Browsing by Author "Babić A."

Now showing 1 - 3 of 3

Comparison of classical statistical methods and artificial neural network in traffic noise prediction
(2014) Nedić, Vladimir; Despotović, Danijela; Cvetanović A.; Despotović M.; Babić A.
Traffic is the main source of noise in urban environments and significantly affects human mental and physical health and labor productivity. Therefore it is very important to model the noise produced by various vehicles. Techniques for traffic noise prediction are mainly based on regression analysis, which generally is not good enough to describe the trends of noise. In this paper the application of artificial neural networks (ANNs) for the prediction of traffic noise is presented. As input variables of the neural network, the proposed structure of the traffic flow and the average speed of the traffic flow are chosen. The output variable of the network is the equivalent noise level in the given time period Leq. Based on these parameters, the network is modeled, trained and tested through a comparative analysis of the calculated values and measured levels of traffic noise using the originally developed user friendly software package. It is shown that the artificial neural networks can be a useful tool for the prediction of noise with sufficient accuracy. In addition, the measured values were also used to calculate equivalent noise level by means of classical methods, and comparative analysis is given. The results clearly show that ANN approach is superior in traffic noise level prediction to any other statistical method. © 2014 Elsevier Inc.
Inter ISO market coordination by calculating border locational marginal prices
(2013) Babić A.; Sarić A.
In this paper the methodology for solving Locational Marginal Price (LMP) differences (inconsistency of LMPs) that arise at the boundary buses between separate power markets is proposed. The algorithm developed enables us to obtain consistent LMP values at the boundary buses between interconnected ISOs. A Primal-Dual Interior Point based optimal power flow (OPF) is applied, with complete set of power system physical limit constraints, to solve a regional spot market. The OPF is implemented such that producer and consumer behaviors are modeled simultaneously, while the welfare is maximized. In this paper a generalized methodology for multiple ISOs case is proposed and later it is practically applied on two interconnected independent entities. The algorithm for approximation of cost coefficients of generators and dispatchable loads for neighboring ISOs is proposed. The developed algorithm enables participating ISOs to obtain LMPs at the boundary buses with other interconnected ISOs. By controlling interchange of electric power at the scheduled level, regional spot markets are resolved eliminating possible exercise of market power by individual interconnected ISOs. Results of proposed methodology are tested on the IEEE 118- bus power system. © 2013 AECE.
Transmission expansion planning based on Locational Marginal Prices and ellipsoidal approximation of uncertainties
(2013) Babić A.; Sarić A.; Ranković, Aleksandar
This paper proposes an algorithm for transmission expansion planning (TEP) which minimizes the congestion surplus calculated from optimized nonlinear (AC) Optimal Power Flow (OPF) and Locational Marginal Prices (LMPs). Uncorrelated and correlated uncertainties related to operating conditions of the future transmission network and expected costs of the submitted energy bids to the energy market are constrained by bounding hyper-ellipsoid around base case AC OPF solution, with assumption of additive uncertainties. Perturbed uncertain points inside a hyper-ellipsoid are selected by proposed quasi-random sampling algorithm. For these points, the linearized OPF around base case AC OPF solution is proposed. The Genetic Algorithm (GA) does selection of lines and years for transmission expansion, where the increments of the fitness function are calculated by proposed linearized AC OPF model. The results and practical aspects of the proposed methodology are illustrated on 12- and 118-bus test power system examples. © 2013 Elsevier Ltd. All rights reserved.