Real-time Stochastic Optimization of Energy Storage Management using Rolling Horizon Forecasts for Residential PV Applications
- 1 September 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-9
Abstract
In this paper, an energy management method for a residential PV-storage hybrid system composed of a solar photovoltaic (PV) generation and a battery energy storage (BES) is formulated as an offline optimization model concurrent with a real-time rule-based controller. Existing offline energy management approaches for day ahead scheduling of BES generally suffers from energy loss in real-time due to the stochastic nature of load and solar generation. On the other hand, typical online algorithms do not offer optimal solutions for minimizing electricity purchase costs to the owners. To overcome such limitations, we propose an integrated framework where optimization is performed in receding horizon utilizing the forecasted load and solar generation profiles from long short term memory (LSTM) in rolling horizon to reduce daily electricity purchase costs. The optimization model is formulated as a multi-stage stochastic program where we use the stochastic dual dynamic programming (SDDP) algorithm in the receding horizon to update the optimal set-point for BES dispatch at a fixed interval. To prevent loss of energy during optimal solution update instants, we propose a rule-based controller beneath the optimization layer in finer time resolution at the power electronics converter control level. The proposed framework is evaluated using a realtime controller-hardware-in-the-Ioop (CHIL) test platform in an Opal-RT simulator. The proposed real-time method reduces the net electricity purchase cost relative to other existing energy management methods.Keywords
This publication has 30 references indexed in Scilit:
- Electric Load Forecasting Based on a Least Squares Support Vector Machine with Fuzzy Time Series and Global Harmony Search AlgorithmEnergies, 2016
- Real-Time Energy Storage Management With Renewable Integration: Finite-Time Horizon ApproachIEEE Journal on Selected Areas in Communications, 2015
- Real-Time Energy Management in MicrogridsIEEE Transactions on Smart Grid, 2015
- Market-Oriented Energy Management of a Hybrid Wind-Battery Energy Storage System Via Model Predictive Control With Constraint OptimizerIEEE Transactions on Industrial Electronics, 2015
- Short-Term Load Forecasting Using Random Forests2015
- Effects of wind penetration in the scheduling of a hydro-dominant power system2014
- A review on applications of ANN and SVM for building electrical energy consumption forecastingRenewable and Sustainable Energy Reviews, 2014
- Sharing cuts under aggregated forecasts when decomposing multi-stage stochastic programsOperations Research Letters, 2013
- Cyclic electric load forecasting by seasonal SVR with chaotic genetic algorithmInternational Journal of Electrical Power & Energy Systems, 2013
- Multi-stage stochastic optimization applied to energy planningMathematical Programming, 1991