Solar energy is the key to clean energy, which can generate large amounts of electricity for the future smart grid. Unfortunately, the randomness and intermittency of solar energy resources bring difficulties to the stable operation and management of the power systems. To reduce the negative impact of photovoltaic (PV) plants accessing on the power systems, it is great significant to predict PV power accurately. In light of this, we propose a hybrid deep learning approach based on convolutional neural network (CNN) and long-short term memory recurrent neural network (LSTM) for the PV output power forecasting. The CNN model is leveraged to discover the nonlinear features and invariant structures exhibited in the previous output power data, thereby facilitating the prediction of PV power. The LSTM is used to model the temporal changes in the latest PV data, and predict the PV power of next time step. Then, the prediction results in the two models are comprehensively considered to obtain the expected output power. The proposed approach is extensively evaluated on real PV data in Limberg, Belgium, and numerical results demonstrate that the proposed approach can provide good prediction performance in PV systems.

The intermittency of solar energy resources has brought a big challenge for the optimization and planning of a future smart grid. To reduce the intermittency, an accurate prediction of photovoltaic (PV) power generation is very important. Therefore, this paper proposes a new forecasting method based on the recurrent neural network (RNN). At first, the entire solar power time series data is divided into inter-day data and intra-day data. Then, we apply RNN to discover the nonlinear features and invariant structures exhibited in the adjacent days and intra-day data. After that, a new point prediction model is proposed, only by taking the previous PV power data as input without weather information. The forecasting horizons are set from 15 to 90 min. The proposed forecasting method is tested by using real solar power in Flanders, Belgium. The classical persistence method (Persistence), back propagation neural network (BPNN), radial basis function (RBF) neural network and support vector machine (SVM), and long short-term memory (LSTM) networks are adopted as benchmarks. Extensive results show that the proposed forecasting method exhibits a good forecasting quality on very short-term forecasting, which demonstrates the feasibility and effectiveness of the proposed forecasting model.

With the deregulation of the electric energy industry, accurate electricity price forecasting (EPF) is increasingly significant to market participants’ bidding strategies and uncertainty risk control. However, it remains a challenging task owing to the high volatility and complicated nonlinearity of electricity prices. Aimed at this, a novel hybrid deep-learning framework is proposed for day-ahead EPF, which includes four modules: the feature preprocessing module, the deep learning-based point prediction module, the error compensation module, and the probabilistic prediction module. The feature preprocessing module is based on isolation forest (IF), and least absolute shrinkage and selection operator (Lasso), which is used to detect outliers and select the correlated features of electricity price series. The point prediction module combines the deep belief network (DBN), long-short-term memory (LSTM) neural network (RNN), and convolutional neural network (CNN), and is employed to extract complicated nonlinear features. The residual error between forecasting price and actual price can be reduced based on the error compensation module. The probabilistic prediction module based on quantile regression (QR) is used to estimate the uncertainty under various confidence levels. The PJM market data is employed in case studies to evaluate the proposed framework, and the results revealed that it has a competitive advantage compared with all of the considered comparison methods.

With the booming development of prosumers, there is an urgent need for a prosumer energy management system to take full advantage of the flexibility of prosumers and take into account the interests of other parties. However, building such a system will undoubtedly reveal users' privacy. In this paper, by solving the non-independent and identical distribution of data (Non-IID) problem in federated learning with federated cluster average (FedClusAvg) algorithm, prosumers' information can efficiently participate in the intelligent decision making of the system without revealing privacy. In the proposed FedClusAvg algorithm, each client performs cluster stratified sampling and multiple iterations. Then, the average weight of the parameters of the sub-server is determined according to the degree of deviation of the parameter from the average parameter. Finally, the sub-server multiple local iterations and updates, and then upload to the main server. The advantages of FedClusAvg algorithm are the following two parts. First, the accuracy of the model in the case of Non-IID is improved through the method of clustering and parameter weighted average. Second, local multiple iterations and three-tier framework can effectively reduce communication rounds.

To support the big-data processing needs of large-scale deployments of smart devices, there is significant interest in moving from cloud-computing to multi-agent (fog-computing) models, given these algorithms scalability and self-healing properties with respect to nodes and link failures. However, these algorithms are often based on the average consensus primitive, which is, unfortunately, vulnerable to data injection attacks. Recognizing this challenge, this work proposes three novel methods for detecting and localizing adversarial nodes using neural network (NN) models. The methods proposed are based on fully distributed algorithms, wherein each node locally updates its local states by exchanging information with its neighbors without supervision. Compared to the state-of-the-art, the proposed approach leverages the automatic learning characteristics of NN to reduce the dependence on pre-designed models and human expertise in complex internal attack scenarios. Simulation results show that the NN-based methods can significantly improve the attacker detection and localization performance.

Atrial fibrillation is a common cardiac arrhythmia, and its incidence increases with age. Currently, numerous deep learning methods have been proposed for AF detection. However, these methods either have complex structures or poor robustness. Given the evidence from recent studies, it is not surprising to observe the limitations in the learning performance of these approaches. This can be attributed to their strictly homogenous conguration, which solely relies on the linear neuron model. The limitations mentioned above have been addressed by operational neural networks (ONNs). These networks employ a heterogeneous network configuration, incorporating neurons equipped with diverse nonlinear operators. Therefore, in this study, to enhance the detection performance while maintaining computational efficiency, a novel model named multi-scale Self-ONNs (MSSelf-ONNs) was proposed to identify AF. The proposed model possesses a significant advantage and superiority over conventional ONNs due to their self-organization capability. Unlike conventional ONNs, MSSelf -ONNs eliminate the need for prior operator search within the operator set library to find the optimal set of operators. This unique characteristic sets MSSelf -ONNs apart and enhances their overall performance. To validate and evaluate the system, we have implemented the experiments on the well-known MIT-BIH atrial fibrillation database. The proposed model yields total accuracies and kappa coefficients of 98% and 0.95, respectively. The experiment results demonstrate that the proposed model outperform the state-of-the-art deep CNN in terms of both performance and computational complexity.