为准确预测直驱式波浪发电系统的输出功率,提出基于变分模式分解和向量自回归模型预测方案。通过分析原始时间序列的相关性选择预测特征时间,应用变分模式分解方法将所选特征时间序列分解为不同子序列,经过单位根检验及差分运算,建立每个子序列的向量自回归模型,求和重构子序列模型预测结果获得所选特征的预测初值。建立了直驱式波浪发电系统的波能转换模型,仿真结果表明：所提方案模型具备合理性与可行性,模型预测结果稳定,预测精度高,预测趋势准确。

Aiming to accurately predict the output power of direct-drive wave power generation systems, a prediction scheme based on variational pattern decomposition and vector autoregressive model is proposed. The predicted feature time is selected by analysing the correlation of the original time series, and the selected feature time series is decomposed into different sub-series by applying the variational mode decomposition method, which is subjected to unit root test and difference operation to establish a vector autoregressive model for each sub-series. A wave energy conversion model for direct-drive wave power generation system is established. The simulation results show that the proposed scheme model is reasonable and feasible, with stable model prediction results, high prediction accuracy and accurate prediction trends.

Meteorological changes urge engineering communities to look for sustainable and clean energy technologies to keep the environment safe by reducing CO2 emissions. The structure of these technologies relies on the deep integration of advanced data-driven techniques which can ensure efficient energy generation, transmission, and distribution. After conducting thorough research for more than a decade, the concept of the smart grid (SG) has emerged, and its practice around the world paves the ways for efficient use of reliable energy technology. However, many developing features evoke keen interest and their improvements can be regarded as the next-generation smart grid (NGSG). Also, to deal with the non-linearity and uncertainty, the emergence of data-driven NGSG technology can become a great initiative to reduce the diverse impact of non-linearity. This paper exhibits the conceptual framework of NGSG by enabling some intelligent technical features to ensure its reliable operation, including intelligent control, agent-based energy conversion, edge computing for energy management, internet of things (IoT) enabled inverter, agent-oriented demand side management, etc. Also, a study on the development of data-driven NGSG is discussed to facilitate the use of emerging data-driven techniques (DDTs) for the sustainable operation of the SG. The prospects of DDTs in the NGSG and their adaptation challenges in real-time are also explored in this paper from various points of view including engineering, technology, et al. Finally, the trends of DDTs towards securing sustainable and clean energy evolution from the NGSG technology in order to keep the environment safe is also studied, while some major future issues are highlighted. This paper can offer extended support for engineers and researchers in the context of data-driven technology and the SG.

In recent years, with the development of societies and economies, the demand for social electricity has further increased. The efficiency and accuracy of electric-load forecasting is an important guarantee for the safety and reliability of power system operation. With the sparrow search algorithm (SSA), long short-term memory (LSTM), and random forest (RF), this research proposes an SSA-LSTM-RF daily peak-valley forecasting model. First, this research uses the Pearson correlation coefficient and the random forest model to select features. Second, the forecasting model takes the target value, climate characteristics, time series characteristics, and historical trend characteristics as input to the LSTM network to obtain the daily-load peak and valley values. Third, the super parameters of the LSTM network are optimized by the SSA algorithm and the global optimal solution is obtained. Finally, the forecasted peak and valley values are input into the random forest as features to obtain the output of the peak-valley time. The forest value of the SSA-LSTM-RF model is good, and the fitting ability is also good. Through experimental comparison, it can be seen that the electric-load forecasting algorithm based on the SSA-LSTM-RF model has higher forecasting accuracy and provides ideal performance for electric-load forecasting with different time steps.

准确预测短期多种能源负荷，是确保综合能源系统可靠、高效运行的必要前提。为此，提出了一种基于遗传粒子群混合优化(genetic algorithm particle swarm optimization, GAPSO)算法的卷积长短期记忆神经网络(convolutional neural network-long short-term memory, CNN-LSTM)综合能源系统多元负荷预测模型。首先，利用皮尔逊系数来描述各影响因素与负荷之间的相关性强弱。其次，采用GAPSO算法对长短期记忆(long short-term memory, LSTM)网络模型进行改进，然后构建卷积神经网络(convolutional neural networks, CNN)以提取小时级高阶特征，并通过改进后的LSTM网络模型对提取的隐含高阶特征进行分位数回归建模，构建了基于GAPSO-CNN-LSTM综合能源系统多元负荷预测模型。最后，以美国亚利桑那州立大学坦佩校区综合能源系统负荷数据为算例进行验证，结果表明：改进后的算法具有更好的收敛能力，模型具有更高的预测精度。

Accurate prediction of short-term multiple energy loads is a prerequisite to ensure the reliable and efficient operation of integrated energy system. For this reason, a convolutional neural network-long short-term memory (CNN-LSTM) model for integrated energy system multivariate load prediction based on genetic algorithm particle swarm optimization (GAPSO) is proposed. Firstly, Pearson's coefficient is used to describe the correlation between the influencing factors and the load. Secondly, GAPSO algorithm is used to improve the LSTM model, and then a one-dimensional CNN is constructed to extract the hourly higher-order features, and the extracted implicit higher-order features are partitioned by the improved long short-term memory (LSTM) modeling. The multivariate load forecasting model based on GAPSO-CNN-LSTM for integrated energy system is constructed through quantile regression modeling. Finally, the load data of integrated energy system of Arizona State University Tempe Campus is used as an example, and the results show that the improved algorithm has a better convergence ability and the model has a higher prediction accuracy.

为应对可再生能源利用和用户负荷的不确定性，提出一种多时间尺度预测方法。预测过程分日前、日内滚动和实时3个阶段进行，时间尺度分别为1 h、15 min和5 min。首先，采用基于差值统计的预测方法完成气象参数的3个阶段预测；其次，在负荷预测的日前和日内阶段，建立了信号分解与机器学习相结合的回归预测模型，实时阶段建立了机器学习时间序列预测模型；接着，以测试集的预测精度指标为依据确定了日前和日内滚动阶段对典型日负荷的最佳预测方法；最后，将预测方法应用于典型日的能量预测，验证了方法的可行性。研究结果显示：3个阶段典型日气象参数预测结果的决定系数R²都在0.8以上；在日前和日内滚动阶段，多元负荷的预测任务应采用不同的信号分解方法，实时阶段负荷预测结果的R²值均超过0.9，平均绝对误差百分比(mean absolute percentage error, MAPE)接近0。

In order to cope with the uncertainty of renewable energy utilization and customer loads, a multi-timescale prediction method is proposed, where the prediction process is carried out in three phases: day-ahead, intra-day rolling and real-time, with timescales of 1 h, 15 min and 5 min, respectively. First, a prediction method based on difference statistics is used to accomplish the three stages of forecasting meteorological parameters. Second, a regression prediction model combining signal decomposition and machine learning is established for the day-ahead and intraday stages of load prediction, and a machine learning time series prediction model is established for the real-time stage. Next, the best prediction methods for typical daily loads in the day-ahead and intra-day rolling stages are determined based on the prediction accuracy metrics of the test set. Finally, the prediction method is applied to the energy forecast of typical days to verify the feasibility of the method. The results show that the determination coefficient R² of the prediction results of the meteorological parameters for a typical day in all three phases is above 0.8; in the day-ahead and intraday rolling phases, the prediction tasks of multivariate loads should be performed with different signal decomposition methods, and the R² of the load prediction results in the real-time phase is above 0.9, and the mean absolute percentage error (MAPE) is close to 0.