Search

With recent advancements in data technologies, particularly machine learning, research focusing on the enhancement of energy efficiency in residential, commercial, and industrial settings through the collection of load data, such as heat, electricity, and gas, has gained significant attention. Nevertheless, issues arising from hardware- or network-related problems can result in missing data, necessitating the development of management techniques to mitigate these challenges. Traditional methods for missing imputation face difficulties when operating in constrained environments characterized by short data collection periods and frequent consecutive missing. In this paper, we introduce the denoising masked autoencoder (DMAE) model as a solution to improve the handling of missing data, even in such restrictive settings. The proposed DMAE model capitalizes on the advantages of the denoising autoencoder (DAE), enabling effective learning of the missing imputation process, even with relatively small datasets, and the masked autoencoder (MAE), allowing for learning in environments with a high missing ratio. By integrating these strengths, the DMAE model achieves an enhanced performance in terms of missing imputation. The simulation results demonstrate that the proposed DMAE model outperforms the DAE or MAE significantly in a constrained environment where the duration of the training data is short, less than a year, and missing values occur frequently with durations ranging from 3 h to 12 h. [ABSTRACT FROM AUTHOR]

In an era of high penetration of renewable energy, accurate photovoltaic (PV) power forecasting is crucial for balancing and scheduling power systems. However, PV power output has uncertainty since it depends on stochastic weather conditions. In this paper, we propose a novel short-term PV forecasting technique using Delaunay triangulation, of which the vertices are three weather stations that enclose a target PV site. By leveraging a Transformer encoder and gated recurrent unit (GRU), the proposed TransGRU model is robust against weather forecast error as it learns feature representation from weather data. We construct a framework based on Delaunay triangulation and TransGRU and verify that the proposed framework shows a 7–15% improvement compared to other state-of-the-art methods in terms of the normalized mean absolute error. Moreover, we investigate the effect of PV aggregation for virtual power plants where errors can be compensated across PV sites. Our framework demonstrates 41–60% improvement when PV sites are aggregated and achieves as low as 3–4% of forecasting error on average. [ABSTRACT FROM AUTHOR]

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%. [ABSTRACT FROM AUTHOR]

Recently, renewable energy is rapidly integrated into the power grid to prevent climate change, and accurate forecasting of renewable generation becomes critical for reliable power system operation. However, existing forecasting algorithms only focused on reducing forecasting errors without considering error compensability by using a large-scale battery. In this paper, we propose a novel strategy called error compensable forecasting. We switch the objective of forecasting from reducing errors to making errors compensable by leveraging a battery, which in turn reduces the dispatched error , the difference between forecasted value and dispatched value. The challenging part of the proposed objective lies in that the stored energy at current time is affected by the previous forecasting result. In this regard, we propose a deep reinforcement learning based error compensable forecasting framework, called DeepComp, having forecasting in the loop of control. This makes an action as a continuous forecasted value, which requires a continuous action space. We leverage proximal policy optimization, which is simple to implement with outstanding performance for continuous control. Extensive experiments with solar and wind power generations show that DeepComp outperforms the conventional forecasting methods by up to 90% and achieves accurate forecasting, e.g., 0.58–1.22% of the mean absolute percentage error. • A novel forecasting strategy is proposed to make errors compensable using a battery. • A framework having forecasting in the loop of control is developed. • Deep reinforcement learning is applied for continuous control of forecasting. • Any forecasting algorithms can be combined with the proposed framework. • Accurate forecasting is achieved by outperforming the existing methods by up to 90%. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Recent proliferation of renewable energy has increased the installation of residential energy sources (e.g., roof-top photovoltaic (PV) panel and residential wind turbine) in households. To manage electricity usage incurred by renewable energy and residential load, home energy management systems (HEMSs) provide intelligence to home by real-time monitoring and controlling appliances. In this paper, we propose a novel HEMS framework considering multiple uncertainties from renewable generation and load profiles. First, we generate scenarios of each uncertainty through deep learning. Then, we propose an algorithm called clustered quantile scenario reduction (CQSR) to reduce computation time while preserving the stochastic properties of generated scenarios based on the Wasserstein-1 distance. We prove that solution of CQSR is determined by the number of clustered scenarios. Also, we show provable upper bound of performance degradation incurred by the scenario reduction. Simulation results show that the optimality gap and computation time of the proposed framework is substantially reduced compared to other HEMS algorithms, e.g., by up to 81.4% and 93.7%, respectively. Furthermore, although the original scenarios are generated through different scenario generation algorithms, HEMS using CQSR is less vulnerable to performance degradation incurred by scenario reduction. • Propose HEMS framework under multiple uncertainties. • Propose a scenario reduction algorithm that leverages the cardinality of the cluster. • Provide upper bound of performance degradation incurred by scenario reduction. • Achieve less optimality gap of cost and computation time compared to baselines. • Reduce vulnerability to performance degradation incurred by scenario reduction. [ABSTRACT FROM AUTHOR]