Scenario Generation for Cooling,Heating,and Power Loads Using Generative Moment Matching Networks

Scenario generations of cooling,heating,and power loads are of great significance for the economic operation and stability analysis of integrated energy systems.In this paper,a novel deep generative network is proposed to model cooling,heating,and power load curves based on generative moment matching networks(GMMNs)where an auto-encoder transforms highdimensional load curves into low-dimensional latent variables and the maximum mean discrepancy represents the similarity metrics between the generated samples and the real samples.After training the model,the new scenarios are generated by feeding Gaussian noises to the scenario generator of the GMMN.Unlike the explicit density models,the proposed GMMN does not need to artificially assume the probability distribution of the load curves,which leads to stronger universality.The simulation results show that the GMMN not only fits the probability distribution of multiclass load curves very well,but also accurately captures the shape(e.g.,large peaks,fast ramps,and fluctuation),frequency-domain characteristics,and temporal-spatial correlations of cooling,heating,and power loads.Furthermore,the energy consumption of generated samples closely resembles that of real samples.

Generative Adversarial Networks with Joint Distribution Moment Matching

Generative adversarial networks(GANs)have shown impressive power in the field of machine learning.Traditional GANs have focused on unsupervised learning tasks.In recent years,conditional GANs that can generate data with labels have been proposed in semi-supervised learning and have achieved better image quality than traditional GANs.Conditional GANs,however,generally only minimize the difference between marginal distributions of real and generated data,neglecting the difference with respect to each class of the data.To address this challenge,we propose the GAN with joint distribution moment matching(JDMM-GAN)for matching the joint distribution based on maximum mean discrepancy,which minimizes the differences of both the marginal and conditional distributions.The learning procedure is iteratively conducted by the stochastic gradient descent and back-propagation.We evaluate JDMM-GAN on several benchmark datasets,including MNIST,CIFAR-10 and the Extended Yale Face.Compared with the state-of-the-art GANs,JDMM-GAN generates more realistic images and achieves the best inception score for CIFAR-10 dataset.

REAL-TIME STEREO MATCHING ALGORITHM IN PHOTODYNAMIC THERAPY BINOCULAR SURVEILLANCE SYSTEM FOR PORT WINE STAIN

A stereo matching algorithm based on the epipolar line constraint is designed to meet the real-time and the accuracy requirements. The algorithm is applied to photodynamic therapy binocular surveillance system for port wine stain （PWS） when it monitors the position of the treatment region. The corner matching based on Hu moments is used to calculate the fundamental matrix of the binocular vision system. Experimental results are in agreement with the theoretical calculation.

Efficient Interconnect Network Model for Linear Circuit Reduction

A new interconnect network model for linear netw ork reduction is presented.In this new model,the ports of the interconnect network are classified into two groups:active and passive ports.After the classification,some proprieties of the interconnect network are found to be redundant and pruned before reduction.For common interconnect networks,the scale of reduced models is smaller than 50% of the scale of previous works.

Study on Method of Removing Stripe Noise in CBERS-02 Image

Based on the project of land macroscopical monitoring by CBERS,a remote sensing image of Arongqi in Inner Mongolia was studied by different methods such as histogram matching,principal component analysis,moment matching,low-pass filter and wavelet transform.A qualitative analysis and quantitative assessment was also carried out.The results showed that wavelet transform could effectively remove stripe noise,and also kept its advantages in the details.Moment matching had a better strip removal,but it changed features in its spectrum easily and it was not fit for CBERS-02 image processing.Principal component analysis could not remove stripe noise,but also strengthened it in a certain extent.

Proportional integral derivative controller design using Legendre orthogonal functions

The Legendre orthogonal functions are employed to design the family of PID controllers for a variety of plants. In the proposed method, the PID controller and the plant model are represented with their corresponding Legendre series. Matching the first three terms of the Legendre series of the loop gain with the desired one gives the PID controller parameters. The closed loop system stability conditions in terms of the Legendre basis function pole(λ) for a wide range of systems including the first order, second order, double integrator, first order plus dead time, and first order unstable plants are obtained. For first order and double integrator plants, the closed loop system stability is preserved for all values of λ and for the other plants, an appropriate range in terms of λ is obtained. The optimum value of λ to attain a minimum integral square error performance index in the presence of the control signal constraints is achieved. The numerical simulations demonstrate the benefits of the Legendre based PID controller.

Symbolic Macromodeling for Statistical Simulation of Operational Amplifiers

Symbolic circuit simulator is traditionally applied to the small-signal analysis of analog circuits. This paper establishes a symbolic behavioral macromodeling method applicable to both small-signal and large-signal analysis of general two-stage operational amplifiers （op-amps）. The proposed method creates a two-pole parametric macromodel whose parameters are analytical functions of the circuit element parameters generated by a symbolic circuit simulator. A moment matching technique is used in deriving the analytical model parameter. The created parametric behavioral model can be used for op-amps performance simulation in both frequency and time domains. In particular, the parametric models are highly suited for fast statistical simulation of op-amps in the time-domain. Experiment results show that the statistical distributions of the op-amp slew and settling time characterized by the proposed model agree well with the transistor-level results in addition to achieving significant speedup.

Enhanced Destriping of Satellite Data of Ice Surface in Antarctica

This paper briefly reviews the cause of the striping and then develops a tapered (Chebwin & Kaiser) window finite impulse response (FIR) filter and a constrained least squares FIR filter by reason of the striping of ASTER satellite data . Both filters minimize the stripes in the visible data and simultaneously minimize any distortion in the filtered data. Finally, the results obtained by using these new filtering methods are quantitatively compared with those produced by other destriping methods.

A Scenario-Based Robust Transmission Network Expansion Planning Method for Consideration of Wind Power Uncertainties

This paper uses a novel scenario generation method for tackling the uncertainties of wind power in the transmission network expansion planning(TNEP)problem.A heuristic moment matching(HMM)method is first applied to generate the typical scenarios for capturing the stochastic features of wind power,including expectation,standard deviation,skewness,kurtosis,and correlation of multiple wind farms.Then,based on the typical scenarios,a robust TNEP problem is presented and formulated.The solution of the problem is robust against all the scenarios that represent the stochastic features of wind power.Three test systems are used to verify the HMM method and is compared against Taguchi’s Orthogonal Array(OA)method.The simulation results show that the HMM method has better performance than the OA method in terms of the trade-off between robustness and economy.Additionally,the main factors influencing the planning scheme are studied,including the number of scenarios,wind farm capacity,and penalty factors,which provide a reference for system operators choosing parameters.

Scenario-based Planning of Active Distribution Systems Under Uncertainties of Renewable Generation and Electricity Demand

The rising penetration of intermittent renewable distributed generation leads to uncertainties in the planning of electric distribution networks.Fully considering the uncertainties pertinent to wind power generation,photovoltaic power generation and load demand,this paper proposes a scenariobased model for the planning of active distribution systems.The solution obtains the optimal capacities and locations of wind and photovoltaic based distributed generators in the distribution system,whilst minimizing the active and reactive power losses as well as voltage deviation.A scenario matrix is generated using the heuristic moment matching technique that captures the stochastic moments and correlation among historical wind and photovoltaic power,and electricity demand.The scenario matrix is then incorporated to propose a stochastic planning model that considers a multi-objective index for minimizing power losses and voltage deviation.Finally,the effectiveness of the proposed planning model is confirmed using case-studies in 53-bus and IEEE 123-bus distribution systems.