Hybrid Neuro Fuzzy approach for automatic generation control in restructured power system
Graphical abstract
Introduction
The electric power trade at present is largely in the hands of Vertically Integrated Utilities (VIU) which possess generation, transmission and distribution systems facilitates to supply power to the customer at regulated tariff. The major revolutionize that has arises be the emergence of Independent Power Producer (IPP) that can sell power to VIU. Given the present situation, it is generally agreed that the first step in deregulation will be to separate the generation of power from the transmission and distribution, thus putting all the generation on the same footing as the IPP. In an interconnected power system, a sudden load perturbation in any area causes the deviation of frequencies of all the areas and also in the tie-line powers.
This has to be corrected to ensure the generation and distribution of electric power with good quality. This is accomplished by Automatic Generation Control (AGC). The main objectives of AGC [10], [11] are to be maintained the desired MegaWatt output and the nominal frequency in an interconnected power system besides maintaining the net interchange of power between control areas at predetermined values. The AGC task is carried out through the error signal produced during generation and net interchange between the areas (i.e.,) Area Control Error (ACE) [27].where be the frequency bias coefficient of the ith area, be the frequency error of the ith area, be the tie line power flow error between ith area and jth area. With the restructuring of electric utilities, AGC requirements should be expanded to include the planning functions necessary to ensure the resources needed for AGC implementation are within the functional requirements. So most of the methods that may be proposed must have a good ability to track the contracted or uncontracted demands and can be used in a practical environment. A lot of studies have been made about AGC in a restructured power industry over last decades. These studies try to modify the conventional LFC system [30] to take into account the effect of bilateral contracts on the dynamics [12] and improve the dynamical transient response of the system under competitive conditions [9], [18], [19]. This paper proposes a control scheme that guarantees a minimum transient deviation and ensures zero steady state error. The stabilization of frequency oscillations in an interconnected power system [26] becomes challenging when implements in the future competitive environment. Consequently advanced economic, high efficiency and improved control schemes [21], [22] are required to ensure the power system reliability. The conventional load-frequency controller may no longer be able to attenuate the large frequency oscillation due to the slow response of the governor [24], [25]. A number of control strategies have been employed in the design of load frequency controllers in order to achieve better dynamic performance [31], [32]. Among the various types of load frequency controllers, the most widely employed is the conventional proportional integral (PI) controller [30], [31], [32]. Conventional controller is simple for implementation but takes more time and gives large frequency deviation. A number of state feedback controllers based on linear optimal control theory have been proposed to achieve enhanced performance [20], [8]. Fixed gain controllers are designed at nominal operating conditions and fail to provide best control performance over a wide range of operating conditions [17]. Subsequently, to keep system performance near its optimum, it is desirable to track the operating conditions and use updated parameters to compute the control. Adaptive controllers with self-adjusting gain settings have been proposed for LFC [4], [8], [13], [14], [15]. There has also been considerable research work attempting to propose better AGC systems based on modern control theory [20], neural network [2], [3], [5], [6], [29] fuzzy system theory [4] and reinforcement learning [7]. Recent study confirms that ANFIS approach has also been applied to hydrothermal system [16], [23], [28]. All research during the earlier period in the area of AGC narrates interconnected two equal area thermal system and petite attention has been paid to AGC of unequal multi area systems [1]. Most of ancient time works have been centered in the region of the design of governor secondary controllers, and design of governor primary control loop. Apparently no literature has discussed AGC performance subject to simultaneous small step load perturbations in all area or the application of ANFIS technique to a multi-area power system. The escalation in size and convolution of electric power systems along with increase in power demand has necessitated the use of intelligent systems that combine knowledge, techniques and methodologies from various sources for the real-time control of power systems.
In this paper, an effort has been made to apply Hybrid Neuro-Fuzzy (HNF) controller for the automatic load frequency control for the three area hydro-thermal restructured power system in consideration with GRC. The simulations are carried out in presence of the GRC’s because ignoring GRC show the way to non-realistic results.
Section snippets
System analyzed
In this multi source generating system, there are three control areas (Fig. 1) in which each areas has different combinations of GENCOs and DISCOs. Area 1 comprises of three GENCOs with thermal power system of reheat and non reheat turbine combinations and two DISCOs, Area 2 comprises of two GENCOs with hydro and thermal (non reheat turbine) combination and one DISCO, Area 3 consists of two GENCOs with hydro and thermal (reheat turbine) combination and two DISCOs as shown in Fig. 2. In this
HNF approach
The Hybrid combination of neural and fuzzy is considered to be an adaptive network, which has no synaptic weights, but has consequently called adaptive and non-adaptive nodes. It must be assumed that the adaptive network can be straightforwardly transformed to neural network architecture with classical feed forward topology. This proposed network works similar to adaptive network simulator of Takagi–Sugeno’s fuzzy controllers. This adaptive network is functionally comparable to a fuzzy
Simulation results and discussion
Hybrid combination of Neuro and Fuzzy be implemented for AGC in deregulated environment taking into account the GRC. The simulations have been carried out for the possible electricity contracts and also for large demand variations using HCPSO, RCGA, ANN controllers and the results were compared with proposed controller so as to prove the robustness. The plant parameters for three area deregulated power system is presented in Table 2. The results illustrate that HNF controller proves good
Conclusions
The hydro- thermal power generation is considered with GRC in deregulated power system. The three area control structure is tested using HNF controller. The simulated values show that the proposed controller provides zero steady state deviations with minimum overshoot, undershoot and also reduced settling time. The comparative results states that the ANFIS controller holds robust performance than HCPSO, RCGA and ANN controllers. Table 3, Table 4 show the percentage reduction of frequency and
References (32)
- et al.
Application of neural network to load frequency control in power system
IEEE Trans Neural Networks
(1994) - et al.
Load frequency control: a generalized neural network approach
Electr Power Energy Syst
(1999) - et al.
The application of ANN technique to automatic generation control for multi-area power system
Electr Power Energy Syst
(2002) - et al.
A reinforcement learning approach to automatic generation control
Electr Power Syst Res
(2002) - et al.
Application of GA based optimal integral gains in fuzzy based active power-frequency control of non-reheat and reheat thermal generating systems
Electr Power Syst Res
(2003) - et al.
Using a FACTS device controlled by a decentralized control law to damp the transient frequency deviation in a deregulated electric power system
Electric Power Syst Res
(2004) - et al.
Robust decentralized AGC in a restructured power system
Energy Convers Manage
(2004) - et al.
Bilateral based robust load frequency control
Energy Convers Manage
(2005) - et al.
Multi-stage fuzzy PID power system automatic generation controller in deregulated environments
Energy Convers Manage
(2006) - et al.
GA application to optimization of AGC in three area power system after deregulation
Int J Electr Power Energy Syst
(2007)
Adaptive Neuro–Fuzzy inference system based automatic generation control
Electr Power Syst Res
Tuning of PID load frequency controller for power systems
Energy Convers Manage
Robust analysis and design of load frequency controller for power systems
Electric Power Syst Res
Load frequency control strategies: a state of-the-art survey for the researcher
Energy Convers Manage
Optimized multi area AGC simulation in restructured power systems
Int J Electr Power Energy Syst
Practical viewpoints on load frequency control problem in a deregulated power system
Energy Convers Manage
Cited by (64)
CBO-based PID-F controller for Load frequency control of SPV integrated thermal power system
2022, Materials Today: ProceedingsCitation Excerpt :Under this scenario, the LFC plays a prominent role in efficiently keeping system frequency and TLP changes within acceptable limits [1]. Over the last few decades, researchers developed several novel control approaches for designing the LFC for various types of power systems, such as using variable structure control [2], linear quadratic control [3], robust control [4], fuzzy control [5], artificial neural network [6], internal model control [7,8,11,17] and so on. The above control techniques are rigid and proficient in managing the physical constraints of power systems.
Optimization of controllers using soft computing technique for load frequency control of multi-area deregulated power system
2024, International Journal of Applied Power Engineering