Adaptive Error Curve Learning Ensemble Model for Improving Energy Consumption Forecasting

Despite the advancement within the last decades in the field of smart grids,energy consumption forecasting utilizing the metrological features is still challenging.This paper proposes a genetic algorithm-based adaptive error curve learning ensemble(GA-ECLE)model.The proposed technique copes with the stochastic variations of improving energy consumption forecasting using a machine learning-based ensembled approach.A modified ensemble model based on a utilizing error of model as a feature is used to improve the forecast accuracy.This approach combines three models,namely CatBoost(CB),Gradient Boost(GB),and Multilayer Perceptron(MLP).The ensembled CB-GB-MLP model’s inner mechanism consists of generating a meta-data from Gradient Boosting and CatBoost models to compute the final predictions using the Multilayer Perceptron network.A genetic algorithm is used to obtain the optimal features to be used for the model.To prove the proposed model’s effectiveness,we have used a four-phase technique using Jeju island’s real energy consumption data.In the first phase,we have obtained the results by applying the CB-GB-MLP model.In the second phase,we have utilized a GA-ensembled model with optimal features.The third phase is for the comparison of the energy forecasting result with the proposed ECL-based model.The fourth stage is the final stage,where we have applied the GA-ECLE model.We obtained a mean absolute error of 3.05,and a root mean square error of 5.05.Extensive experimental results are provided,demonstrating the superiority of the proposed GA-ECLE model over traditional ensemble models.

ALGORITHM FOR SPHERICITY ERROR AND THE NUMBER OF MEASURED POINTS

The data processing technique and the method determining the optimal number of measured points are studied aiming at the sphericity error measured on a coordinate measurement machine （CMM）. The consummate criterion for the minimum zone of spherical surface is analyzed first, and then an approximation technique searching for the minimum sphericity error from the form data is studied. In order to obtain the minimum zone of spherical surface, the radial separation is reduced gradually by moving the center of the concentric spheres along certain directions with certain steps. Therefore the algorithm is precise and efficient. After the appropriate mathematical model for the approximation technique is created, a data processing program is developed accordingly. By processing the metrical data with the developed program, the spherical errors are evaluated when different numbers of measured points are taken from the same sample, and then the corresponding scatter diagram and fit curve for the sample are graphically represented. The optimal number of measured points is determined through regression analysis. Experiment shows that both the data processing technique and the method for determining the optimal number of measured points are effective. On average, the obtained sphericity error is 5.78 μm smaller than the least square solution, whose accuracy is increased by 8.63%; The obtained optimal number of measured points is half of the number usually measured.

Finite-difference time-domain modeling of curved material interfaces by using boundary condition equations method

To deal with the staircase approximation problem in the standard finite-difference time-domain（FDTD） simulation,the two-dimensional boundary condition equations（BCE） method is proposed in this paper.In the BCE method,the standard FDTD algorithm can be used as usual,and the curved surface is treated by adding the boundary condition equations.Thus,while maintaining the simplicity and computational efficiency of the standard FDTD algorithm,the BCE method can solve the staircase approximation problem.The BCE method is validated by analyzing near field and far field scattering properties of the PEC and dielectric cylinders.The results show that the BCE method can maintain a second-order accuracy by eliminating the staircase approximation errors.Moreover,the results of the BCE method show good accuracy for cylinder scattering cases with different permittivities.

Detecting Circles Using a Two-Stage Approach

We propose a two-stage method for detecting circular objects in this paper. In the first stage, curves are divided as linear segments or nonlinear segments. A least square estimator is used to find the estimated centers and radii of the nonlinear segments in the second stage. The found centers and radii are then evaluated to see if there exist circles in the nonlinear segments. Both of the broken and occluded circular objects are evaluated for the proposed method. From the experimental results, it is seen that the proposed method is efficient.

Nonlinear Systems Identification via an Input-Output Model Based on a Feedforward Neural Network

This paper develops a feedforward neural network based input output model for a general unknown nonlinear dynamic system identification when only the inputs and outputs are accessible observations. In the developed model, the size of the input space is directly related to the system order. By monitoring the identification error characteristic curve, we are able to determine the system order and subsequently an appropriate network structure for systems identification. Simulation results are promising and show that generic nonlinear systems can be identified, different cases of the same system can also be discriminated by our model.