Design of a Fuzzy Logic Controller for Short-Term Load Forecasting With Randomly Varying Load

Design of a Fuzzy Logic Controller for Short-Term Load Forecasting With Randomly Varying Load

D. V. N. Ananth (Raghu Institute of Technology, Modavalasa, India), Lagudu Venkata Suresh Kumar (GMR Institute of Technology, India), Tulasichandra Sekhar Gorripotu (Sri Sivani College of Engineering, India) and Ahmad Taher Azar (College of Computer and Information Sciences, Prince Sultan University, Riyadh, Saudi Arabia & Faculty of Computers and Artificial Intelligence, Benha University, Benha, Egypt)
Copyright: © 2021 |Pages: 18
DOI: 10.4018/IJSKD.2021100103
OnDemand PDF Download:
Available
$37.50
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

Short-term load forecasting (STLF) is an integral component of energy management systems. In this paper, fuzzy logic-based algorithm is used for short-term load forecasting. The load changes over time and the goal is to satisfy the shift in demand and to maintain a fault as low as possible between the reference and real powers. The error in the load demand in mega-watt (MW) is compared with proposed technique as well as conventional methods. Three cases were investigated in which the load changes were 1) more random in nature, but the variance to the reference was more; 2) the random load changes were simpler, but a little different from the reference; and lastly, 3) the load changing was random, and the reference deviation was maximum. The results are analyzed for different load changes, and the corresponding results are verified using MATLAB. The deviation of the error value in load response is less experienced with a fuzzy logic controller than with a traditional system, and in fewer iterations, the objective function is also achieved.
Article Preview
Top

1. Introduction

The electrical power system is getting tremendous revolution in terms of automation, source and load management for effective utilization of resources (Gorripotu et al., 2019; Pilla et al., 2010, 2019; Fekik et al., 2018a,b,c; Bendakir et al., 2016). For modern grid settings, renewable energy sources including wind and solar are an inevitable aspect of power (Kamal et al., 2020; Abdelmalek et al., 2017, 2018; Ammar et al., 2019; Ben Smida et al., 2018; Meghni et al., 2018; 2017a,b; Ghoudelbourk et al., 2016). Smaller energy resources are managed by planning and optimization of demand for renewable energy sources and the so-called microgrid system. This microgrid is operating optimally based on demand side response (DSR), where generation is done based on exact requirement of load using optimal techniques like fuzzy logic control (FLC) (Babahajiani et al., 2016; Keshtkar et al., 2015), neural network (Dou et al. 2018; Habibi et al., 2019) and different methods (Babahajiani et al., 2016; Habibi et al., 2019). If the load demand decreases, the microgrid frequency response increases. This change in frequency is controlled and maintained to its normal value as early as possible (Gorripotu et al., 2020; Gorripotu et al., 2018; Sahoo et al., 2018). So, even for a smaller microgrid or for a larger grid these intelligent methods appear as successful. For the operating system to perform efficiently, demand side response is therefore required.

The demand side response has many applications in residential loads (Ponoćko & Milanović 2018), electrical vehicle parking (Yao et al., 2016), smart electric grid (Lu & Hong, 2019) and hybrid energy management (Yan et al., 2018). All these principles typically measure energy costs automatically based on the standard load profile and calibrate optimum saving using the integrated software. The programme's effectiveness depends on the method, the exact calculation and the load measurement parameters. For DSM to work effectively, an efficient closed loop with a fast control system is also required (McNamara & McLoone, 2015; Yan et al., 2018). The DSR is useful in industrial, commercial and residential applications with techno-economic potential (Anjo et al., 2018; Ikpe & Torriti, 2018), plug-in-electric vehicle (Gnann et al. 2018), residential load applications (Olkkonen et al., 2018) and commercial applications (Pechmann et al., 2017). From the literature survey, it is observed that the DSR is classified based on short term load reductions like load shifting or shedding. This is based on the concepts like technical, environmental, or economic feasibility. Different techniques for DSR management goals are conservation of strategy, peak clipping, valley shifting, strategic demand augmentation etc. (Dranka & Ferreira, 2019; Himang et al.; 2019; Zahra et al., 2020).

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 14: 4 Issues (2022): 2 Released, 2 Forthcoming
Volume 13: 4 Issues (2021)
Volume 12: 4 Issues (2020)
Volume 11: 4 Issues (2019)
Volume 10: 4 Issues (2018)
Volume 9: 4 Issues (2017)
Volume 8: 4 Issues (2016)
Volume 7: 4 Issues (2015)
Volume 6: 4 Issues (2014)
Volume 5: 4 Issues (2013)
Volume 4: 4 Issues (2012)
Volume 3: 4 Issues (2011)
Volume 2: 4 Issues (2010)
Volume 1: 4 Issues (2009)
View Complete Journal Contents Listing