Active voltage control (AVC) is a widely-used technique to improve voltage quality essential in the emerging active distribution networks (ADNs). However, the voltage fluctuation caused by intermittent renewable energy makes it difficult for traditional voltage control methods to deal with. In this paper, the voltage control problem is formulated as a decentralized partial observable Markov decision process (Dec-POMDP), and a multi-agent reinforcement learning (MARL) algorithm is developed considering each controllable device as an agent. The new formulation aims to adjust the strategies of agents to stabilize the voltage within the specified range and reduce the network loss. To better represent the mutual interaction between the agents, a graph convolutional network (GCN) is introduced. By aggregating the information of adjacent agents, complex latent features are effectively extracted by the GCN, hence promotes the generation of voltage control strategy for the agents. Meanwhile, a barrier function is applied in MARL to ensure the system voltage within a safe operation range. Comparative studies are conducted with traditional voltage control and other MARL methods on IEEE 33-bus and 141-bus systems, which demonstrate the performance of the proposed approach.

In a conventional power grid, energy theft is difficult to detect due to limited communication and data transition. The smart meter along with big data mining technology leads to significant technological innovation in the field of energy theft detection (ETD). This article proposes a convolutional long short-term memory (ConvLSTM)-based ETD model to identify electricity theft users. In this work, electricity consumption data are reshaped quarterly into a 2-D matrix and used as the sequential input to the ConvLSTM. The convolutional neural network (CNN) embedded into the long short-term memory (LSTM) can better learn the features of the data on different quarters, months, weeks, and days. Besides, the proposed model incorporates batch normalization. This technique allows the proposed ETD model to support raw format electricity consumption data input, reducing training time and increasing the efficiency of model deployment. The result of the case study shows that the proposed ConvLSTM model exhibits good robustness. It outperforms the multilayer perceptron (MLP) and CNN-LSTM in terms of performance metrics and model generalization capability. Moreover, the result also demonstrates that $K$ -fold cross validation can improve the ETD prediction accuracy.

Accurate short-term load forecasting is essential to modern power systems and smart grids. The utility can better implement demand-side management and operate power system stably with a reliable load forecasting system. The load demand contains a variety of different load components, and different loads operate with different frequencies. The conventional load forecasting methods, e.g., linear regression (LR), auto-regressive integrated moving average (ARIMA), deep neural network, ignore the frequency domain and can only use time-domain load demand as inputs. To make full use of both time-domain and frequency-domain features of the load demand, a load forecasting method based on hybrid empirical wavelet transform (EWT) and deep neural network is proposed in this paper. The proposed method first filters noises via wavelet-based denoising technique, and then decomposes the original load demand into several sub-layers to show the frequency features while the time-domain information is preserved as well. Then, a bidirectional long short-term memory (LSTM) method is trained for each sub-layer independently. In order to better tune the hyper-parameters, a Bayesian hyperparameter optimization (BHO) algorithm is adopted in this paper. Three case studies are de-signed to evaluate the performance of the proposed method. From the results, it is found that the proposed method improves the prediction accuracy compared with other load forecasting method.

Advanced metering infrastructure (AMI) is the backbone of the next generation smart city and smart grid; it not only provides near real-time two-way communication between the consumers and the energy systems, but also enables the third parties (TPs) to provide relevant value-added services to the consumers to improve user satisfaction. However, the existing services are implemented in a centralized manner, which has potential and associated security and privacy risks also increased with Internet-of-Things (IoT) devices. To better balance the quality of the services and ensure users’ privacy, a TP AMI service model based on differentially private federated learning (FL) is proposed in this article. Instead of sending the private energy data to the cloud server, the proposed service model trains the neural network models locally, and only model parameters are shared with the central server. Moreover, the identity of individuals is eliminated by adding random Gaussian noise during the secure aggregation. Furthermore, an attention-based bidirectional long short-term memory (ATT-BLSTM) neural network model is adopted to solve the long-range dependency problem of conventional neural networks. In the case study, a residential short-term load forecasting (STLF) task is implemented to evaluate the performance of the proposed model. Compared with other state-of-the-art energy service models, the proposed one can achieve similar accuracy as the typical centralized model and balances the trade-off between privacy loss and prediction accuracy flexibly.

As an essential component in reducing anthropogenic CO₂ emissions to the atmosphere, tree planting is the key to keeping carbon dioxide emissions under control. In 1992, the United Nations agreed to take action at the Earth Summit to stabilize and reduce net zero global anthropogenic CO₂ emissions. Tree planting was identified as an effective method to offset CO₂ emissions. A high net photosynthetic rate (Pn) with fast-growing trees could efficiently fulfill the goal of CO₂ emission reduction. Net photosynthetic rate model can provide refernece for plant’s stability of photosynthesis productivity. Using leaf phenotype data to predict the Pn can help effectively guide tree planting policies to offset CO₂ release into the atmosphere. Tree planting has been proposed as one climate change solution. One of the most popular trees to plant are poplars. This study used a Populus simonii (P. simonii) dataset collected from 23 artificial forests in northern China. The samples represent almost the entire geographic distribution of P. simonii. The geographic locations of these P. simonii trees cover most of the major provinces of northern China. The northwestern point reaches (36°30’N, 98°09’E). The northeastern point reaches (40°91’N, 115°83’E). The southwestern point reaches (32°31’N, 108°90’E). The southeastern point reaches (34°39’N, 113°74’E). The collected data on leaf phenotypic traits are sparse, noisy, and highly correlated. The photosynthetic rate data are nonnormal and skewed. Many machine learning algorithms can produce reasonably accurate predictions despite these data issues. Influential outliers are removed to allow an accurate and precise prediction, and cluster analysis is implemented as part of a data exploratory analysis to investigate further details in the dataset. We select four regression methods, extreme gradient boosting (XGBoost), support vector machine (SVM), random forest (RF) and generalized additive model (GAM), which are suitable to use on the dataset given in this study. Cross-validation and regularization mechanisms are implemented in the XGBoost, SVM, RF, and GAM algorithms to ensure the validity of the outputs. The best-performing approach is XGBoost, which generates a net photosynthetic rate prediction that has a 0.77 correlation with the actual rates. Moreover, the root mean square error (RMSE) is 2.57, which is approximately 35 percent smaller than the standard deviation of 3.97. The other metrics, i.e., the MAE, R², and the min-max accuracy are 1.12, 0.60, and 0.93, respectively. This study demonstrates the ability of machine learning models to use noisy leaf phenotype data to predict the net photosynthetic rate with significant accuracy. Most net photosynthetic rate prediction studies are conducted on herbaceous plants. The net photosynthetic rate prediction of P. simonii, a kind of woody plant, illustrates significant guidance for plant science or environmental science regarding the predictive relationship between leaf phenotypic characteristics and the Pn for woody plants in northern China.