RL and AHP-Based Multi-Timescale Multi-Clock Source Time Synchronization for Distribution Power Internet of Things

Time synchronization(TS)is crucial for ensuring the secure and reliable functioning of the distribution power Internet of Things(IoT).Multi-clock source time synchronization(MTS)has significant advantages of high reliability and accuracy but still faces challenges such as optimization of the multi-clock source selection and the clock source weight calculation at different timescales,and the coupling of synchronization latency jitter and pulse phase difference.In this paper,the multi-timescale MTS model is conducted,and the reinforcement learning(RL)and analytic hierarchy process(AHP)-based multi-timescale MTS algorithm is designed to improve the weighted summation of synchronization latency jitter standard deviation and average pulse phase difference.Specifically,the multi-clock source selection is optimized based on Softmax in the large timescale,and the clock source weight calculation is optimized based on lower confidence bound-assisted AHP in the small timescale.Simulation shows that the proposed algorithm can effectively reduce time synchronization delay standard deviation and average pulse phase difference.

Real-Time Information System of Power Plant Based on B/S Computing Mode

This paper introduces the system structure and work principle of the upgraded real time information system in Wangting Power Plant, and then expounds the realization way and function features of this system on B/S computing mode. The results of field application show the new system has good capability, reliability and expandability.

A Combined Method of Temporal Convolutional Mechanism and Wavelet Decomposition for State Estimation of Photovoltaic Power Plants

Time series prediction has always been an important problem in the field of machine learning.Among them,power load forecasting plays a crucial role in identifying the behavior of photovoltaic power plants and regulating their control strategies.Traditional power load forecasting often has poor feature extraction performance for long time series.In this paper,a new deep learning framework Residual Stacked Temporal Long Short-Term Memory(RST-LSTM)is proposed,which combines wavelet decomposition and time convolutional memory network to solve the problem of feature extraction for long sequences.The network framework of RST-LSTM consists of two parts:one is a stacked time convolutional memory unit module for global and local feature extraction,and the other is a residual combination optimization module to reduce model redundancy.Finally,this paper demonstrates through various experimental indicators that RST-LSTM achieves significant performance improvements in both overall and local prediction accuracy compared to some state-of-the-art baseline methods.

Deep Learning for Financial Time Series Prediction:A State-of-the-Art Review of Standalone and HybridModels

Financial time series prediction,whether for classification or regression,has been a heated research topic over the last decade.While traditional machine learning algorithms have experienced mediocre results,deep learning has largely contributed to the elevation of the prediction performance.Currently,the most up-to-date review of advanced machine learning techniques for financial time series prediction is still lacking,making it challenging for finance domain experts and relevant practitioners to determine which model potentially performs better,what techniques and components are involved,and how themodel can be designed and implemented.This review article provides an overview of techniques,components and frameworks for financial time series prediction,with an emphasis on state-of-the-art deep learning models in the literature from2015 to 2023,including standalonemodels like convolutional neural networks(CNN)that are capable of extracting spatial dependencies within data,and long short-term memory(LSTM)that is designed for handling temporal dependencies;and hybrid models integrating CNN,LSTM,attention mechanism(AM)and other techniques.For illustration and comparison purposes,models proposed in recent studies are mapped to relevant elements of a generalized framework comprised of input,output,feature extraction,prediction,and related processes.Among the state-of-the-artmodels,hybrid models like CNNLSTMand CNN-LSTM-AM in general have been reported superior in performance to stand-alone models like the CNN-only model.Some remaining challenges have been discussed,including non-friendliness for finance domain experts,delayed prediction,domain knowledge negligence,lack of standards,and inability of real-time and highfrequency predictions.The principal contributions of this paper are to provide a one-stop guide for both academia and industry to review,compare and summarize technologies and recent advances in this area,to facilitate smooth and informed implementation,and to highlight future research directions.

Primary frequency control considering communication delay for grid-connected offshore wind power systems

Offshore wind farms are becoming increasingly distant from onshore centralized control centers,and the communication delays between them inevitably introduce time delays in the measurement signal of the primary frequency control.This causes a deterioration in the performance of the primary frequency control and,in some cases,may even result in frequency instability within the power system.Therefore,a frequency response model that incorporates communication delays was established for power systems that integrate offshore wind power.The Padéapproximation was used to model the time delays,and a linearized frequency response model of the power system was derived to investigate the frequency stability under different time delays.The influences of the wind power proportion and frequency control parameters on the system frequency stability were explored.In addition,a Smith delay compensation control strategy was devised to mitigate the effects of communication delays on the system frequency dynamics.Finally,a power system incorporating offshore wind power was constructed using the MATLAB/Simulink platform.The simulation results demonstrate the effectiveness and robustness of the proposed delay compensation control strategy.

Analysis and Modeling of Time Output Characteristics for Distributed Photovoltaic and Energy Storage

Due to the unpredictable output characteristics of distributed photovoltaics,their integration into the grid can lead to voltage fluctuations within the regional power grid.Therefore,the development of spatial-temporal coordination and optimization control methods for distributed photovoltaics and energy storage systems is of utmost importance in various scenarios.This paper approaches the issue from the perspective of spatiotemporal forecasting of distributed photovoltaic(PV)generation and proposes a Temporal Convolutional-Long Short-Term Memory prediction model that combines Temporal Convolutional Networks(TCN)and Long Short-Term Memory(LSTM).To begin with,an analysis of the spatiotemporal distribution patterns of PV generation is conducted,and outlier data is handled using the 3σ rule.Subsequently,a novel approach that combines temporal convolution and LSTM networks is introduced,with TCN extracting spatial features and LSTM capturing temporal features.Finally,a real spatiotemporal dataset from Gansu,China,is established to compare the performance of the proposed network against other models.The results demonstrate that the model presented in this paper exhibits the highest predictive accuracy,with a single-step Mean Absolute Error(MAE)of 1.782 and an average Root Mean Square Error(RMSE)of 3.72 for multi-step predictions.

Intelligent modeling and optimization on time-sharing power dispatching system for electrolytic zinc process

Based on real time price counting of electric power, an optimization model of time sharing power for electrolytic zinc process(EZP) was established by means of an incremental fuzzy neural network(FNN), which is adopted to approximate the relationship of current efficiency, current density and acidity. Penalty function introduced and optimal objective function reconstructed, a single loop simulated annealing algorithm(SAA) by using mutation and extending searching spaces was used to obtain optimal time sharing power scheme. Industrial practical results show that the whole system can greatly decrease the power consumption of EZP and increase the time sharing profits.

A Method for Improving Power Distribution Characteristics of Space Time Block Codes

Improving power distribution characteristics of space time block codes(STBCs),namely peak to average power ratio(PAPR),average to minimum power ratio(Ave/min),and probability of transmitting"zero"by antenna,makes easier their practical implementation.To this end,this study proposes to multiply full diversity STB C with a non-singular matrix in multiple input multiple output(MIMO)or multiple input single output(MISO)systems with linear or maximum likelihood(ML)receivers.It is proved that the obtained code achieves full diversity and the order of detection complexity does not change.The proposed method is applied to different types of STBCs.The bit error rate(BER)and power distribution characteristics of the new codes demonstrate the superiority of the introduced method.Further,lower and upper bounds on the BER of the obtained STBCs are derived for all receivers.The proposed method provides trade-off among PAPR,spectral efficiency,energy efficiency,and BER.

A Remote Real-Time Monitoring System for Power Quality

An introduction is made to the composition, design method and engineering application of a remote real time monitoring system of power quality in substations based on internet. With virtual instrument and network technique adopted, this system is characterized by good real time property, high reliability, plentiful functions, and so on. It also can be used to monitor the load of a substation, such as electric locomotives.

Long-time Convergence of Numerical Approximations for Semilinear Parabolic Equations (Ⅱ)

In this article we extend ours framework of long time convergence for numeracal approximations of semilinear parabolic equations prorided in “Wu Haijun and Li Ronghua, Northeast. Math. J., 16(1)(2000), 1—28”, to the Gauss Ledendre full discretization. When apply the result to the Crank Nicholson finiteelement full discretization of the Navier Stokes equations, we can remore the grid ratio restriction of “Heywood, J. G. and Rannacher, R., SIAM J. Numer. Anal., 27(1990), 353—384”, and weaken the stability condition on the continuous solution.

An optimal strategy for coordinating and dispatching “source-load” in power system based on multiple time scales

Due to the phenomenon of abandoning wind power and photo voltage(PV)power in the“Three Northern Areas”in China,this paper presents an optimal strategy for coordinating and dispatching“source-load”in power system based on multiple time scales.On the basis of the analysis of the uncertainty of wind power and PV power as well as the characteristics of load side resource dispatching,the optimal model of coordinating and dispatching“source-load”in power system based on multiple time scales is established.It can simultaneously and effectively dispatch conventional generators,wind plant,PV power station,pumped-storage power station and load side resources by optimally using three time scales:day-ahead,intra-day and real-time.According to the latest predicted information of wind power,PV power and load,the original generation schedule can be rolled and amended by using the corresponding time scale.The effectiveness of the model can be verified by a real system.The simulation results show that the proposed model can make full use of“source-load”resources to improve the ability to consume wind power and PV power of the grid-connected system.

Grey series time-delay predicting model in state estimation for power distribution networks

A new combined model is proposed to obtain predictive data value applied in state estimation for radial power distribution networks. The time delay part of the model is calculated by a recursive least squares algorithm of system identification, which can gradually forget past information. The grey series part of the model uses an equal dimension new information model (EDNIM) and it applies 3 points smoothing method to preprocess the original data and modify remnant difference by GM(1,1). Through the optimization of the coefficient of the model, we are able to minimize the error variance of predictive data. A case study shows that the proposed method achieved high calculation precision and speed and it can be used to obtain the predictive value in real time state estimation of power distribution networks.

SRDAAR－QNPP：a computer code system for the real－time dose assessment of an accident release for Qinshan Nuclear Power Plant

The paper presents a computer code system 'SRDAAR- QNPP' for the real-time dose as-sessment of an accident release for Qinshan Nuclear Power Plant. It includes three parts:thereal-time data acquisition system, assessment computer. and the assessment operating code system. InSRDAAR-QNPP, the wind field of the surface and the lower levels are determined hourly by using amass consistent three-dimension diasnosis model with the topographic following coordinate system.A Lagrangin Puff model under changing meteorological condition is adopted for atmosphericdispersion, the correction for dry and wet depositions. physical decay and partial plume penetrationof the top inversion and the deviation of plume axis caused by complex terrain have been taken in-to account. The calculation domain areas include three square grid areas with the sideline 10 km, 40krn and 160 km and a grid interval 0.5 km, 2.0 km, 8.0 km respectively. Three exposure pathwaysare taken into account:the external exposure from immersion cloud and passing puff, the internalexposure from inhalation and the external exposure from contaminated ground. This system is ableto provide the results of concentration and dose distributions within 10 minutes after the data havebeen inputed.

Synthesis Scheme for Low Power Designs Under Timing Constraints

To minimize the power consumption with resources operating at multiple voltages a time-constrained algorithm is presented.The input to the scheme is an unscheduled data flow graph (DFG),and timing or resource constraints.Partitioning is considered with scheduling in the proposed algorithm as multiple voltage design can lead to an increase in interconnection complexity at layout level.That is,in the proposed algorithm power consumption is first reduced by the scheduling step,and then the partitioning step takes over to decrease the interconnection complexity.The time-constrained algorithm has time complexity of O(n 2),where n is the number of nodes in the DFG.Experiments with a number of DSP benchmarks show that the proposed algorithm achieves the power reduction under timing constraints by an average of 46 5%.

Source time functions of the 1999, Jiji (Chi-Chi) earthquake from GDSN long period waveform data using aftershocks as empirical Green's functions

A large earthquake (Mw=7.6) occurred in Jiji (Chi-Chi), Taiwan, China on September 20, 1999, and was followed by many moderate-size shocks in the following days. Two of the largest aftershocks with the magnitudes of Mw=6.1 and Mw=6.2, respectively, were used as empirical Green's functions (EGFs) to obtain the source time functions (STFs) of the main shock from long-period waveform data of the Global Digital Seismograph Network (GDSN) including IRIS, GEOSCOPE and CDSN. For the Mw=6.1 aftershock of September 22, there were 97 pairs of phases clear enough from 78 recordings of 26 stations; for the Mw=6.2 aftershock of September 25, there were 81 pairs of phases clear enough from 72 recordings of 24 stations. For each station, 2 types of STFs were retrieved, which are called P-STF and S-STF due to being from P and S phases, respectively. Totally, 178 STF individuals were obtained for source-process analysis of the main shock. It was noticed that, in general, STFs from most of the stations had similarities except that those in special azimuths looked different or odd due to the mechanism difference between the main shock and the aftershocks; and in detail, the shapes of the STFs varied with azimuth. Both of them reflected the stability and reliability of the retrieved STFs. The comprehensive analysis of those STFs suggested that this event consisted of two sub-events, the total duration time was about 26 s, and on the average, the second event was about 7 s later than the first one, and the moment-rate amplitude of the first event was about 15% larger than that of the second one.

Time-domain clustered transmit power adaptation for OFDM system in fading channels

This paper proposes a time-domain clustered transmitter power adaptation scheme for orthogonal frequency division multiplexing (OFDM) system, which can significantly reduce the feedback amount during power adaptation comparison with conventional frequency-domain adaptation schemes. It was found that the cluster size plays an important role on the adaptation performance, especially for the vehicular environment. Simulation results showed that using Lagrange interpolation to obtain an explicit curve of Doppler frequency vs cluster size yields good trade-off between the resulted bit error rate (BER) and the amount of feedback.

Laboratory creep tests for time-dependent properties of a marble in Jinping Ⅱ hydropower station

In order to investigate the time-dependent behaviors of deep hard rocks in the diversion tunnel of Jinping II hydropower station, uniaxial creep tests were carried out by using the triaxial testing machine RC-2000. The axial compressive load was applied step by step and each creep stage was kept for over several days. Test results show that： （1） The lateral deformation of rock specimens is 2-3 times the axial compressive deformation and accelerates drastically before damage, which may be employed as an indicator to predict the excavation-induced instability of rocks. （2） The resultant deformation changes from compression to expansion when the Poisson＇s ratio is larger than 0.5, indicating the starting point of damage. （3） In the step-loading stages, the Poisson＇s ratio approximately remains constant; under constantly imposed load, the Poisson＇s ratio changes with elapsed time, growing continuously before the specimen is damaged. （4） When the applied load reaches a certain threshold value, the rock deteriorates with time, and the strength of rocks approximately has a negative exponent relation with time. （5） The failure modes of the deep marble are different in long- and short-term loading conditions. Under the condition of short-term loading, the specimen presents a mode of tensile failure; while under the condition of long-term loading, the specimen presents a mode of shear failure, followed by tensile failure.

Longtime Convergence of Numerical Approximations for Semilinear Parabolic Equations (Ⅰ)

The numerical approximations of the dynamical systems governed by semilinear parabolic equations are considered. An abstract framework for long time error estimates is established. When applied to reaction diffusion equation, Navier Stokes equations and Chan Hilliard equation, approximated by Galerkin and nonlinear Galerkin methods in space and by Runge Kutta method in time, our framework yields error estimates uniform in time.

Hierarchical and Distributed Optimal Control Strategy for Power and Power Quality of Microgrid Based on Finite-Time Consistency

Droop control is one of the main control strategies of islanded microgrid(MG),but the droop control cannot achieve reasonable power distribution of microgrid,resulting in frequency and voltage deviation from the rating value,which needs the upper control link to eliminate the deviation.However,at present,most layered control requires a centralized control center,which excessively relies on microgrid central controller(MGCC)and real-time communication among distributed generation(DG),which has certain limitations.To solve the above problems,this paper proposes a hierarchical distributed power and power quality optimization strategy based on multi-agent finite time consistency algorithm(MA-FTCA).Firstly,based on the first layer droop control,MA-FTCA is applied to introduce frequency and voltage compensation to stabilize the system frequency and voltage at the rated value.Secondly,in the third layer,the MA-FTCA is adopted to estimate the total active power and total reactive power spare capacity of the system,to realize the reasonable distribution of active power and reactive power output of each DG according to its proportion of spare capacity when the system load side changes.The control strategy proposed in this paper adopts a completely distributed control method and does not need a centralized control center in each layer of control.Finally,MATLAB/Simulink simulation platform is used to verify the correctness and effectiveness of the proposed optimization strategy.

Long-pulse power-supply system for EAST neutral-beam injectors

The long-pulse power-supply system equipped for the 4 MW beam-power ion source is comprised of three units at ASIPP（Institute of Plasma Physics, Chinese Academy of Sciences）： one for the neutralbeam test stand and two for the EAST neutral-beam injectors（NBI-1 and NBI-2, respectively）. Each power supply system consists of two low voltage and high current DC power supplies for plasma generation of the ion source, and two high voltage and high current DC power supplies for the accelerator grid system. The operation range of the NB power supply is about 80 percent of the design value, which is the safe and stable operation range. At the neutral-beam test stand, a hydrogen ion beam with a beam pulse of 150 s, beam power of 1.5 MW and beam energy of 50 ke V was achieved during the long-pulse testing experiments. The result shows that the power-supply system meets the requirements of the EAST-NBIs fully and lays a basis for achieving plasma heating.