Optimal Load Distribution of CHP Based on Combined Deep Learning and Genetic Algorithm

Wan, Anping; Chang, Qing; Zhang, Yinlong; Wei, Chao; Agbozo, Reuben Seyram Komla; Zhao, Xiaoliang

doi:10.3390/en15207736

Cited by 3 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…TRIGPSO parameters are initialized such as particle swarm size, maximum number of iterations, learning factor, particle position, and velocity range. At the same time, the hyperparameters of the LSTM neural network were initialized, including the number of hidden layer neurons, the learning rate, and the maximum number of iterations of the LSTM network 31 .…”

Section: Ims Signaling Storm Warning Based On Trigpso-lstm-am-kmeans ...mentioning

confidence: 99%

Research on predicting alrm of Signaling Storm by hybrid LSTM-AM optimized with improved PSO

Tong,

Jia,

Deng

et al. 2023

Preprint

View full text Add to dashboard Cite

For the voice services under 5G, the prediction of the IMS signaling storm is the foundation for ensuring the stable operation of Voice over New Radio (VoNR) services and strengthening the intelligent management of 5G networks. Simultaneously, it is also an important approach for operators to enhance their core competitiveness. However, the IP Multimedia Subsystem (IMS) signaling storm prediction alarm function for live network systems is still not robust, with most attention being directed towards equipment fault detection and network element health monitoring. Given this limitation of the live network management system, a method combining 2 modules of prediction and judgment is proposed in this research to realize a more advanced prediction of IMS signaling storms. Among this proposed method, a new neurally network model named Trigonometric Particle Swarm Ptimization-Long Short Term Memory-Attention Mechanism (TRIGPSO-LSTM-AM) is constructed and served as the cornerstone of the method. Firstly, the LSTM-AM model, which combines temporal recurrent neural networks with attention mechanism, is established to predict the key index values of the IMS. At the same time, the traditional Particle Swarm Optimization (PSO) algorithm is improved, and a more intelligent particle swarm optimization algorithm based on trigonometric transformation, named TRIGPSO, is proposed to enhance the convergence of the prediction model. Then, an alarm judgment module is built, and the output of the prediction module is utilized as the input for this module. Clustering is achieved based on the KMeans algorithm, and each class is mapped to the alarm level, thereby informing the network management to execute the corresponding alarm operation. Finally, the effectiveness and rationality of the proposed method are validated through several groups of comparative experiments.

show abstract

Section: Ims Signaling Storm Warning Based On Trigpso-lstm-am-kmeans ...mentioning

confidence: 99%

Research on predicting alrm of Signaling Storm by hybrid LSTM-AM optimized with improved PSO

Tong,

Jia,

Deng

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Based on this information, conclusions can be drawn about the advantages and disadvantages of both methods that are included in the SWOT analysis. The main advantage of genetic algorithms is the ability to solve complex systems with many elements [161]. This algorithm can be used for optimization [162,163].…”

mentioning

confidence: 99%

Review of Methods for Diagnosing the Degradation Process in Power Units Cooperating with Renewable Energy Sources Using Artificial Intelligence

Ziółkowski,

Drosińska-Komor,

Głuch

et al. 2023

Energies

View full text Add to dashboard Cite

This work is based on a literature review (191). It mainly refers to two diagnostic methods based on artificial intelligence. This review presents new possibilities for using genetic algorithms (GAs) for diagnostic purposes in power plants transitioning to cooperation with renewable energy sources (RESs). The genetic method is rarely used directly in the modeling of thermal-flow analysis. However, this assignment proves that the method can be successfully used for diagnostic purposes. The GA method was presented in this work for thermal-flow studies of steam turbines controlled from the central power system to obtain the stability of RESs. It should be remembered that the development of software using genetic algorithms to locate one-off degradations is necessary for a turbine that works sustainably with RESs. In this paper, against the background of the review, diagnostic procedures create an inverse model of a thermal power plant. Algorithms were used to detect fast global extremes through the convergence of simulated signatures with signs explaining degradation. In addition, statistical dependencies are used in the selection phase to accelerate fault detection. The created procedure allows obtaining a diagnosis in the form of a single degradation. This procedure turns out to be quite effective for the above example.

show abstract

Short-term power load forecasting for combined heat and power using CNN-LSTM enhanced by attention mechanism

Wan

Chang

Al-Bukhaiti

et al. 2023

Energy

View full text Add to dashboard Cite

Optimal Load Distribution of CHP Based on Combined Deep Learning and Genetic Algorithm

Cited by 3 publications

References 12 publications

Research on predicting alrm of Signaling Storm by hybrid LSTM-AM optimized with improved PSO

Research on predicting alrm of Signaling Storm by hybrid LSTM-AM optimized with improved PSO

Review of Methods for Diagnosing the Degradation Process in Power Units Cooperating with Renewable Energy Sources Using Artificial Intelligence

Short-term power load forecasting for combined heat and power using CNN-LSTM enhanced by attention mechanism

Contact Info

Product

Resources

About