Search

The distribution network reconfiguration (DNR) aims at minimizing the power losses and improving the voltage profile. Traditional model-based methods exactly need the network parameters to derive the optimal configuration of the distribution network. This paper proposes a DNR method based on model-free reinforcement learning (RL) approach. The proposed method adopts NoisyNet deep Q-learning network (DQN), by which the exploration can be automatically realized without need of tuning the exploration parameters, in order to accelerate the training process and improve the optimization performance. The proposed method is validated by the simulation results.

Due to the small number of participants in realistic cases, the Nash equilibrium generated by an oligopolistic market is more appropriate for depicting the actual energy market than the competitive equilibrium generated by a competitive market. However, the market efficiency decreases when the Nash equilibrium is used rather than the competitive equilibrium because of the strategic behaviors of the participants. In this paper, we propose two new mechanisms (subsidization and punishment) for each generator, both of which drive the Nash equilibrium to the competitive equilibrium in heterogeneous oligopolistic energy markets with a uniform pricing mechanism. Under the two proposed mechanisms, the equivalence of the Nash equilibrium and the competitive equilibrium is strictly proven. Furthermore, we apply a distributed algorithm to numerically confirm that both mechanisms perfectly eliminate the market efficiency loss. Finally, these two mechanisms are applied to the energy market under three different stages of development. Simulation results illustrate that the additional costs caused by the mechanisms converge to a low value and that the subsidization mechanism slightly outperforms the punishment mechanism.

In the era of the Internet of Things (IoT), billions of smart devices connect, interact, and exchange data with each other. As “things” get connected together, intelligent systems and technologies have been developed to exploit the rich information in the collected data, perceive what is happening in the surroundings, and finally take actions to maximize their own utility. Thanks to the ubiquitous wireless signals and the prevalence of wireless devices, wireless sensing becomes more popular among the various approaches that have been adopted in the IoT to measure the surrounding environment. Because human activities interact with wireless signals and introduce distinct patterns to the propagation, analyzing how wireless channel state information (CSI) responds to human activities enables many IoT applications. Recently, radio analytics has been proposed as a promising technique that exploits multipath as virtual antennas, extracts various features from wireless signals, and reveals rich environmental information. As automobiles continue to play an important role nowadays, manufacturers have been seeking emerging techniques for IoT applications that support drivers and enhance safety. The interior of an automobile can be viewed as a special indoor environment where most of the multipaths are restricted inside by the metal exterior. In this article, we introduce the concept of wireless artificial intelligence (AI) and demonstrate its concept in a smart car scenario where information about drivers and passengers is collected by commercial Wi-Fi devices deployed in the car. The proposed wireless AI system is capable of identifying authorized drivers based on radio biometric information. Vital signals of human introduce periodic patterns to the wireless CSI. By extracting the vital sign from wireless signals, the proposed wireless AI system can monitor the driver's state, count number of people in the car, and detect a child left in an unattended car.

Navigation systems have been widely used in modern applications in which the moving speed and direction estimations are two key steps. Instead of using traditional device-based orientation sensor such as accelerometer and magnetometer to estimate the moving direction, this paper presents a novel radio frequency (RF) signal-based moving direction sensing scheme by using 5G massive multiple input and output (MIMO) system. We first explore the energy distribution of the received signal in massive MIMO in both near- and far-field scenarios. The energy distribution in near-field is proved to be highly related to the geometric shape of the antenna deployment. In contrast, the energy distribution turns out to be a stationary sinc-like focusing beam in far-field scenario. Inspired by such an observation, we develop a novel method to estimate the speed of a moving target with respect to a single based station. The moving direction can be further determined by jointly considering the speed estimation results and the geometric property of the locations between the target and nearby base stations. Finally, numerical simulations show that the proposed RF-based method can achieve high accuracy in which the moving speed estimation error is less than 1.5m/s while the moving direction estimation error is within 2 degrees.

Flexible loads, most of which are on/off appliances, are playing an important role in keeping the balance between power generation and demand. In this paper, a distributed consensus-based control strategy is proposed for the economic load dispatch in the frequency regulation. In order to avoid the complexity caused by the discrete cost characteristics, the continuous cost function of each user is fitted by the least squares method in advance. To minimize the overall load dispatching costs during the frequency regulation, Incremental Cost Consensus (ICC) algorithm is proposed in the load control. The economic load dispatch is realized through the convergence of the Incremental Cost (IC) of users. Case studies are provided to verify the effectiveness of the proposed method, with comparisons of different discretization methods.

Detecting hot topics from massive academic data is a very challenging task. Because various types of academic information are overgrowing, e.g., papers, news, and blogs, which has gone far beyond the limits that researchers can accept. Therefore, how to efficiently and accurately detect hot topics from big academic data is the main problem that researchers are facing. In view of this, we design a general framework for Academic Hot Topic Detection (AHTD). Specifically, in this framework, a DeepWalk-based keyword extraction algorithm for a single paper (S-DWKE) is proposed to detect popular topics in diverse academic fields dynamically. Moreover, we propose a keyword extraction algorithm to extract keywords from multiple articles (M-GCKE), which enables us to detect new topics in emerging academic areas. Then, hot topics can be generated from keywords extracted by the S-DWKE and M-GCKE. A large number of experiments demonstrates the proposed framework effectively improves the performance of hot topic detection in the academic field and performs better than the comparison algorithms. We have applied the above work to the “Academic Headline” application to provide the hot topics for researchers.

In the past few years, Battery Energy Storage System (BESS) has been found of great potential in supporting the frequency control. Increasing attentions have been given to the control strategy of BESS. In this paper, a distributed control method considering the life-loss cost is proposed for BESS. Based on the multi-agent system, the Incremental Cost Consensus (ICC) algorithm is applied to minimize the life-loss cost of BESS. In order to improve the control performance, parameters of the system are optimized by Genetic Algorithm (GA). The simulation results are provided to verify the effectiveness of the proposed approach.