Meng Zhang

Global buildings account for about 30% of the total energy consumption and carbon emission, raising severe energy and environmental concerns. Therefore, it is significant and urgent to develop novel smart building energy management (SBEM) technologies for the advance of energy efficient and green buildings. However, it is a nontrivial task due to the following challenges. First, it is generally difficult to develop an explicit building thermal dynamics model that is both accurate and efficient enough for building control. Second, there are many uncertain system parameters (e.g., renewable generation output, outdoor temperature, and the number of occupants). Third, there are many spatially and temporally coupled operational constraints. Fourth, building energy optimization problems can not be solved in real time by traditional methods when they have extremely large solution spaces. Fifthly, traditional building energy management methods have respective applicable premises, which means that they have low versatility when confronted with varying building environments. With the rapid development of Internet of Things technology and computation capability, artificial intelligence technology find its significant competence in control and optimization. As a general artificial intelligence technology, deep reinforcement learning (DRL) is promising to address the above challenges. Notably, the recent years have seen the surge of DRL for SBEM. However, there lacks a systematic overview of different DRL methods for SBEM. To fill the gap, this article provides a comprehensive review of DRL for SBEM from the perspective of system scale. In particular, we identify the existing unresolved issues and point out possible future research directions.

Recent convolutional neural networks (CNNs)-based image processing methods have proven that CNNs are good at extracting features of spatial data. In this letter, we present a CNN-based modulation recognition framework for the detection of radio signals in communication systems. Since the frequency variation with time is the most important distinction among radio signals with different modulation types, we transform 1-D radio signals into spectrogram images using the short-time discrete Fourier transform. Furthermore, we analyze statistical features of the radio signals and use a Gaussian filter to reduce noise. We compare the proposed CNN framework with two existing methods from literature in terms of recognition accuracy and computational complexity. The experiments show that the proposed CNN architecture with spectrogram images as signal representation achieves better recognition accuracy than existing deep learning-based methods.

Using solar photovoltaics (PV) to help a microgrid (MG) operator for cost reduction may not be a straightforward problem due to the intermittent nature of PV power generation and unpredictable load demands. One potential way to address this challenge is to use batteries that can store the surplus PV energy whenever possible and supply the energy back to the MG when needed. In this context, this paper proposes a battery energy management system (BEMS) for an MG, in which PVs and diesel generators (DGs) are the primary sources of electricity. The novelty of the proposed BEMS lies within the energy management of multiple types of batteries' characteristics and the reduction of DGs' operating hours simultaneously. Furthermore, the proposed BEMS also takes into account different characteristics of the batteries when controlling the charging and discharging decision to extend the battery lifetime. Real-world data of MG load and PV power generations are used to verify the effectiveness of the proposed BEMS. Through numerical simulation case studies, it is demonstrated that the proposed BEMS is capable of achieving the following: reduction in DGs' operating hours, reduction in PV power fluctuations, and concurrent management of multiple batteries of different characteristics and extension of battery lifetime by controlling battery charge and discharge rate.