Accurately predicting renewable energy output is crucial for the efficient integration of solar and wind power into modern systems. This study develops evaluates an advanced deep learning model, Channel-Time Patch Time-Series Transformer (CT-PatchTST), to forecast photovoltaic systems using annual offshore power, onshore generation data from Denmark. While original Transformer(PatchTST) model employs a channel-independent (CI) approach, it tends overlook inter-channel relationships during...

A multilayered self-normalizing gated recurrent units (MS-GRU) model is proposed for short-term electricity load forecasting. This introduces scaled exponential linear (SELU) activation function to squash the hidden states calculate output of model. Meanwhile, squashed also contribute calculation update gate, reset gate and candidate state GRU. Therefore, exploding vanishing gradient problem can be overcome in a stacked GRU neural network using this method. Fuzzy cluster-means (FCM)...

Heating load forecasting is the premise for guiding heating operation management and dispatching. a time series prediction problem which requires us to predict real-time loads in next 24 hours using available historical records weather information. In this paper, we propose model short-term based on properly designed strand-based long short term memory (LSTM) recurrent neural network. We present how data are pre-processed, loss function improve model's performance. Furthermore, an ensemble...

This study presents a rapid preparation method for self-supporting polymer electrolyte via thiol-ene click reaction. The resulting demonstrates high ionic conductivity of 9.5 × 10-4 S cm-1 at 90 °C and lithium ion transference number 0.77. symmetrical battery stably operated 1200 h 0.1 mA cm-2, significantly suppressing the formation dendrites.

In this study, some polyethylene/graphene nanoplatelet (PE-GE) composites are successfully prepared via a melt-blending process used for thermally conductive pipes. A comparison study on the effect of different fillers (i.e., graphene and aluminum oxide) thermal conductivity is conducted. The was over 2.5 W/m·K when 30 fractions GE were involved. Furthermore, an electron beam irradiation technology utilized to obtain cross-linked composite materials with excellent comprehensive performance....

Abstract This article introduces a novel hole edge inspection and metrology technology by diffractometry, which occurs when light interacts with the edge. The proposed method allows for simultaneous characterization of part error roughness conditions. Edge diffraction as bends at sharp Such diffractive fringe pattern, so-called interferogram, is directly related to geometry roughness. Image-based diffractometry was developed capture patterns. collected patterns were analyzed through...

We propose a long short-term memory (LSTM) network based encoder-decoder (E-D) model for wind power prediction (WPP). The LSTM-based E-D is constructed as an auto-encoder mapping the (WP) time-series into fixed-length representation, state of trained LSTM. Then, representation concatenated with weather forecasting information used new input to another multiple LSTM make WPP. Real data collected from farm capacity 50 MW Shan Xi province were verify conclusions. Results illustrate that...

A gated recurrent units (GRU) network based encoder-decoder (E-D) model is proposed for combined heat and power (CHP) load forecasting. First, we use the GRU E-D as an auto-encoder to map historical CHP time series into a fixed length representation. Then, concatenate representation with weather forecasting information new input another multiple GRUs prediction. Data collected from Rizhao, Shandong province used verify conclusions. Results illustrate that GRU-based can give more accurate...

This paper introduces a new digital integration that combines edge diffractometry with convolutional neural networks (CNN) for via metrology and inspection. The beam propagation method (BMP) was used to simulate the interferogram generated by characterize roughness (VER). A comprehensive database established link different fringe patterns VER CNN training. well-trained CNN-based methodology provided fast accurate assessment of VER, root mean squared error (RMSE) 0.073 an average absolute...

A concatenated LSTM (Long Short-Term Memory) architecture for CHP (combined heat and power) load forecasting was presented. Firstly, input data normalized separated into historical climate data. Then feed the two neural networks. Finally, models were as inputs to another model followed by dense layers. Relu function is used activation layers ADAM (Adaptive moment) method gradient based optimizer. The trained tested on from Nov.2016 Feb.2017 of Rizhao, Shandong. Experimental results show an...

The collaboration between renewable energy (RE) and an electric vehicles battery switch station (BSS) is a win-win strategy for both. In order to effectively coordinate manage RE BSS belonging different investors, new cooperative operation mode considering multi-stakeholder scenario proposed. By analyzing the relationship of cooperation competition them, their pursuit maximizing own interests modeled as Stackelberg game model. As leader, company determines charge/discharge prices guide...

A novel wafer edge quality inspection method based on analyzing curved-edge diffraction patterns is introduced in this paper. The patters, being collected through two approaches: (1) single point scanning and (2) areal imaging method, are affected by topography, geometry defects. After applying statistical feature extraction methods wavelet transform to the fringe data, corresponding features of various defect modes were further extracted. In summary, both proposed enabled characterization...

Abstract Line-edge roughness (LER) characterization is vital in modern semiconductor industry. An EKEI (enhanced knife edge interferometry)-based method for photomask LER characterization, being capable of a 0.01μm measurement accuracy, was proposed this paper. The changes fringe pattern caused by were derived and analyzed through cross-correlation index. A negative relationship between the value observed. results are validated both simulation experiment, indicating that can detect residual...

With the large-scale integration of renewable energy sources, demanding secondary frequency regulation task has been increasing. As a result, conventional thermal power plants that bear are no longer able to meet requirements grid. Energy storage system (ESS) become suitable source for regulation, which can effectively assist in regulation. This paper establishes plant-energy integrated and propose coordinated control strategy improving performance. proposed strategy, numerical...

Abstract Automatic generation control (AGC) plays an important role to maintain real time power and load balance, ensure the quality of supply. Power system requires each unit have satisfactory AGC performance. In addition design strategy, characteristics equipment also affect its performance in control. This paper introduces assess index unit, analyzes reasons for poor Based on strategy thermal units, proposes optimization method improve Through implementation typical industrial case...

This paper mainly expounds on the motivation of RMB internationalization and mutually beneficial relationship between Belt Road Initiative (BRI) renminbi (RMB) through literature collection.As China's economic power voice grow, yuan also needs a place in world monetary system.The inclusion into SDR is sign recognition by system.However, expected to become successful regional even international currency deepening cooperation countries along routes.

With the transformation and upgrading of energy structure, installed capacity power generation new have continued to grow in recent years. Due randomness energy, impact on grid will increase with its large-scale connection. Therefore, order ensure stability grid, it is necessary make a reasonable forecast power. So far, there been many authors using deep methods perform forecasting. However, these usually assume errors model across different time steps are independent, which inaccurate...

The integration of renewable energy resources (RERs) not only shows significant environmental effect, social effect and economic but also brings many challenges to grid planning operation power grid. Based on systematic dynamics, from the perspective changes cost benefit enterprises caused by RERs, RERs economical is studied. Finally, a simulation trend based empirical data one province demonstrates validity model proposed in this paper.