Complex power quality disturbances (PQDs) are caused by the combination of multiple single disturbances. There exist complex mutual exclusion and combination relationships among these single disturbances, so-called mutually-exclusive labels mean that the disturbances corresponding to these labels cannot occur simultaneously (such as disturbance C2:Sag and C3:Swell). However, in the multilabel classification neural network, the fully connected layer and activation function corresponding to each label are identical, and there is no design to accommodate the mutually-exclusive and combination relationships, which allows the multilabel classification output mutually-exclusive disturbances simultaneously, which could mistakenly activate two incompatible governance devices at the same time. This is one of the reasons why this method cannot be applied in the power system, which requires an ultra-safe identification approach. A multilabel and multitask classification method with robust generalization ability and universal applicability is proposed to realize the mutually-exclusive output of PQDs mutually-exclusive labels. In principle, this method cannot output mutually-exclusive labels at the same time, to achieve an ultra-safe output. Meanwhile, this article proposes a faster and more accurate calculation method for PQDs envelope by using fast plug Hilbert transform, and uses Landau level transition field proposed in this article to achieve further feature extraction of the envelope and convert it into a two-dimensional (2-D) image, and then uses the proposed shallow double-path neural network DPN-17 to achieve classification and identification of PQDs. This methodology has strong universality and can be extensively utilized in various 1-D signal identification and feature extraction fields.

Brain simulation is one of the most important measures to understand how information is represented and processed in the brain, which usually needs to be realized in supercomputers with a large number of interconnected graphical processing units (GPUs). For the whole human brain simulation, tens of thousands of GPUs are utilized to simulate tens of billions of neurons and tens of trillions of synapses for the living brain to reveal functional connectivity patterns. However, as an application of the irregular spares communication problem on a large-scale system, the sparse and imbalanced communication patterns of the human brain make it particularly challenging to design a communication system for supporting large-scale brain simulations. To face this challenge, this paper proposes a hierarchical regularized communication mechanism, HRCM. The HRCM maintains a hierarchical virtual communication topology (HVCT) with a merge-forward algorithm that exploits the sparsity of neuron interactions to regularize inter-process communications in brain simulations. HRCM also provides a neuron-level partition scheme for assigning neurons to simulation processes to balance the communication load while improving resource utilization. In HRCM, neuron partition is formulated as a k-way graph partition problem and solved efficiently by the proposed hybrid multi-constraint greedy (HMCG) algorithm. HRCM performs finer-grained neuron-level communication control while leveraging voxel-level control as the basis, thus being more effective in balancing inter-process traffic in large-scale simulations. The hierarchical characteristics of the finer-grained communication control are considered by the problem formulation and algorithm design in HRCM. HRCM has been implemented in human brain simulations at the scale of up to 86 billion neurons running on 10000 GPUs. Results obtained from extensive simulation experiments verify the effectiveness of HRCM in significantly reducing communication delay, increasing resource usage, and shortening simulation time for large-scale human brain models.