Short-term load forecasting in a hybrid microgrid: a case study in Tanzania

摘要

Most emerging countries such as Tanzania are promoting rural electrification throughinstallation of microgrids. This paper proposes an approach for short-term day-ahead loadforecast in rural hybrid microgrids in emerging countries. Energy4Growing research project byPolitecnico di Milano department of energy in collaboration with EKOENERGY(www.ekoenergy.org) implemented in Ngarenanyuki Secondary School (Arusha, Tanzania)innovative control switchboards to form an energy smart-hub. The smart-hub was designed tomanage the school’s 10kW hybrid micro-grid comprising: PV-inverter, battery storage, microhydrosystem, and genset. Ngarenanyuki school microgrid’s data was used for the experimentalshort-term load forecast in this case study. A short-term load forecast model frameworkconsisting of hybrid feature selection and prediction model was developed using MATLAB?environment. Prediction error performance evaluation of the developed model was done byvarying input predictors and using the principal subset features to perform supervised trainingof 20 different conventional prediction models and their hybrid variants. The objective functionwas feature minimization and error performance optimization. The experimental andcomparative day-ahead load forecast analysis performed showed the importance of usingdifferent feature selection algorithms and formation of hybrid prediction models approach tooptimize overall prediction error performance. The proposed principal k-features subset unionapproach registered low error performance values than standard feature selection methods whenit was used with ‘linearSVM’ prediction model. Furthermore, a hybrid prediction model formedfrom the elementwise maximum forecast instances of two regression models (‘linearSVM’ and‘cubicSVM’) yielded better MAE prediction error than the individual regression models fused toform the hybrid.