Recent years have witnessed the widespread popularity of Internet of things (IoT). By providing sufficient data for model training and inference, IoT has promoted the development of artificial intelligence (AI) to a great extent. Under this background and trend, the traditional cloud computing model may nevertheless encounter many problems in independently tackling the massive data generated by IoT and meeting corresponding practical needs. In response, a new computing model called edge computing (EC) has drawn extensive attention from both industry and academia. With the continuous deepening of the research on EC, however, scholars have found that traditional (non-AI) methods have their limitations in enhancing the performance of EC. Seeing the successful application of AI in various fields, EC researchers start to set their sights on AI, especially from a perspective of machine learning, a branch of AI that has gained increased popularity in the past decades. In this article, we first explain the formal definition of EC and the reasons why EC has become a favorable computing model. Then, we discuss the problems of interest in EC. We summarize the traditional solutions and hightlight their limitations. By explaining the research results of using AI to optimize EC and applying AI to other fields under the EC architecture, this article can serve as a guide to explore new research ideas in these two aspects while enjoying the mutually beneficial relationship between AI and EC.

With the increasing concern on climate change and global warming, the reduction of carbon emission becomes an important topic in many aspects of human society. The development of energy Internet (EI) makes it possible to achieve better utilization of distributed renewable energy sources with the power sharing functionality introduced by energy routers (ERs). In this paper, a bottom-up EI architecture is designed, and a novel data-driven dynamical control strategy is proposed. Intelligent controllers augmented by deep reinforcement learning (DRL) techniques are adopted for the operation of each microgrid independently in the bottom layer. Moreover, the concept of curriculum learning (CL) is integrated into DRL to improve the sample efficiency and accelerate the training process. Based on the power exchange plan determined in the bottom layer, considering the stochastic nature of electricity price in the future power market, the optimal power dispatching scheme in the upper layer is decided via model predictive control. The simulation has shown that, under the bottom-up architecture, compared with the conventional methods such as proportional integral and optimal power flow, the proposed method reduces overall generation cost by 7.1% and 37%, respectively. Meanwhile, the introduced CL-based training strategy can significantly speed up the convergence during the training of DRL. Last but not least, our method increases the profit of energy trading between ERs and the main grid.

In this paper, an energy management issue is considered for energy Internet (EI) where microgrids (MGs) are interconnected via energy routers (ERs). Focusing on an individual MG, we propose controllers in micro-turbines (MTs) and the ER, such that the following three criterions are hold simultaneously. First, a bottom-up energy management approach is realized. Second, the operation cost of utilizing BES devices is minimized. Thirdly, the situation of over-control with respect to MTs and the ER is considered to be avoided. Besides, we develop a novel hybrid modelling method combining both recurrent neural networks (RNNs) and Ornstein-Uhlenbeck process to obtain accurate power models for both PVs and loads. Next, we formulate our energy management issue into a stochastic optimal control problem and solve it via dynamic programming approach. Finally, examples illustrating the feasibility of the proposed methods are provided.

Demand side management has been proved to be effective in improving the operating efficiency of microgrids, while posing a severe threat to user privacy. This paper proposes a novel privacy preserving load control scheme for the residential microgrid, in which the microgrid operator manages a multitude of home appliances including electric vehicles (EVs) and air conditioners (ACs). This problem is formulated as a partially observable Markov decision process, since users' privacy information including indoor temperatures associated with ACs and arrival/departure times of EVs cannot be observed by microgrid operator. To address the formulated problem with high-dimensional continuous action space caused by massive controllable appliances, we develop a novel deep reinforcement learning algorithm by introducing credit assignment mechanism. Moreover, we integrate recurrent neural network to accommodate the partial observability of state due to privacy issues. Simulation results demonstrate the superiority and flexibility of the developed algorithm and verify the advantages of the proposed scheme compared with prior privacy preserving load control method.