Contents lists available at ScienceDirect Journal of Energy Storage journal homepage: www.elsevier.com/locate/est An efective battery management scheme for wind energy systems using multi Kernel Ridge regression algorithm S.P. Mishra, Snehamoy Dhar, P.K. Dash ⁎ Siksha O Anusandhan (Deemed to be University), Bhubaneswar, India ARTICLEINFO Keywords: Doubly fed induction generator based wind energy system Wind power forecast error Battery management system Model reference binary tree switching scheme DSP validation ABSTRACT BatteryEnergyStorage(BES)systemsareadequatealternativeforanyWindPowerGenerationSystem(WPGS) forachievinggreateroperational fexibilitybycompensatingthegenerationvolatility.AnefcientLocalEnergy Management (LEM) for Wind/ Battery Energy Storage (BES) system is described in this chapter to reduce the prediction error and to improve associated battery life. Error in prediction impacts on DG control reference & system stability for local energy management. BES life degrades by prediction error in terms of battery power loss and temperature. A Doubly-Fed Induction Generator (DFIG) based WPGS is considered as primary DistributedGeneration(DG),whereDClinkvoltagestabilitychallengesduetowindspeedvolatility,aswellas prediction error is addressed with Lithium-ion (Li-ion) BES stacks. A new online Multi Kernel Ridge Pseudo InverseNeuralNetwork(MK-RPINN)algorithmisproposedtoobtainanimpactfuldecreaseinpredictionerror. A new secondary controller is proposed here for addressing temperature efect of battery. A Model Reference (MR) based battery temperature plan, linked to Rule based switching characteristics of battery stacks with temperature tolerance, is being incorporated in the proposed secondary controller. The efectiveness of this model is represented in various observations through TMS320 C6713 and MATLAB platform. 1. Introduction In last two decades wind systems have become very attractive preferenceofnonconventionalenergysourcesforanylocaldistribution network, due to their reliability and compatibility. The hybrid confg- urationsofrenewableenergybasedDistributedGenerations(DGs)have gainedimportanceinrecentliteratures[1]tocopewiththechallenges relatedtotheirintermittentnature.BatteryEnergyStorage(BES)with Wind Power Generation System (WPGS) has become an attractive choice [2] for isolated ofshore/ coastline grid networks. The integra- tion of BES to WPGS is mostly at its DC bus to compensate the wind speed intermittence as well as to provide voltage stability, for any Doubly-FedInductionGenerator(DFIG)application[33].Amultimode controlscheme[3]isproposedforDFIG-basedWPGS/storagesystem, with grid connected/ islanded to enable the switching operation. A seamless switching with efcient operation within stability limit is fo- cusedinthisliterature.Lowvoltageride-through(LVRT)abilitybased on crowbar and DC link BES is presented [4], towards a blended pro- tectionandcontrolsolution.RemoteAreaPowerSupply(RAPS)[5]for DFIG/ BES based application is discussed, where control is achieved between BES bufer and load to balance the instantaneous power. A distributed tuning of DFIG/ BES system by using bacterial foraging optimization [6]ispresentedtoprovideconstantpoweroutputtogrid against higher/lower wind speed. An efective Battery Management System(BMS)helpstoachievetheoptimalBESperformance[7,8].Any Energy Management System (EMS) is dependent on power prediction efcacyandthereisrarelyanyliteraturetoelaborateBESperformance under prediction mismanagement. Hence improved controller archi- tecture for DFIG/ BES based DG integration is proposed in this paper, where local EMS considerations are incorporated. Generally power prediction faces challenges due to its volatility behavior throughout the day/ month/ year. Prediction error (power mismatch between actual and predicted generation) is needed to be minimized for ensuring accurate management decision to the best possible extent. The EMS in WPGS application is dependent on two important parts: Centralized and Local EMS [9]. Where Centralized EMSismajorlyconcernedaboutenergymanagementinlongtermbasis andLocalEMSismorerelatedtooperationalaccuracy,dynamicload/ generation management. These management decisions have direct im- pactonpowerreferenceestimationinhierarchicalcontrolarchitecture (ISA-95 standards) for Local EMS [10]. The inaccurate reference to control level may lead to grid instability for WPGS based application. Variousefectivewindgenerations forecastingschemesareavailablein literature for improved accuracy. Fixed rate of change, seamless https://doi.org/10.1016/j.est.2018.12.013 Received 27 August 2018; Received in revised form 27 November 2018; Accepted 12 December 2018 ⁎ Corresponding author. E-mail address: pkdash.india@gmail.com (P.K. Dash). Journal of Energy Storage 21 (2019) 418–434 2352-152X/ © 2018 Elsevier Ltd. All rights reserved. T