With the rise of the Internet of Things (IoT), some emerging mobile devices have been widely used such as wireless sensor networks, Radio Frequency Identification (RFID) chips, and smart cards etc. However, their comm...
详细信息
Establishing robust and efficient intrusion detection systems (IDS) and Intrusion prevention systems (IPS) are inevitable in today's security world. The major role of IDS is detecting the anomaly in network traffi...
详细信息
Breast cancer is very common type of cancer now a day. It is observed in many of the women and responsible for many deaths in recent days. In this work the power of machinelearning classifiers is applied in predictio...
详细信息
The influence of small-signal stability on the safety and stability of the power system is becoming more prominent. A mapping model based on steady-state operation information is established using the sample learning ...
详细信息
The influence of small-signal stability on the safety and stability of the power system is becoming more prominent. A mapping model based on steady-state operation information is established using the sample learning method, which provides a new technical path for the rapid assessment and correction of significant power grid oscillation characteristics. This paper establishes a small signal stability assessment and correction control model based on the Extreme Gradient Boosting (XGBoost) algorithm. Firstly, the XGBoost model is obtained by analyzing the mapping relationship between generator power, node power, branch power, and minimum damping ratio. Then, the sensitivity of the generator damping ratio is calculated, and the objective is to minimize the active power adjustment amount of the generator. The stability constraint and power balance are the constraint conditions to establish the optimization correction model, obtain the optimal adjustment amount, correct the minimum damping ratio, and improve the system's stability. Finally, the minimum damping ratio after correction is obtained, and the modified damping ratio is estimated by XGBoost algorithm. The performance of the proposed model is verified in IEEE 3-machine 9-node and 10-machine 39-node systems. (c) 2022 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (http://***/licenses/by-nc-nd/4.0/). Peer-review under responsibility of the scientific committee of the 2021 The 2nd internationalconference on Power engineering, ICPE, 2021.
We introduce a modality-agnostic neural compression algorithm based on a functional view of data and parameterised as an Implicit Neural Representation (INR). Bridging the gap between latent coding and sparsity, we ob...
详细信息
We introduce a modality-agnostic neural compression algorithm based on a functional view of data and parameterised as an Implicit Neural Representation (INR). Bridging the gap between latent coding and sparsity, we obtain compact latent representations non-linearly mapped to a soft gating mechanism. This allows the specialisation of a shared INR network to each data item through subnetwork selection. After obtaining a dataset of such latent representations, we directly optimise the rate/distortion trade-off in a modality-agnostic space using neural compression. Variational Compression of Implicit Neural Representations (VC-INR) shows improved performance given the same representational capacity pre quantisation while also outperforming previous quantisation schemes used for other INR techniques. Our experiments demonstrate strong results over a large set of diverse modalities using the same algorithm without any modality-specific inductive biases. We show results on images, climate data, 3D shapes and scenes as well as audio and video, introducing VC-INR as the first INR-based method to outperform codecs as well-known and diverse as JPEG 2000, MP3 and AVC/HEVC on their respective modalities.
In the present era of deep learning, continual learning research is mainly focused on mitigating forgetting when training a neural network with stochastic gradient descent on a non-stationary stream of data. On the ot...
详细信息
In the present era of deep learning, continual learning research is mainly focused on mitigating forgetting when training a neural network with stochastic gradient descent on a non-stationary stream of data. On the other hand, in the more classical literature of statistical machinelearning, many models have sequential Bayesian update rules that yield the same learning outcome as the batch training, i.e., they are completely immune to catastrophic forgetting. However, they are often overly simple to model complex real-world data. In this work, we adopt the meta-learning paradigm to combine the strong representational power of neural networks and simple statistical models' robustness to forgetting. In our novel meta-continual learning framework, continual learning takes place only in statistical models via ideal sequential Bayesian update rules, while neural networks are meta-learned to bridge the raw data and the statistical models. Since the neural networks remain fixed during continual learning, they are protected from catastrophic forgetting. This approach not only achieves significantly improved performance but also exhibits excellent scalability. Since our approach is domain-agnostic and model-agnostic, it can be applied to a wide range of problems and easily integrated with existing model architectures. Copyright 2024 by the author(s)
This research paper focuses on CFD analysis for comparative evaluation of different hybrid nanofluids (NFs): MWCNT-Al2O3/H2O, MWCNT-MgO/H2O, Al2O3-CuO/H2O performance as working fluid (WF) inside parabolic trough sola...
详细信息
A wide variety of algorithms are used in machinelearning to develop models that can anticipate future data that has not yet been observed and learn predictive rules from existing data. Using machinelearning techniqu...
详细信息
The advantages of hybrid energy ship with photovoltaic in energy conservation and emission reduction are becoming more and more prominent with increasing tension of global fossil energy. However, how to deal with phot...
详细信息
The advantages of hybrid energy ship with photovoltaic in energy conservation and emission reduction are becoming more and more prominent with increasing tension of global fossil energy. However, how to deal with photovoltaic uncertainty in real time and make photovoltaic efficiently connected to ship microgrid has become a key technical problem. Therefore, we propose a real-time energy management strategy for hybrid energy ship based on approximate model predictive control. Firstly, aiming at minimizing the operating cost and deviation from the reference state of charge, an energy management framework based on model predictive control is established. Secondly, the machinelearning algorithm is trained to approximate the optimal control action of model predictive control offline, and the performance of different machinelearning algorithms is analyzed quantitatively. Finally, taking a ferry equipped with photovoltaic as an example, the appropriate machinelearning algorithm and sample number are selected. The results show that the proposed strategy can not only ensure the optimization performance, but also effectively reduce the amount of calculation and realize the real-time operation of energy management in hybrid energy ship. (c) 2022 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (http://***/licenses/by-nc-nd/4.0/). Peer-review under responsibility of the scientific committee of the 2021 The 2nd internationalconference on Power engineering, ICPE, 2021.
In the task of system analysis for VSG cluster, aggregation modeling method is widely used for simplification. However, there are inevitable errors occur from the process of cluster aggregation. To improve the accurac...
详细信息
In the task of system analysis for VSG cluster, aggregation modeling method is widely used for simplification. However, there are inevitable errors occur from the process of cluster aggregation. To improve the accuracy of VSG cluster modeling, a data-physical driven modeling method is presented. At first, the equivalence between aggregation error and black box modeling issue is analyzed. Secondly, a hybrid model structure is proposed, which consists of single machine aggregation model and deep neural network based aggregated-error model. Then, to illustrate the modeling procedure, test cases are studied under large disturbance and multi-operating points conditions. The simulation results confirm that the proposed method can provide satisfactory modeling accuracy. (c) 2022 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (http://***/licenses/by-nc-nd/4.0/). Peer-review under responsibility of the scientific committee of the The 2nd internationalconference on Power engineering, ICPE, 2021.
暂无评论