Deep learning-based gas identification and quantification with auto-tuning of hyper-parameters

One-Day-Ahead Solar Irradiation and Windspeed Forecasting with Advanced Deep Learning Techniques

In recent years, demand for electric energy has steadily increased; therefore, the integration of renewable energy sources (RES) at a large scale into power systems is a major concern. Wind and solar energy are among the most widely used alternative sources of energy. However, there is intense variability both in solar irradiation and even more in windspeed, which causes solar and wind power generation to fluctuate highly. As a result, the penetration of RES technologies into electricity networks is a difficult task. Therefore, more accurate solar irradiation and windspeed one-day-ahead forecasting is crucial for safe and reliable operation of electrical systems, the management of RES power plants, and the supply of high-quality electric power at the lowest possible cost. Clouds’ influence on solar irradiation forecasting, data categorization per month for successive years due to the similarity of patterns of solar irradiation per month during the year, and relative seasonal similarity of windspeed patterns have not been taken into consideration in previous work. In this study, three deep learning techniques, i.e., multi-head CNN, multi-channel CNN, and encoder–decoder LSTM, were adopted for medium-term windspeed and solar irradiance forecasting based on a real-time measurement dataset and were compared with two well-known conventional methods, i.e., RegARMA and NARX. Utilization of a walk-forward validation forecast strategy was combined, firstly with a recursive multistep forecast strategy and secondly with a multiple-output forecast strategy, using a specific cloud index introduced for the first time. Moreover, the similarity of patterns of solar irradiation per month during the year and the relative seasonal similarity of windspeed patterns in a timeseries measurements dataset for several successive years demonstrates that they contribute to very high one-day-ahead windspeed and solar irradiation forecasting performance.

Design of Intelligent Solar PV Power Generation Forecasting Mechanism Combined with Weather Information under Lack of Real-Time Power Generation Data

In order to reduce the cost of data transmission, the meter data management system (MDMS) of the power operator usually delays time to obtain the power generation information of a solar photovoltaic (PV) power generation system. Although this approach solves the problem of data transmission cost, it brings more challenges to the solar PV power generation forecast. Because power operators usually need real-time solar PV power generation as a basis for the power dispatch, but considering the cost of communication, they cannot always provide corresponding historical power generation data in real time. In this study, an intelligent solar PV power generation forecasting mechanism combined with weather information is designed to cope with the issue of the absence of real-time power generation data. Firstly, the Pearson correlation coefficient analysis is used to find major factors with a high correlation in relation to solar PV power generation to reduce the computational burden of data fitting via a deep neural network (DNN). Then, the data preprocessing, including the standardization and the anti-standardization, is adopted for data-fitting or real-time solar PV power generation data to take as the input data of a long short-term memory neural network (LSTM). The salient features of the proposed DNN-LSTM model are: (1) only the information of present solar PV power generation is required to forecast the one at the next instant, and (2) an on-line learning mechanism is helpful to adjust the trained model to adapt different solar power plant or environmental conditions. In addition, the effectiveness of the trained model is verified by six actual solar power plants in Taiwan, and the superiority of the proposed DNN-LSTM model is compared with other forecasting models. Experimental verifications show that the proposed forecasting model can achieve a high accuracy of over 97%.

Electromagnetic Modulation Signal Classification Using Dual-Modal Feature Fusion CNN

AMC (automatic modulation classification) plays a vital role in spectrum monitoring and electromagnetic abnormal signal detection. Up to now, few studies have focused on the complementarity between features of different modalities and the importance of the feature fusion mechanism in the AMC method. This paper proposes a dual-modal feature fusion convolutional neural network (DMFF-CNN) for AMC to use the complementarity between different modal features fully. DMFF-CNN uses the gram angular field (GAF) image coding and intelligence quotient (IQ) data combined with CNN. Firstly, the original signal is converted into images by GAF, and the GAF images are used as the input of ResNet50. Secondly, it is converted into IQ data and as the complex value network (CV-CNN) input to extract features. Furthermore, a dual-modal feature fusion mechanism (DMFF) is proposed to fuse the dual-modal features extracted by GAF-ResNet50 and CV-CNN. The fusion feature is used as the input of DMFF-CNN for model training to achieve AMC of multi-type signals. In the evaluation stage, the advantages of the DMFF mechanism proposed in this paper and the accuracy improvement compared with other feature fusion algorithms are discussed. The experiment shows that our method performs better than others, including some state-of-the-art methods, and has superior robustness at a low signal-to-noise ratio (SNR), and the average classification accuracy of the dataset signals reaches 92.1%. The DMFF-CNN proposed in this paper provides a new path for the AMC field.

A Carbonate Reservoir Prediction Method Based on Deep Learning and Multiparameter Joint Inversion

Deep-water carbonate reservoirs are currently the focus of global oil and gas production activities. The characterization of strongly heterogeneous carbonate reservoirs, especially the prediction of fluids in deep-water presalt carbonate reservoirs, exposes difficulties in reservoir inversion due to their complex structures and weak seismic signals. Therefore, a multiparameter joint inversion method is proposed to comprehensively utilize the information of different seismic angle gathers and the simultaneous inversion of multiple seismic parameters. Compared with the commonly used simultaneous constrained sparse-pulse inversion method, the multiparameter joint inversion method can characterize thinner layers that are consistent with data and can obtain higher-resolution presalt reservoir results. Based on the results of multiparameter joint inversion, in this paper, we further integrate the long short-term memory network algorithm to predict the porosity of presalt reef reservoirs. Compared with a fully connected neural network based on the backpropagation algorithm, the porosity results are in better agreement with the new log porosity curves, with the average porosity of the four wells increasing from 89.48% to 97.76%. The results show that the method, which is based on deep learning and multiparameter joint inversion, can more accurately identify porosity and has good application prospects in the prediction of carbonate reservoirs with complex structures.

A New Hybrid Based on Long Short-Term Memory Network with Spotted Hyena Optimization Algorithm for Multi-Label Text Classification

An essential work in natural language processing is the Multi-Label Text Classification (MLTC). The purpose of the MLTC is to assign multiple labels to each document. Traditional text classification methods, such as machine learning usually involve data scattering and failure to discover relationships between data. With the development of deep learning algorithms, many authors have used deep learning in MLTC. In this paper, a novel model called Spotted Hyena Optimizer (SHO)-Long Short-Term Memory (SHO-LSTM) for MLTC based on LSTM network and SHO algorithm is proposed. In the LSTM network, the Skip-gram method is used to embed words into the vector space. The new model uses the SHO algorithm to optimize the initial weight of the LSTM network. Adjusting the weight matrix in LSTM is a major challenge. If the weight of the neurons to be accurate, then the accuracy of the output will be higher. The SHO algorithm is a population-based meta-heuristic algorithm that works based on the mass hunting behavior of spotted hyenas. In this algorithm, each solution of the problem is coded as a hyena. Then the hyenas are approached to the optimal answer by following the hyena of the leader. Four datasets are used (RCV1-v2, EUR-Lex, Reuters-21578, and Bookmarks) to evaluate the proposed model. The assessments demonstrate that the proposed model has a higher accuracy rate than LSTM, Genetic Algorithm-LSTM (GA-LSTM), Particle Swarm Optimization-LSTM (PSO-LSTM), Artificial Bee Colony-LSTM (ABC-LSTM), Harmony Algorithm Search-LSTM (HAS-LSTM), and Differential Evolution-LSTM (DE-LSTM). The improvement of SHO-LSTM model accuracy for four datasets compared to LSTM is 7.52%, 7.12%, 1.92%, and 4.90%, respectively.