The Department of Electrical and Electronics Engineering is proud to announce that the estimable book of Springer Nature, ‘Soft Computing: Theories and Applications’ has featured three publications by Dr Tousif Khan, Assistant Professor. His publications are part of the book series, Lecture Notes in Networks and Systems (LNNS), Volume 425. The book stimulates discussions on various emerging trends, innovations, practices, and applications in the field of soft computing, ranging from data mining, prediction analysis, control systems, image processing, health care, medicine, agriculture analysis, supply chain management and cryptanalysis etc.
The first chapter titled “Design of Fast Battery Charging Circuit for Li-Ion Batteries” was co-authored by Dr Khan along with the final year EEE students; P Manoj Sai, G Nithin Sai, Puja Manohari, and P Gopi Krishna. In this chapter, a battery charging topology has been designed and developed for the fast charging of Li-ion batteries. The charging circuitry comprises a Proportional-Integral-Derivative (PID) controlled DC-DC buck converter system for reducing the charging time in Li-ion batteries. Battery charging time depends on several factors and the charging current is one of the major criteria. In this work, the buck converter is used to attain a high charging current, besides providing the regulated voltage to the battery. Initially, the AC supply obtained from the mains is converted to DC using an AC-DC rectifier. The rectifier output is further fed to the buck converter to increase the output current of the circuit. The buck converter reduces the output voltage and increases through it.
The circuit parameters are designed by considering the commercially available Lithium-ion battery LIR18650 as the load with a capacity of 2600 mAh and a nominal voltage of 3.7 V. The considered battery requires a standard charging current of 0.5 A, however, the circuit is designed to provide the rapid charge current of 1.3 A as the output by using the buck converter. The converter is operated in continuous conduction mode and helps in charging the battery under constant current mode. To avoid interruption to the charging current when there is a simultaneous discharge of the battery, further improvement in the closed-loop control action is made by employing a PID controller. Extensive simulation work has been conducted using the MATLAB/Simulink tool. The results obtained suggest there is a significant reduction in charging time under different conditions compared to the conventional method of battery charging.
In the chapter, “Global Horizontal Solar Irradiance Forecasting Based on Data-Driven and Feature Selection Techniques”, Dr Khan discusses the need for an accurate solar prediction. It has become an essential part of the renewable energy sector with the rapidly expanding infrastructure of the solar energy system. Over the past decade, various machine learning (ML) algorithms have been used for this purpose. Although the prediction of solar irradiance forecasting has been discussed in many studies, the use of meta-heuristic optimization techniques has not been explored to select features for the forecasting model. This study comprises two meta-heuristic optimization techniques such as simulated annealing (SA) and ant colony optimization (ACO) for feature selection. The results show that feature selection based on meta-heuristics gave better results than models without feature selection.
Amongst the two optimization methods, ACO outperformed SA with some exceptions. For SA, the declining order of performance observed is extreme gradient boosting (XGBoost), random forest (RF), multilayer perceptron (MLP), decision tree (DT) and support vector regression (SVR), while for ACO the declining order observed is XGBoost followed by MLP, RF, DT and SVR. This manuscript indicates the potential capability of meta-heuristic techniques for accurate prediction of global horizontal irradiance (GHI) given a wide array of feature variables.
In yet another chapter, “Exhaustive Search Approach to Place PV in Radial Distribution Network for Power Loss Minimization”, co-authored with Dr Shubh Lakshmi, Assistant Professor, and the final year students; P Manoj Sai and M Dhana Sai Baji from the Department of Electrical and Electronics Engineering, an exhaustive search approach to determine the best location and size of PV placement for power loss minimization of radial distribution networks is discussed. In this approach, the network power loss is determined by placing PV in each location, one at a time, and the size of PV in the same location is varied between 10 and 300 kW with an increment of 10 kW.
The combination of location and size of PV which provides the minimum network power loss can be the best location and size of PV for power loss minimization of radial distribution networks. The forward–backward sweep load flow algorithm is used to incorporate the PV model. The 33-bus radial distribution network is used to demonstrate the approach. The simulation results show that the placement of a suitable size of PV in some specific locations significantly reduces the network power loss.
Publishing the latest advancements in Networks and Systems, The LNNS series will serve as an edifying read for all the researchers and scientists across the globe. Volumes published in LNNS give a deep insight into all aspects and subfields of, as well as new challenges in, Networks and Systems. The series encompasses the theory, applications, and perspectives on the state of the art and future developments relevant to systems and networks, decision making, control, complex processes and related areas, as embedded in the fields of interdisciplinary and applied sciences, engineering, computer science, physics, economics, social, and life sciences, as well as the paradigms and methodologies behind them.