Spintronic Physical Reservoir for Autonomous Prediction and Long-Term Household Energy Load Forecasting
arXiv:2304.03343 · doi:10.1109/ACCESS.2023.3326414
Abstract
In this study, we have shown autonomous long-term prediction with a spintronic physical reservoir. Due to the short-term memory property of the magnetization dynamics, non-linearity arises in the reservoir states which could be used for long-term prediction tasks using simple linear regression for online training. During the prediction stage, the output is directly fed to the input of the reservoir for autonomous prediction. We employ our proposed reservoir for the modeling of the chaotic time series such as Mackey-Glass and dynamic time-series data, such as household building energy loads. Since only the last layer of a RC needs to be trained with linear regression, it is well suited for learning in real time on edge devices. Here we show that a skyrmion based magnetic tunnel junction can potentially be used as a prototypical RC but any nanomagnetic magnetic tunnel junction with nonlinear magnetization behavior can implement such a RC. By comparing our spintronic physical RC approach with energy load forecasting algorithms, such as LSTMs and RNNs, we conclude that the proposed framework presents good performance in achieving high predictions accuracy, while also requiring low memory and energy both of which are at a premium in hardware resource and power constrained edge applications. Further, the proposed approach is shown to require very small training datasets and at the same time being at least 16X energy efficient compared to the sequence to sequence LSTM for accurate household load predictions.
References in corpus (20)
- The design and verification of Mumax3
- Recent Advances in Physical Reservoir Computing: A Review
- Optoelectronic Reservoir Computing
- Next Generation Reservoir Computing
- Building Energy Load Forecasting using Deep Neural Networks
- Reconfigurable Training and Reservoir Computing in an Artificial Spin-Vortex Ice via Spin-Wave Fingerprinting
- Spin waves in coupled YIG/Co heterostructures
- Reservoir Computing with Random Skyrmion Textures
- Physical reservoir computing built by spintronic devices for temporal information processing
- Experimental Clocking of Nanomagnets with Strain for Ultra Low Power Boolean Logic
- Experimental creation and annihilation of nonvolatile magnetic skyrmions using voltage control of magnetic anisotropy without an external magnetic field
- Pattern recognition with neuromorphic computing using magnetic-field induced dynamics of skyrmions
- A perspective on physical reservoir computing with nanomagnetic devices
- Brain-inspired photonic signal processor for periodic pattern generation and chaotic system emulation
- Voltage controlled core reversal of fixed magnetic skyrmions without a magnetic field
- Skyrmion mediated voltage controlled switching of ferromagnets for reliable and energy efficient 2-terminal memory
- Energy Efficient Learning with Low Resolution Stochastic Domain Wall Synapse Based Deep Neural Networks
- Dynamic Skyrmion-Mediated Switching of Perpendicular MTJs: Scaling to 20 nm with Thermal Noise
- Skyrmion based energy efficient straintronic physical reservoir computing
- Passive frustrated nanomagnet reservoir computing