The accurate forecasting of photovoltaic (PV) power generation is critical for smart grids and the renewable energy market. In this paper, we propose a novel short-term PV forecasting technique called the space-time convolutional neural network (STCNN) that exploits the location information of multiple PV sites and historical PV generation data. The proposed structure is simple but effective for multi-site PV forecasting. In doing this, we propose a greedy adjoining algorithm to preprocess PV data into a space-time matrix that captures spatio-temporal correlation, which is learned by a convolutional neural network. Extensive experiments with multi-site PV generation from three typical states in the US (California, New York, and Alabama) show that the proposed STCNN outperforms the conventional methods by up to 33% and achieves fairly accurate PV forecasting, e.g., 4.6–5.3% of the mean absolute percentage error for a 6 h forecasting horizon. We also investigate the effect of PV sites aggregation for virtual power plants where errors from some sites can be compensated by other sites. The proposed STCNN shows substantial error reduction by up to 40% when multiple PV sites are aggregated.

Recently, various renewable energy sources and large-scale batteries have been integrated into power grids, and renewable energy bidding and battery control become critical problems in the real-time energy market. However, bidding and control problems have been studied separately while these two problems simultaneously influence the total profit of renewable producers. In this paper, we propose a novel strategy where renewable energy bidding and battery control are collectively investigated. First, unlike the previous studies where bidding is simply the forecasted value, the proposed methods determine the bidding values considering the error compensability of the battery by switching the objective of forecasting from reducing errors to making errors compensable. After the error compensation, additional battery control is applied to utilize the energy arbitrage process considering the energy price. As there are energy price and renewable generation uncertainties, we propose a deep reinforcement learning based bidding combined with control, called DeepBid, for sequential decision making under uncertainty. Our extensive simulations with real solar and wind generation data show that the proposed DeepBid strategy substantially increases the total profit compared to existing bidding strategies by achieving as high revenues as the arbitrage strategy and as low deviation penalties as the error compensation strategy.

In most deep learning-based load forecasting, an intact dataset is required. Since many real-world datasets contain missing values for various reasons, missing imputation using deep learning is actively studied. However, missing imputation and load forecasting have been considered independently so far. In this article, we provide a deep learning framework that jointly considers missing imputation and load forecasting. We consider a family of autoencoder/long short-term memory (LSTM) combined models for missing-insensitive load forecasting. Specifically, autoencoder (AE), denoising autoencoder (DAE), convolutional autoencoder (CAE), and denoising convolutional autoencoder (DCAE) are considered for extracting features, of which the encoded outputs are fed into the input of LSTM. Our experiments show that the proposed DCAE/LSTM combined model significantly improves forecasting accuracy no matter what missing rate or type (random missing, consecutive block missing) occurs compared to the baseline LSTM.

Machine learning-based time-series forecasting has recently been intensively studied. Deep learning (DL), specifically deep neural networks (DNN) and long short-term memory (LSTM), are the popular approaches for this purpose. However, these methods have several problems. First, DNN needs a lot of data to avoid over-fitting. Without sufficient data, the model cannot be generalized so it may not be good for unseen data. Second, impaired data affect forecasting accuracy. In general, one trains a model assuming that normal data enters the input. However, when anomalous data enters the input, the forecasting accuracy of the model may decrease substantially, which emphasizes the importance of data integrity. This paper focuses on these two problems. In time-series forecasting, especially for photovoltaic (PV) forecasting, data from solar power plants are not sufficient. As solar panels are newly installed, a sufficiently long period of data cannot be obtained. We also find that many solar power plants may contain a substantial amount of anomalous data, e.g., 30%. In this regard, we propose a data preprocessing technique leveraging convolutional autoencoder and principal component analysis (PCA) to use insufficient data with a high rate of anomaly. We compare the performance of the PV forecasting model after applying the proposed anomaly detection in constructing a virtual power plant (VPP). Extensive experiments with 2517 PV sites in the Republic of Korea, which are used for VPP construction, confirm that the proposed technique can filter out anomaly PV sites with very high accuracy, e.g., 99%, which in turn contributes to reducing the forecasting error by 23%.