SHORT TERM LOAD
FORECASTING USING ARTIFICIAL NEURAL NETWORKS
ABSTRACT
In electrical engineering, load forecasting is being tried out using most traditional forecasting models as well as artificial intelligence techniques as it is one of the major research fields. Electrical load forecasting is an integral process in planning and operation of electrical power utilities. The significance of load forecasting includes planning for transmission and distribution facilities as well as new generation plants. It is the basis for economic dispatch, unit commitment and load management. This work presents a new approach for short term electrical load forecasting using artificial neural networks (ANN).
An attempt has been made to examine the feasibility of various mathematical models. To make these mathematical models to yield satisfactory and acceptable results, various system models are formulated considering various combination of parameters like base load component, day of the week, load inertia, short term trends, autocorrelation, the length of the past data, etc. various modifications of BP have been proposed, to explore the ideal combination that suit the forecasting need of large utilities like state Electricity Boards (SEBs) and regional grids. Further, the load dynamics are extensively studied to identify the parameters for system modeling.
BIBLIOGRAPHY
[1]. A.G. Baklrtzis, V. Petrldis, S. J. Klartzls, M. C. Alexladls,” A neural network short term load forecasting model for the Greek power system” IEEE transactions on power systems, vol.11,no.2, may 1996.
[2]. Osama A. Mohammed, Dong C. Park and Rim S. Merchant, “Implementation of an Adaptive Neural Network Short-Term Electric Load Forecasting System in the Energy Control Center”.
[3]. James W. Taylor and Roberto Buizza, “ Neural Network Load Forecasting With
Weather Ensemble Predictions”, IEEE TRANSACTIONS ON POWER SYSTEMS, VOL. 17, NO. 3, AUGUST 2002
[4]. Tomonobu Senjyu, Member, IEEE, Hitoshi Takara, Katsumi Uezato, and Toshihisa Funabashi, Senior Member, IEEE “One-Hour-Ahead Load Forecasting
Using Neural Network” IEEE TRANSACTIONS ON POWER SYSTEMS, VOL. 17, NO. 1, FEBRUARY 2002.
[5]. Nahi Kandil, Vijay Sood, Maarouf Saad, “USE OF A"s FOR SHORT-TERM LOAD FORECASTING”, Proceedings of the 1999 IEEE Canadian Conference on Electrical and Computer Engineering Shaw Conference Center, Edmonton, Alberta, Canada May 9-12 1999.
[ 61 Gross, G. and Galiana, ED., “Short-Term Forecasting”, Proc. IEEE, vol. 75, No 12, pp. 1558-1573, 1987.
[7] El-Sharkawi, M. and Niebur, D., “Short-Tern Load Forecasting with Artificial Neural Networks: theInternational Activities”, IEEE Power Engineering Society: Tutorial Course on Artificial Neural Networks with Applications to Power Systems, pp. 90-103, 1996.
[8] Soucek, B. and Soucek, M., Neural and Massively Parallel Computers, The Sixth Generation, Wiley, NewYork, 1988.
[9] Widrow, B. and Stems, D., Adaptive Signal Processing, New York, Prentice-Hall 1985.
[10] Park, D.C., El-Sharakawi, M.A., and Marks 11, R.J., “Electric Load Forecasting Using Artificial Neural Networks,” ZEEE Trans. on Power Systems, 1991, 6,
[11] Sobajic, D.J., and Pao, Y.H., “Artificial Neural-net Based Dynamic Security Assessment for Electric Power Systems,” IEEE Trans. on Power Systems 1989, 4, (l), pp. 220-228.
[12] Nguyen, T.T. and Bui, H.X., “Neural Network Dynamic Load Model,” Proc, 4th International Symposium on Expert System Application to Power Systems, 1993, Melbourne, Australia, pp. 467-472.
[13] Kandil, N., Sood, V.K., Khorasani, K., and Patel, R.V., “Fault Identification in an AC-DC transmission System Using Neural Networks,” IEEE Trans. on Power Systems,
1992,7, (2), pp. 812-819.
[14] Narendra, K.S. and Parthasarathy, K., “Identification and Control of Dynamical Systems Using Neural Networks,” IEEE Trans. on Neural Networks, vol. 1. no. 1.
(2), pp. 442-449. pp. 4-27, 1990.
[15]. Nahi Kandil, Vijay Sood, Maarouf Saad, “USE OF A"s FOR SHORT-TERM LOAD FORECASTING”, Proceedings of the 1999 IEEE Canadian Conference on Electrical and Computer Engineering Shaw Conference Center, Edmonton, Alberta, Canada May 9-12 1999.
[16]. Wiktor Charytoniuk, Member: IEEE, and Mo-Shing Chen, Fellow, IEEE, “Very Short-Term Load Forecasting Using Artificial Neural Networks”, lEFFTRANSACT'IONS ON IPOWRRSYSTRMS, VOL. IS. NO. I, FEBRUARY
[17]. Kit Po Wong, “ARTIFICIAL INTELLIGENCE AND NEURAL NETWORK APPLICATIONS IN POWER SYSTEMS”, IEE 2nd International Conference on Advances in Power System Control, Operation and Management, December 1993, Hong Kong
[18]. James A. Momoh Yanchun Wang Mahmoud IZlfayoumy, “ARTIFICIAL NEURAL NETWORK BASED LOAD FORECASTING”,
[19]. Y. Rui A.A. El-Keib, ” A Review of ANN-based Short-Term Load Forecasting Models”, 0094-2898/95 $04.00 0 1995 IEEE
Modelling and Harmonic analysis of domestic loads and harmonic mitigation techniques in industrial distribution system
SYNOPSIS
Distribution system is the part of power system consisting of different combinations of linear and non-linear loads. The widespread application of power electronics is introducing non-linear loads in the distribution system resulting in the distortion of current voltage waveforms. The objective of this project is to study the harmonic distribution in a typical distribution system and suggest suitable harmonic compensation technique.
Various domestic loads such as TV/CPU, computer, fluorescent lamp, CFL lamp, fan, light dimmer, washing machine, water pump, refrigerator, air conditioner dish washer and small scale industry loads such as adjustable speed drive, arc welder and lift water pump are modelled in PSCAD/EMTDC. These models are then used for harmonic analysis of domestic and small scale industrial system. Voltage and current harmonics injected at point of common coupling (PCC) due to these nonlinear loads is tested for an individual house, village and a typical industry. THD of voltage and current are used as harmonic indices and harmonic components are found.
Case study of harmonic analysis of CARTOSAT-2A distribution system of ISRO, Bangalore is performed by using the models of above nonlinear loads. To validate the modeling of nonlinear loads, source current and voltage THDs are found at PCC and are matching with the practical data provided.
Current and voltage harmonic analysis is performed for standard IEEE 13-Bus medium voltage industrial distribution system by performing simulation using PSCAD/EMTDC. Adjustable speed drive is modelled and used as nonlinear loads and RL loads as static loads. The harmonic distribution in found and THD of voltage and current is found at all buses. Harmonic mitigation is performed by using single tuned, double tuned and reactance one-port filters. Also, use of shunt and series active filters is made for mitigating harmonics at PCC. Sensitivity analysis is then performed to analyse the effect on harmonic distribution and filter performance various load conditions, variation in system or transformer or feeder X/R ratio, change in filter positions and effect of power factor correction capacitor.
Short term wind power forecasting using adaptive neuro-fuzzy inference systems
Johnson, P.; Negnevitsky, M.; Muttaqi, K.M.
Power Engineering Conference, 2007. AUPEC 2007. Australasian Universities
Volume , Issue , 9-12 Dec. 2007 Page(s):1 - 6
Digital Object Identifier 10.1109/AUPEC.2007.4548099
Summary:As the global political will to address climate change gains momentum, the issues associated with integrating an increasing penetration of wind power into power systems need to be addressed. This paper summarises the current trends in wind power and how it is accepted into electricity markets. The need for accurate short term wind power forecasting is highlighted with particular reference to the five minute dispatch interval for the proposed Australian Wind Energy Forecasting System. Results from a case study show that adaptive neuro-fuzzy inference system (ANFIS) models can be a useful tool for short term wind power forecasting providing a performance improvement over the industry standard "persistence" approach.
Johnson, P.; Negnevitsky, M.; Muttaqi, K.M.
Power Engineering Conference, 2007. AUPEC 2007. Australasian Universities
Volume , Issue , 9-12 Dec. 2007 Page(s):1 - 6
Digital Object Identifier 10.1109/AUPEC.2007.4548099
Summary:As the global political will to address climate change gains momentum, the issues associated with integrating an increasing penetration of wind power into power systems need to be addressed. This paper summarises the current trends in wind power and how it is accepted into electricity markets. The need for accurate short term wind power forecasting is highlighted with particular reference to the five minute dispatch interval for the proposed Australian Wind Energy Forecasting System. Results from a case study show that adaptive neuro-fuzzy inference system (ANFIS) models can be a useful tool for short term wind power forecasting providing a performance improvement over the industry standard "persistence" approach.
Microarchitecture-level power management
Iyer, A.; Marculescu, D.
Very Large Scale Integration (VLSI) Systems, IEEE Transactions on
Volume 10, Issue 3, Jun 2002 Page(s): 230 - 239
Digital Object Identifier 10.1109/TVLSI.2002.1043326
Summary: In this paper, we present a strategy for run-time profiling to optimize the configuration of a superscalar microprocessor dynamically so as to save power with minimum-performance penalty. The configuration of the processor is changed according to the parallelism and power profile of the running application. To identify the optimal configuration, additional hardware with minimal overhead is used to detect the parts of the running application which have good potential for energy savings. Experiments on some benchmark programs show good savings in total energy consumption; we have observed a mean decrease of 18% in average power, and 9% in total energy. Our proposed approach can be used for energy-aware computing in either portable applications or in desktop environments where power density is becoming a concern. This approach can also be incorporated in power-management strategies like advanced configuration and power interface (ACPI) as a replacement for classic thermal management schemes such as static-clock throttling. Our approach is shown to be better than static-throttling methods presently used in power management.
Iyer, A.; Marculescu, D.
Very Large Scale Integration (VLSI) Systems, IEEE Transactions on
Volume 10, Issue 3, Jun 2002 Page(s): 230 - 239
Digital Object Identifier 10.1109/TVLSI.2002.1043326
Summary: In this paper, we present a strategy for run-time profiling to optimize the configuration of a superscalar microprocessor dynamically so as to save power with minimum-performance penalty. The configuration of the processor is changed according to the parallelism and power profile of the running application. To identify the optimal configuration, additional hardware with minimal overhead is used to detect the parts of the running application which have good potential for energy savings. Experiments on some benchmark programs show good savings in total energy consumption; we have observed a mean decrease of 18% in average power, and 9% in total energy. Our proposed approach can be used for energy-aware computing in either portable applications or in desktop environments where power density is becoming a concern. This approach can also be incorporated in power-management strategies like advanced configuration and power interface (ACPI) as a replacement for classic thermal management schemes such as static-clock throttling. Our approach is shown to be better than static-throttling methods presently used in power management.
A new intelligent algorithm for online voltage stability assessment and monitoring
Abstract:This paper presents a new approach for assessing power system voltage stability based on artificial feed forward neural network (FFNN). The approach uses real and reactive power, as well as voltage vectors for generators and load buses to train the neural net (NN). The input properties of the NN are generated from offline training data with various simulated loading conditions using a conventional voltage stability algorithm based on the L-index. The performance of the trained NN is investigated on two systems under various voltage stability assessment conditions. Main advantage is that the proposed approach is fast, robust, accurate and can be used online for predicting the L-indices of all the power system buses simultaneously. The method can also be effectively used to determining local and global stability margin for further improvement measures.
Electrical machine design based on energy conversion efficiency using Finite element
Economic dispatch problem solving using Particle Swarm Optimization (PSO) IEEE-2005
Frequency control in an interconnected power system in restructured power system using HVDC tie line
A stabilization of frequency oscillations using a power modulationcontrol of HVDC link in a parallel AC-DC interconnected system
Summary:When an interconnected AC power system is subjected to a large load with rapid change, system frequency may be considerably disturbed and becomes oscillatory. By utilizing the system interconnections as the control channels of high-voltage direct current (HVDC) link, the tie-line power modulation of HVDC link via the interconnections creates a sophisticated stabilization of frequency oscillations in AC systems. This paper takes this advantage of the HVDC link to implement a concept of frequency stabilization in interconnected power systems. A power modulation controller is designed based on stabilization of the inter-area oscillation mode. The techniques of overlapping decompositions and eigenvalue assignment are applied to establish the state feedback scheme of controller. Simulation study exhibits the significant effects of the proposed control
Summary:When an interconnected AC power system is subjected to a large load with rapid change, system frequency may be considerably disturbed and becomes oscillatory. By utilizing the system interconnections as the control channels of high-voltage direct current (HVDC) link, the tie-line power modulation of HVDC link via the interconnections creates a sophisticated stabilization of frequency oscillations in AC systems. This paper takes this advantage of the HVDC link to implement a concept of frequency stabilization in interconnected power systems. A power modulation controller is designed based on stabilization of the inter-area oscillation mode. The techniques of overlapping decompositions and eigenvalue assignment are applied to establish the state feedback scheme of controller. Simulation study exhibits the significant effects of the proposed control
Frequency control in an interconnected power system in restructured power system with Fuzzy Controller
Power Distribution Management System using WAP(wire less application protocol)
Wireless access to SCADA system
Summary: The use of the wireless application protocol architecture to provide a wireless channel to access the database operating under the commonly used distributed network protocol system running for SCADA in the power process plant is discussed. A distributed network protocol (DNP) is developed to be applied in the SCADA systems while the terminals and RTUs are presently connected through local area network. The conditions in a process plant are harsh and the site is remote. Resources for data communication are difficult to obtain under the environment and a wireless channel communication through a cellular phone is practical and efficient. The WAP API on power industry applications is one of the area for extensive attention. The WAP architecture provides an open application programming environment for defining the WAP server and WAP application interface modules. It is used to investigate the different WAP protocols and the wireless application environment on the Internet and mobile service for accessing a computing system. The Nokia WAP toolkit is used as the tool for investigation. Eventually, the mobile service can be incorporated into the DNP protocol such that a wireless WAP phone can reach and operate the resources available in a SCADA system.
Summary: The use of the wireless application protocol architecture to provide a wireless channel to access the database operating under the commonly used distributed network protocol system running for SCADA in the power process plant is discussed. A distributed network protocol (DNP) is developed to be applied in the SCADA systems while the terminals and RTUs are presently connected through local area network. The conditions in a process plant are harsh and the site is remote. Resources for data communication are difficult to obtain under the environment and a wireless channel communication through a cellular phone is practical and efficient. The WAP API on power industry applications is one of the area for extensive attention. The WAP architecture provides an open application programming environment for defining the WAP server and WAP application interface modules. It is used to investigate the different WAP protocols and the wireless application environment on the Internet and mobile service for accessing a computing system. The Nokia WAP toolkit is used as the tool for investigation. Eventually, the mobile service can be incorporated into the DNP protocol such that a wireless WAP phone can reach and operate the resources available in a SCADA system.
Application of Fuzzy Logic in intelligent Traffic Control System
Describes the design and implementation of an intelligent traffic lights controller based on fuzzy logic technology. A
software has been developed to simulate the situation of an isolated traffic junction based on this technology. It is
highly graphical in nature, uses the Windows system and allows simulation of different traffic conditions at the
junction. A comparison can be made between the fuzzy logic controller and a conventional fixed-time controller.
Simulation results show that the fuzzy logic controller has better performance and is more cost effective
ROBUST FUZZY LOAD FREQUENCY CONTROLLER FOR A
TWO AREA INTERCONNECTED POWER SYSTEM
In this paper a new robust load frequency controller for two area interconnected power system is presented
to quench the deviations in frequency and tie line power due to different load disturbances. The dynamic
model of the interconnected power system is developed without the integral control. The area control error
is also not included. The frequency and derivatives are zero under normal operation and after the
disturbance effects are died. Then the problem is restructured as the problem of state transfer from the
initial steady state to final steady state without oscillations in less time. The fuzzy controller designed here
consists of two crisp inputs namely deviation of frequency and the other is derivative of frequency
deviation. The output of the fuzzy controller is the control input to each area.
The studies power system is subjected to a wide range of load disturbances to validate the
effective ness of the proposed fuzzy controller. The simulated results are obtained for different
configurations of the fuzzy controller like placing in area 1 only and placing area 1 and area 2 for different
options of load variations.
The digital results prove the present fuzzy controller over the other control studies presented in
earlier work in terms of fast response (dead beat response for certain configuration of fuzzy controller) with
very less undershoots and negligible overshoot with having small state transfer time to reach the final
steady state with zero frequency.
SHORT-TERM LOAD FORECASTINGUSING ADAPTIVE NEURO-FUZZY INFERENCE SYSTEM (ANFIS)APPLICATION TO ALEPPO LOAD DEMAND
Abstract: The huge consumption of electric energy in these days has given the load forecasting a big attention
from researchers and utility operators. Forecasting electric load will aid the electric company in optimal energy
generation, dispatching and unit commitment.
This paper introduces the preliminary results of applying Adaptive Neuro-Fuzzy inference System (ANFIS) to
short term load forecasting The theoretical foundations are introduced and details of the adaptive fuzzy system are
presented. The results of its application on Aleppo 24 hours load demand are included.
Fuzzy logic based Speed Control of AC Motor Using Microcontroller
Electricity Billing Automation
Prepaid Electricity Billing Automation
Electrical Station Variables Reader/Controller with True Graph and SCADA
Power Sharing of Transformers with WAP
Energy Saving In 1- Phase Induction Motor using A.C Chopper
Two / Four Quadrent chopper in Indian Military.
Fuzzy Logic Based Differential Relay For Power Transformer Protection.
Fuzzy logic-based relaying for large power transformer protection
Summary: Power transformer protective relay should block the tripping during magnetizing inrush and rapidly operate the tripping during internal faults. The frequency environment of power system has been made more complicated and the quantity of 2nd frequency component in inrush state has been decreased because of the improvement of core steel. Then, traditional approaches will likely be maloperated in the case of magnetizing inrush with low second harmonic component and internal faults with high second harmonic component. This paper proposes a new relaying algorithm to enhance the fault detection sensitivities of conventional techniques by using a fuzzy logic approach. The proposed fuzzy-based relaying algorithm consists of flux-differential current derivative curve, harmonic restraint, and percentage differential characteristic curve. The proposed relaying was tested with relaying signals obtained from Salford EMTP simulation package and showed a fast and accurate trip operation.
Summary: Power transformer protective relay should block the tripping during magnetizing inrush and rapidly operate the tripping during internal faults. The frequency environment of power system has been made more complicated and the quantity of 2nd frequency component in inrush state has been decreased because of the improvement of core steel. Then, traditional approaches will likely be maloperated in the case of magnetizing inrush with low second harmonic component and internal faults with high second harmonic component. This paper proposes a new relaying algorithm to enhance the fault detection sensitivities of conventional techniques by using a fuzzy logic approach. The proposed fuzzy-based relaying algorithm consists of flux-differential current derivative curve, harmonic restraint, and percentage differential characteristic curve. The proposed relaying was tested with relaying signals obtained from Salford EMTP simulation package and showed a fast and accurate trip operation.
