No abstract

This paper presents a day-ahead optimal energy management strategy for economic operation of industrial microgrids with high-penetration renewables under both isolated and grid-connected operation modes. The approach is based on a regrouping particle swarm optimization (RegPSO) formulated over a day-ahead scheduling horizon with one hour time step, taking into account forecasted renewable energy generations and electrical load demands. Besides satisfying its local energy demands, the microgrid considered in this paper (a real industrial microgrid, "Goldwind Smart Microgrid System" in Beijing, China), participates in energy trading with the main grid; it can either sell power to the main grid or buy from the main grid. Performance objectives include minimization of fuel cost, operation and maintenance costs and energy purchasing expenses from the main grid, and maximization of financial profit from energy selling revenues to the main grid. Simulation results demonstrate the effectiveness of various aspects of the proposed strategy in different scenarios. To validate the performance of the proposed strategy, obtained results are compared to a genetic algorithm (GA) based reference energy management approach and confirmed that the RegPSO based strategy was able to find a global optimal solution in considerably less computation time than the GA based reference approach.

Improved performance electricity demand forecast can provide decentralized energy system operators, aggregators, managers, and other stakeholders with essential information for energy resource scheduling, demand response management, and energy market participation. Most previous methodologies have focused on predicting the aggregate amount of electricity demand at national or regional scale and disregarded the electricity demand for small-scale decentralized energy systems (buildings, energy communities, microgrids, local energy internets, etc.), which are emerging in the smart grid context. Furthermore, few research groups have performed attribute selection before training predictive models. This paper proposes a machine learning (ML)-based integrated feature selection approach to obtain the most relevant and nonredundant predictors for accurate short-term electricity demand forecasting in distributed energy systems. In the proposed approach, one of the ML tools -binary genetic algorithm (BGA) is applied for the feature selection process and Gaussian process regression (GPR) is used for measuring the fitness score of the features. In order to validate the effectiveness of the proposed approach, it is applied to various building energy systems located in the Otaniemi area of Espoo, Finland. The findings are compared with those achieved by other feature selection techniques. The proposed approach enhances the quality and efficiency of the predictor selection, with minimal chosen predictors to achieve improved prediction accuracy. It outperforms the other evaluated feature selection methods. Besides, a feedforward artificial neural network (FFANN) model is implemented to evaluate the forecast performance of the selected predictor subset. The model is trained using two-year hourly dataset and tested with another one-year hourly dataset. The obtained results verify that the FFANN forecast model based on the BGA-GPR FS selected training feature subset has achieved an annual MAPE of 1.96%, which is a very acceptable and promising value for electricity demand forecasting in small-scale decentralized energy systems.INDEX TERMS Binary genetic algorithm, decentralized energy system, electricity demand forecasting, feature selection, feedforward artificial neural network, fitness evaluation measure, Gaussian process regression, machine learning, smart grid.