G. Currently, most 5G research deals with the algorithms and implementations of modulation and coding schemes, new spatial signal processing technologies, new spectrum opportunities, channel modeling, 5G proof of concept systems, and other system-level enabling technologies. In this paper, we first investigate the contemporary wireless user equipment (UE) hardware design, and unveil the critical 5G UE hardware design constraints on circuits and systems. On top of the said investigation and design tradeoff analysis, a new, highly reconfigurable system architecture for 5G cellular user equipment, namely distributed phased arrays based MIMO (DPA-MIMO) is proposed. Finally, the link budget calculation and data throughput numerical results are presented for the evaluation of the proposed architecture.

View this article on IEEE Xplore