Game theoretic methods and simulations based on reinforcement learning (RL) are often used to analyze electricity market equilibrium. However, the former is limited to a simple market environment with complete information, and difficult to visually reflect the tacit collusion; while the conventional RL algorithm is limited to low-dimensional discrete state and action spaces, and the convergence is unstable. To address the aforementioned problems, this paper adopts deep deterministic policy gradient (DDPG) algorithm to model the bidding strategies of generation companies (GenCos). Simulation experiments, including different settings of GenCo, load and network, demonstrate that the proposed method is more accurate than conventional RL algorithms, and can converge to the Nash equilibrium of complete information even in the incomplete information environment. Moreover, the proposed method can intuitively reflect the different tacit collusion level by quantitatively adjusting GenCos' patience parameter, which can be an effective means to analyze market strategies.

Planar electrical capacitance tomography (ECT) has broad application prospects in the defect detection of composite materials. The image reconstruction of planar ECT is a nonlinear and ill-posed inverse problem, which limits the accuracy of image reconstruction. An image reconstruction method based on the density-based spatial clustering of applications with noise cluster (DBSCAN) and self-adaptive alternating direction method of multipliers (SADMM) algorithms is proposed in this paper. Firstly, the characteristic capacitance values are extracted from the independent measurement capacitance values through the DBSCAN algorithm. Then, the original inverse problem is transformed into a set of local optimization sub-problems, and the SADMM algorithm with an adaptive penalty parameter is used to solve these subproblems to reconstruct the image. The experimental results show that the average relative error of the reconstructed images obtained by this algorithm is 0.086, which is significantly lower than other algorithms, the presented algorithm has higher anti-noise performance and can provide more accurate reconstructed images.

Existing machine learning-based methods for series arc fault (SAF) identification still suffer from slow training speed when dealing with large-scale SAF datasets. For this reason, we propose a series arc fault identification model based on Newton-optimized sparse kernel support vector machine (NSKSVM). Firstly, an SAF experimental platform is built, on which a large amount of single-circle SAF current signals are collected. The frequency-domain features of SAF current signals are analyzed and used as the feature set. Secondly, NSKSVM is constructed to identify SAF quickly for the large-scale SAF datasets and improve the accuracy by the kernel function while ensuring the fast training speed of the model. Finally, a series of experiments are conducted to verify the advantages of NSKSVM in SAF identification, which can meet the needs of real-time detection.

Revealing the evolutionary mechanisms of gas-liquid two-phase flow patterns is vital for production and transport in industry. The resistance sensor array is used to collect gas-liquid two-phase flow information from the vertical upward pipeline. The data are encoded into two-dimensional images using a Gramian angular field (GAF). Based on the GAF images, we propose a framework for analyzing flow patterns by combining bidimensional multi-scale permutation entropy (MPE _2D ) with interconnected pattern transition complex networks (IPTCN). The MPE _2D of GAF images is calculated to measure the multi-scale spatial complexity of the flow patterns. In addition, a new image-based optimal scale IPTCN is proposed to analyze the spatial coupling behavior and evolutionary behavior of the four flow patterns using two network indices in the IPTCN. Finally, a two-dimensional scatter plot is constructed using the average value of MPE _2D and the network indices from IPTCN. The K-Nearest Neighbor (KNN) algorithm is then applied to complete the flow pattern identification. The results show that the method can effectively analyze the nonlinear dynamic behavior of flow pattern at the optimal scale and reveal the evolutionary behavior between the flow patterns when the flow velocity changes.

Series arc fault detection can improve the safety of low-voltage power systems. The existing arc fault detection is mainly based on various indicators of a frequency domain or time-frequency domain transformation for feature extraction, which is difficult to extract comprehensive arc information, resulting in low detection accuracy. This paper presents a method for extracting comprehensive information, combined with a convolutional neural network to detect arc faults. First, the arc fault experimental platform is developed according to the UL1699 standard, and the current signals of various loads under different operating conditions are collected. Then, the current of a single cycle is embedded by coordinate delay, and the distance matrix is calculated by using 50 vectors reconstructed by a single cycle. Finally, a convolutional neural network classification model is designed, which is used to mine the information in the distance matrix to detect series arc faults. The experimental results show that the average accuracy of the method for arc fault identification of various loads is 99.00% and that the sampling frequency is low. It is suitable for lines with different loads and has certain robustness, so this method has the potential to be implemented on hardware.