In this paper, we investigate an energy cost minimization problem for a smart home in the absence of a building thermal dynamics model with the consideration of a comfortable temperature range. Due to the existence of model uncertainty, parameter uncertainty (e.g., renewable generation output, non-shiftable power demand, outdoor temperature, and electricity price) and temporally-coupled operational constraints, it is very challenging to design an optimal energy management algorithm for scheduling Heating, Ventilation, and Air Conditioning (HVAC) systems and energy storage systems in the smart home. To address the challenge, we first formulate the above problem as a Markov decision process, and then propose an energy management algorithm based on Deep Deterministic Policy Gradients (DDPG). It is worth mentioning that the proposed algorithm does not require the prior knowledge of uncertain parameters and building thermal dynamics model. Simulation results based on real-world traces demonstrate the effectiveness and robustness of the proposed algorithm.

Current-induced spin-orbit torques (SOTs) are of interest for fast and energy-efficient manipulation of magnetic order in spintronic devices. To be deterministic, however, switching of perpendicularly magnetized materials by SOT requires a mechanism for in-plane symmetry breaking. Existing methods to do so involve the application of an in-plane bias magnetic field, or incorporation of in-plane structural asymmetry in the device, both of which can be difficult to implement in practical applications. Here, we report bias-field-free SOT switching in a single perpendicular CoTb layer with an engineered vertical composition gradient. The vertical structural inversion asymmetry induces strong intrinsic SOTs and a gradient-driven Dzyaloshinskii–Moriya interaction (g-DMI), which breaks the in-plane symmetry during the switching process. Micromagnetic simulations are in agreement with experimental results, and elucidate the role of g-DMI in the deterministic switching processes. This bias-field-free switching scheme for perpendicular ferrimagnets with g-DMI provides a strategy for efficient and compact SOT device design.

The research about deep learning application for physical layer has been received much attention in recent years. In this paper, we propose a Deep Learning (DL) based channel estimator under time varying Rayleigh fading channel. We build up, train and test the channel estimator using Neural Network (NN). The proposed DL-based estimator can dynamically track the channel status without any prior knowledge about the channel model and statistic characteristics. The simulation results show the proposed NN estimator has better Mean Square Error (MSE) performance compared with the traditional algorithms and some other DL-based architectures. Furthermore, the proposed DL-based estimator also shows its robustness with the different pilot densities.

Spintronic devices use spin instead of charge to process information and are widely considered as promising candidates for next-generation electronic devices. In past decades, the main motivation in spintronics has been to discover new mechanisms and novel material systems to improve both device performance and the application prospects of spintronics. Recently, researchers have found that ferrimagnetic materials—in which sublattices are coupled antiferromagnetically—offer an emerging platform for realizing high-density, high-speed, and low-power-consumption memory and logic functions. Within such a ferrimagnetic class, vanishing magnetization and ultrafast magnetic dynamics can be achieved by adjusting chemical composition and temperature, among other parameters. Meanwhile, unlike for antiferromagnets, conventional electrical read–write methods remain suitable for ferrimagnets, which is beneficial for applications. In this review, an abundant class of ferrimagnets including oxides and alloys is surveyed, and unique magnetic dynamics and effective methods for manipulating the magnetic states of ferrimagnets are discussed. Finally, novel storage and computing devices based on ferrimagnets are considered, as there are some challenges to be addressed in future applications of ferrimagnets.

Massive multi-input multi-output (MIMO) has aroused extensive interest in communication industry, as it can effectively increase communication system capacity and reduce transmit power. For massive MIMO-orthogonal frequency division multiplexing (OFDM) systems, traditional pilot assisted channel estimation methods need to obtain the channel response of data subcarriers by interpolation. However, when the channel response of continuous data subcarriers changes dramatically, the accuracy of channel estimation will be decreased. In this article, therefore, a novel channel prediction framework that integrates the imperfect channel estimation of the massive MIMO-OFDM into the deep neural network scheme is proposed, thus replacing the interpolation method and achieving higher accuracy of channel estimation. From algorithm analysis and simulation results, the performance of proposed deep neural network channel prediction method based on the imperfect channel estimation outperforms the conventional least square method based on interpolation. Furthermore, compared with minimum mean square error, there are no need for channel autocorrelation matrix, prior statistics of noise variance, and the complex matrix inversion operations. In summary, deep neural network is an efficient method for the imperfect channel estimation in massive MIMO-OFDM systems.

The data transfer bottleneck in Von Neumann architecture owing to the separation between processor and memory hinders the development of high-performance computing. The computing in memory (CIM) concept is widely considered as a promising solution for overcoming this issue. In this article, we present a time-domain CIM (TD-CIM) scheme using spintronics, which can be applied to construct the energy-efficient convolutional neural network (CNN). Basic Boolean logic operations are implemented through recording the bit-line output at different moments. A multi-addend addition mechanism is then introduced based on the TD-CIM circuit, which can eliminate the cascaded full adders. To further optimize the compatibility of TD-CIM circuit for CNN, we also propose a quantization method that transforms floating-point parameters of pre-trained CNN models into fixed-point parameters. Finally, we build a TD-CIM architecture integrating with a highly reconfigurable array of field-free spin-orbit torque magnetic random access memory (SOT-MRAM) and evaluate its benefits for the quantized CNN. By performing digit recognition with the MNIST dataset, we find that the delay and energy are respectively reduced by 1.2-2.7 times and $2.4\times 10 ^{3} - 1.1\times 10 ^{4}$ times compared with STT-CIM and CRAM based on spintronic memory. Finally, the recognition accuracy can reach 98.65% and 91.11% on MNIST and CIFAR-10, respectively.