No abstract

No abstract

Multi-service market optimization of battery energy storage system (BESS) requires assessing the forecasting uncertainty arising from coupled resources and processes. For the primary frequency control (PFC), which is one of the highest-value applications of BESS, this uncertainty is linked to the changes of BESS state-of-charge (SOC) under stochastic frequency variations. In order to quantify this uncertainty, this paper aims to exploit one of the recent achievements in the field of deep learning, i.e. multi-attention recurrent neural network (MARNN), for BESS SOC forecasting under PFC. Furthermore, we extend the MARNN model for probabilistic forecasting with a hybrid approach combining Mixture Density Networks and Monte Carlo dropout that incorporate the uncertainties of the data noise and the model parameters in the form of prediction interval (PI). The performance of the model is studied on BESS SOC datasets that are simulated based on real frequency measurements from three European synchronous areas in Great Britain, Continental Europe, and Northern Europe and validated by three PI evaluation indexes. Compared with the state-of-theart quantile regression algorithms, the proposed hybrid model performed well with respect to the coverage probability of PIs for the different regulatory environments of the PFC.

In the past years, a rapid deployment of battery energy storage systems for diverse smart grid services has been seen in electric power systems. However, a cost-effective and multi-objective application of these services necessitates a utilization of forecasting methods for a development of efficient capacity allocation and risk management strategies over the uncertainty of battery state-of-charge. The aim of this paper is to assess the tuning efficiency of multi-attention recurrent neural network for multi-step forecasting of battery state-of-charge under provision of primary frequency control. In particular, this paper describes hyperparameter optimization of the network with a tree-structured parzen estimator and compares such optimization performance with random and manual search on a simulated battery state-of-charge dataset. The experimental results demonstrate that the tree-structured parzen estimator enables 0.6% and 1.5% score improvement for the dataset compared with the random and manual search, respectively.

Forecasting the state-of-charge changes of battery energy storage, anticipated from a provision of different services, can facilitate planning of its market participation strategy and leverage the maximum potential of its energy capacity. This paper provides a performance comparison study of multiple decision-tree and data-driven machine learning methods for point forecasts of the state-of-charge of battery energy storage under frequency containment reserve for normal operation on day-, hour-, and 15-minute-ahead basis. The battery state-of-charge data for the performance evaluation were simulated with a droop curve battery model based on the historical frequency data in the northern Europe synchronous area. The results show that the data-driven methods outperform the decision-tree based methods on the 15-minute-and day-ahead time scales while demonstrating a comparable performance for the hour-ahead time scale.Index Terms-battery state-of-charge, point forecasting, decision trees, machine learning, frequency containment reserve