This article presents a use-inspired perspective of the opportunities and challenges in a massively digitized power grid. It argues that the intricate interplay of data availability, computing capability, and artificial intelligence (AI) algorithm development are the three key factors driving the adoption of digitized solutions in the power grid. The impact of these three factors on critical functions of power system operation and planning practices is reviewed and illustrated with industrial practice case studies. Open challenges and research opportunities for data, computing, and AI algorithms are articulated within the context of the power industry’s tremendous decarbonization efforts.

Railway is evolving into the new era of smart railway. Unfortunately, the challenge of obtaining accurate instantaneous channel state information in high-speed railway (HSR) scenario makes it difficult to apply conventional power allocation schemes. In this paper, we propose an innovative experience-driven power allocation algorithm which is capable of learning power decisions from its own experience instead of the accurate mathematical model, just like one person learns one new skill, e.g. driving. To be specific, with the purpose of maximizing the achievable sum rate, we first formulate a joint hybrid beamforming and power allocation problem based on the millimeter-wave HSR channel model. Then, both at the transmitters (TXs) and receivers (RXs), we obtain the solution of beamforming design. Finally, experience-driven power allocation algorithm with multi-agent deep reinforcement learning is proposed. The numerical results indicate that the spectral efficiency of proposed algorithm significantly outperforms the existing state-of-the-art schemes.

A multi-way factor analysis model is introduced for tensor-variate data of any order. Each data item is represented as a (sparse) sum of Kruskal decompositions, a Kruskal- factor analysis (KFA). KFA is nonparametric and can infer both the tensor-rank of each dictionary atom and the number of dictionary atoms. The model is adapted for online learning, which allows dictionary learning on large data sets. After KFA is introduced, the model is extended to a deep convolutional tensor-factor analysis, supervised by a Bayesian SVM. The experiments section demonstrates the improvement of KFA over vectorized approaches (e.g., BPFA), tensor decompositions, and convolutional neural networks (CNN) in multi-way denoising, blind inpainting, and image classification. The improvement in PSNR for the inpainting results over other methods exceeds 1dB in several cases and we achieve state of the art results on Caltech101 image classification.

This paper designs a system that discovers knowledge from a GIS attribute data list. The system can acquire useful knowledge from the attribute data in a spatial database and get if-then rules to assist in decision-making. Four models, a qualitative model, an importance-judging model, a decision-table reducing model and a decision-making model form the backbone of the system. Every model connects orderly. User inputs parameters in qualitative model by human-computer interaction. According to these parameters the system determines actual bell membership functions based on the golden section model. With the membership functions quantitative data are changed into qualitative data that form an initial decision-table. According to rough set theory we develop an importance-judging model and a decision-table reducing model. In the importance-judging model, based on indiscernible relation we get importance of every condition attribute to decision attribute. In the reducing model we provide an effective reducing method to get the most concise if-then rules. The reducing process consists of two steps: firstly forming a discernable matrix to get core attributes, then simplifying every rule until every rule is composed of the least condition attributes. In the decision-making model neural network is used to simulate the most concise rules getting from decision-table reducing model and test the general ability. At the same time the paper makes transparent three factors that affect the general ability. The paper presents an example of its use for judging drought and flood disasters in Songhua river basin. Simulation results show that the system can quickly form the most concise if-then rules and make the right decision.