An Improved Neural Network Application for Short-Term Load Forecasting in Power Systems

In this paper an improved neural network application for short-term load forecasting purposes is presented. To speed up the learning process on one side, and not to jeopardize the stability performance of the learning process on the other side, the adaptive approach to the learning-rate parameter has been employed. Also, instead of learning overall load characteristics, the preprocessing of input data has been designed with the idea to learn only load demand behavior that is important for a certain period. The proposed neural network has shown good performance, even in the case of the incomplete data temperature set and at high irregularities in weekly load data.     

Sensitivity analysis of an optimal short term hydro-thermalschedule

The authors deal with the sensitivity analysis of an optimal short term hydro-thermal schedule. Methodological and practical aspects of the system economy loss (SEL) calculation caused by incorrect input data are investigated. It was shown and checked by numerical simulations that errors in the hydro plant characteristics can be studied through errors in the short term load forecasting. In a special case when differentiability conditions are satisfied (economic dispatching problem) analytical formulas for the SEL are developed. Some of the important results of sensitivity calculations concerning relevant errors in thermal cost coefficients, hydro plant characteristics, forecasted water inflows and forecasted system demands are presented. The critical input data have been selected and their tolerance margins established to preserve the beneficial effects of an optimal short term schedule     

An innovative approach for solving the restoration problem in distribution networks

An effective heuristic graph-based approach is proposed in this paper for solving the service restoration problem in distribution networks. Minimisation of the de-energised consumers’ load and reduction of the number of switching operations were considered in this service restoration application. A suitable assignment of the weighting coefficient to all branches in a de-energised area was used to decrease the number of switching operations. Prim's algorithm for finding of the minimum spanning tree logic was used to realise this approach. Other applications necessary for the optimal performance of the service restoration application were also developed and tested in this study (e.g., load flow, load reallocation of overloaded network elements, generation of the sequence of switch actions, etc.).     

Influence of accelerated aging on mechanical and structural properties of cross-linked polyethylene (XLPE) insulation

Contents  This paper describes results of laboratory accelerated aging test and the influence of different aging conditions on non-electrical properties of cross-linked polyethylene insulation (XLPE). Accelerated aging has been carried out on a cable model with different electrical and thermal stresses, and with thermal stresses in air or water as surrounding environment. Tensile strength, elongation at break, degree of cross linking and crystallinity degree of XLPE insulation have been measured and monitored. Received: 10 April 2000     

A harmonic domain computational package for nonlinear problems andits application to electric arcs

A general package for harmonic-domain computation is described. It consists of a set of routines which can be used by developers of programs for power system harmonic applications. The most basic routines have been listed. The package represents nonlinear characteristics by fitting the characteristic with a polynomial, for which special harmonic domain processing via convolutions has been developed, or by directly applying a fast Fourier transform. A model in the form of a differential equation is derived for the electric arc. It is based on simple energy balance considerations and therefore is expected to be generally valid. The computational results compare well with existing measurements. The arc model can be used for discharge lamps or for arc furnaces     

Investigation of the inrush phenomenon: a quasi-stationary approachin the harmonic domain

A novel approach for the investigation of the inrush phenomenon in single and three-phase transformers is presented. It consists of the calculation of a sequence of quasi-steady-state images using harmonic domain computation. Thus, lengthy-time domain simulations with the related round-off and truncation errors are avoided. The advantage of the method is its robustness compared to a time-domain simulation with sufficiently small time steps to represent the wave shapes of currents and voltages accurately over a relatively long time span. An important result of the analysis is the fact that the attenuation of inrush currents is not affected by the eddy current and hysteresis losses in the iron. Therefore, no discretization of the laminations is needed, which considerably simplifies the computations without any loss of accuracy. The attenuation is solely determined by the resistance of the external circuit and the total inductance of the circuit, including also that of the iron core. It is shown how remanence and off-peak switching combine to establish the initial bias which determines the magnitude of the inrush current     

Efficiency of oil removal from real wastewater with different sorbent materials

The aim of this paper was to investigate the efficiency of different sorbent materials for oil removal from wastewater. Two types of sorbents were investigated: organic (loose natural wool fibers (NWF) and recycled wool based nonwoven material (RWNM)) and inorganic (sepiolite). Sorption was carried out in continuous tubular contractor (initial oil concentration of 1511 mg/dm(3)) and batch tank (initial oil concentration of 5066 mg/dm(3)). Wool-based sorbents showed higher sorption capacity (5.56 g/g for NWF and 5.48 g/g for RWNM) compared to sepiolite (0.19 g/g) in case of sorption in batch tank. The study on sorption in continuous tubular contractor suggested that volume of oily wastewater strongly affected oil removal. The results indicated that the combination of extractive-gravimetric and FTIR spectrophotometric methods can be recommended for precise determination of oil concentration, being suitable as a controlling tool for oil detection.