G. J. Tsekouras

Two-Stage Pattern Recognition of Load Curves for Classification of Electricity Customers

This paper describes a two-stage methodology that was developed for the classification of electricity customers. It is based on pattern recognition methods, such as k-means, Kohonen adaptive vector quantization, fuzzy k-means, and hierarchical clustering, which are theoretically described and properly adapted. In the first stage, typical chronological load curves of various customers are estimated using pattern recognition methods, and their results are compared using six adequacy measures. In the second stage, classification of customers is performed by the same methods and measures, together with the representative load patterns of customers being obtained from the first stage. The results of the first stage can be used for load forecasting of customers and determination of tariffs. The results of the second stage provide valuable information for electricity suppliers in competitive energy markets. The developed methodology is applied on a set of medium voltage customers of the Greek power system, and the obtained results are presented and discussed.

An optimized adaptive neural network for annual midterm energy forecasting

The objective of this paper is to present a new methodology for midterm energy forecasting. The proposed model is an adaptive artificial neural network (ANN), which properly transforms the input variables to differences or relative differences, in order to predict energy values not included in the training set. The ANN parameters, such as the finally used input variables, the number of neurons, initial values, and time periods of momentum term and training rate, are simultaneously selected by an optimization process. Another characteristic of the model is the use of a minimal training set of patterns. Results from an extensive analysis conducted by the developed method for the Greek power system and for different categories of customers are compared to those obtained from the application of standard regression methods.

New challenges emerged from the development of more efficient electric energy generation units

The current trends in ship technology are turning ships into more energy efficient ones. Thus, the extensive electrification of ship systems, including propulsion, is a most appealing alternative as, the more electrified a ship, the greener and more efficient it turns. In this paper, a brief overview of novel trends regarding electric energy generator schemes is made, and it is shown that these result in new challenges leading to amendments of the traditional concepts dominating over design and operation standards. The discussion is supported by the results of a model comprising a ship generic power grid with multi-type supply units.

Control system for fuel consumption minimization–gas emission limitation of full electric propulsion ship power systems

Environmental pollution caused by ships’ green house gas emissions and worldwide concern about air quality and oil supplies have led to stricter emissions regulations and fuel economy standards. In this regard, respective limits are set, while efforts to provide general guidelines for the achievement of economic and green ship operation with an urge to ship operators to apply them and return feedback. Also, specific design and operation indicators have been proposed in order to ensure compliance with new emissions regulations and fuel economy standards. Up to now, these indices are limited to ships comprising conventional propulsion systems, while full electric propulsion systems are not examined. In this article, an integrated control system that attains economically optimized and environmentally friendly operation is proposed. Moreover, appropriate reformulation of energy efficiency operation indicator is proposed for real-time assessment of gas emissions. The study is supported with the presentation of results obtained from the simulation of the operation of a ship power system comprising full electric propulsion.

Optimal Demand-Side Management and Power Generation Scheduling in an All-Electric Ship

The worldwide effort for the development of more efficient and environmentally friendly ships has led to the development of new concepts. Extensive electrification is a very promising technology for this purpose. Together with optimal power management can lead to a substantial improvement in ship efficiency ensuring, at the same time, compliance with the environmental constraints and enhancing ship sustainability. In this paper, a method for optimal demand-side management and power generation scheduling is proposed. Demand-side management is based on the adjustment of the power consumed by ship electric propulsion motors, and no energy storage facility is exploited. Dynamic programming algorithm subjected to ship operation and environmental and travel constraints is used to solve the problem for all-electric ships (AESs). Simulation results prove that the proposed method ensures cost minimization of ship power system operation, greenhouse gas (GHG) emissions limitation, and compliance with all technical and operational constraints.

Glaucoma risk assessment using a non-linear multivariable regression method

The present research investigates the relationship between the central corneal thickness (CCT), Heidelberg Retina Tomograph II (HRTII) structural measurements and intraocular pressure (IOP) using an innovative non-linear multivariable regression method in order to define the risk factors in future glaucoma development and patient management. The method is implemented to data from ninety-three open angle glaucoma eyes. The results show that in established glaucoma, CCT is significantly associated with HRTII structural measurements (maximum contour depression, cup volume inferotemporally) and IOP. They are also compared to those obtained from the application of standard linear regression methods, improving the coefficient determination R(2) by 35%, exhibiting thus the performance of the proposed methodology.

New nonlinear multivariable model shows the relationship between central corneal thickness and HRTII topographic parameters in glaucoma patients

Purpose: In this paper a new nonlinear multivariable regression method is presented in order to investigate the relationship between the central corneal thickness (CCT) and the Heidelberg Retina Tomograph (HRTII) optic nerve head (ONH) topographic measurements, in patients with established glaucoma. Methods: Forty nine eyes of 49 patients with glaucoma were included in this study. Inclusion criteria were patients with (a) HRT II ONH imaging of good quality (SD < 30 μm), (b) reliable Humphrey visual field tests (30-2 program), and (c) bilateral CCT measurements with ultrasonic contact pachymetry. Patients were classified as glaucomatous based on visual field and/or ONH damage. The relationship between CCT and topographic parameters was analyzed by using the new nonlinear multivariable regression model. Results: In the entire group, CCT was 549.78 ± 33.08 μm (range: 484–636 μm); intraocular pressure (IOP) was 16.4 ± 2.67 mmHg (range: 11–23 mmHg); MD was −3.80 ± 4.97 dB (range: 4.04 – [−20.4] dB); refraction was −0.78 ± 2.46 D (range: −6.0 D to +3.0 D). The new nonlinear multivariable regression model we used indicated that CCT was significantly related (R2 = 0.227, p < 0.01) with rim volume nasally and type of diagnosis. Conclusions: By using the new nonlinear multivariable regression model, in patients with established glaucoma, our data showed that there is a statistically significant correlation between CCT and HRTII ONH structural measurements, in glaucoma patients.

A new pattern recognition methodology for classification of load profiles for ships electric consumers

In this paper a new pattern recognition methodology is presented for the classification of the daily chronological load curves of ship electric consumers (equipment) and the determination of the respective typical load curves of each one of them. It is based on pattern recognition methods, such as k-means, adaptive vector quantisation, fuzzy k-means, self-organising maps and hierarchical clustering, which are theoretically described and properly adapted. The parameters of each clustering method are properly selected by an optimisation process, which is separately applied for each one of six adequacy measures: the error function, the mean index adequacy, the clustering dispersion indicator, the similarity matrix indicator, the Davies-Bouldin indicator and the ratio of within cluster sum of squares to between cluster variation. As a study case, this methodology is applied to a set of consumers of Hellenic Navy MEKO type frigates.

A hybrid non-linear regression midterm energy forecasting method using data mining

The objective of this paper is to present a new methodology for midterm energy forecasting in the framework of a data mining procedure. The method includes the development of a database that contains historical relevant data, such as values for energy consumption, weather parameters, statistical indices etc. The data is mined from the database, filtered, preprocessed and converted to desired forms. Data knowledge discovery is succeeded by constructing a non-linear multivariable regression model which takes in consideration correlation analysis on the selected variables. Results of the method for two types of customers, i.e. high voltage industries and residential customers are compared to standard regression methods.

Short Term Load Forecasting in Electric Power Systems with Artificial Neural Networks

The demand in electric power should be predicted with the highest possible accuracy as it affects decisively many of power system’s operations. Conventional methods for load forecasting were built on several assumptions, while they had to cope with relations between the data used that could not be described analytically. Artificial Neural Networks (ANNs) gave answers to many of the above problems and they became the predominant load forecasting technique. In this chapter the reader is first introduced to Artificial Neural Networks and their usage in forecasting the load demand of electric power systems. Several of the major training techniques are described with their pros and cons being discussed. Finally, feed- forward ANNs are used for the short-term forecasting of the Greek Power System load demand. Various ANNs with different inputs, outputs, numbers of hidden neurons etc. are examined, techniques for their optimization are proposed and the obtained results are discussed.