Search

In order to realize the large-scale and normal implementation of power-to-gas technology, as well as the large-capacity storage and long-distance transportation of gas in the later stage of electric hydrogen production, a power-to-gas technology with real-time energy conversion characteristics and large-scale energy storage characteristics is studied in this paper. Firstly, the water-electricity-gas coupling process between the electrolytic cell and the methanation reactor in the power-to-gas system is discussed in detail, and the model of the power-to-gas system based on the coordination of real-time energy conversion and large-scale energy storage is proposed. Then, based on a multi-energy coupling regional integrated energy system, a highly decoupled multi-step modelling method is adopted to construct its optimal operation model, and the equivalent variable substitution method is used to transform it into a linear programming problem. Finally, the calculation results show that the proposed power-to-gas technology can further improve the energy utilization efficiency due to the complementary characteristics of the two functions, so as to effectively promote the implementation of large-scale power-to-gas projects in the future. • Propose a power-to-gas technology with different functional characteristics. • The proposed method realizes the large-capacity storage and long-distance transmission of energy. • Establish a highly decoupled multi-step optimization model of residential integrated energy system. • Use variable substitution method to linearize the model. • The proposed model reduces system operating costs with efficient energy utilization efficiency. [ABSTRACT FROM AUTHOR]

Accurate photovoltaic power prediction is important to ensure stable and safe operation of microgrids. However, due to the high volatility of photovoltaic power data, the prediction accuracy of traditional prediction models is often unsatisfactory. To ensure stable operation of microgrids, this study proposes a combined improved extreme gradient boosting-kernel extreme learning machine short-term photovoltaic power prediction model consisting of multidimensional similar day clustering and dual decomposition. Initially, gray relation analysis, Pearson correlation coefficient, and Kmeans++ are used for clustering to obtain high-precision similar days. Subsequently, a dual signal decomposition model based on variational modal decomposition and complete ensemble empirical mode decomposition with adaptive noise is proposed. Finally, predictions are made using a combination of predictive models with complementary strengths and weaknesses, and the prediction results of each component are fitted with under three weather conditions, the average root mean square error is reduced by 78.02%,62.99%, and 62.48%, and the average mean absolute error is reduced by 82.55%, 71.13%, and 67.07% in comparison with the baseline model. The results show that the model is effective in improving the prediction accuracy in a variety of different environments. • A new short-term photovoltaic power generation prediction model was developed. • Using GRA, PCC, Kmeans++ for multidimensional similar day clustering. • Innovatively introduced PE into the VMD-PE-CEEMDAN dual decomposition method. • Comparative analysis in different environments emphasizes the reliability of the combined models. [ABSTRACT FROM AUTHOR]

In order to solve the security threat brought by the volatility and randomness of large-scale distributed wind power, this paper proposed a wind power prediction model which integrates two-layer decomposition and deep learning, effectively realizing the accurate prediction of wind power series with non-stationary characteristics. Initially, pearson correlation coefficient (PCC) is employed to identify primary meteorological variables as input series. Second, the wind power series are smoothed by implementing complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), and then all subseries are decomposed and obtained by utilizing empirical wavelet transform (EWT) for the components with the highest complexity. Subsequently, hidden information related to wind speed, wind direction, and wind power series are extracted through the bidirectional temporal convolutional network (BiTCN), and the obtained information is fed into a bidirectional long short-term memory network (BiLSTM) optimized by attention mechanism for prediction. Finally, the predicted values of all components are summed to derive the final prediction results. In addition, the significant advantages of the prediction model in this paper are verified by five comparison experiments. The mean absolute error (MAE) and root mean square error (RMSE) of the model's one-step prediction in the January dataset are 2.1647 and 2.8456, respectively. • A new wind power prediction method based on signal decomposition and deep learning is proposed • CEEMDAN, EWT is used to decompose the original wind power signal • BiTCN, BiLSTM, Attention are used to predict the decomposed subseries [ABSTRACT FROM AUTHOR]

The energy crisis and environmental pollution are the most serious threats to human survival. Currently, many countries and regions have set the goal of carbon neutrality by 2030–2060. Multi-energy systems (MESs), which integrate different energy systems such as electricity, natural gas and district heating networks, have received significant support and development to expedite this process. However, due to the complexity of its structure, the consideration of such a concept necessitates an appropriate model to describe the planning and optimal energy flow throughout the system. Another critical direction for future MES development is the rapid and accurate calculation of MES models. Numerous research institutions and large corporations have concentrated their efforts in this area, which has resulted in the publication of thousands of papers. This article aims to provide readers with a comprehensive and critical overview of the typical MES model and its associated optimisation algorithms to assist them in identifying appropriate models and associated solution methods for their research or engineering problems. We summarise the concept and potential three-layer structure of MESs and introduce their fundamental components in depth. Subsequently, according to different research or application objectives, we divide MES models into three categories and discuss their application scenarios, modelling methods and solution techniques. Additionally, we report six significant obstacles encountered in current real-world MES projects based on our practical engineering experience and propose seven potential development directions for future optimisation of the operating technology. • Providing readers with an overview of the MES model and related algorithms. • Summarizing the concept and potential three-layer structure of MESs. • Dividing MES models into three categories, discussing their modelling and solving. • Reporting six significant obstacles encountered in current MES projects. • Proposing seven potential development directions for future technology. [ABSTRACT FROM AUTHOR]

The state of health (SOH) is a key parameter for fault diagnoses and safety early warnings in the life cycle of lithium batteries in electric vehicles. The SOH prediction model generally uses the experimental data from the same batch of batteries in the same environment. These data may cause "overfitting" to the model as the attenuation of lithium batteries varies depending on the batch and working condition, especially in actual use. And there is a risk of serious deviation in the prediction result if there is no true value of the model. This paper proposes a SOH prediction model that evaluates the prediction uncertainty using data from different batches of batteries under actual working conditions. It not only quantitatively evaluates the credibility of the prediction model in absence of true values, but also filtering training data to improve the model accuracy and avoid overfitting. The model produces evaluation uncertainty for the prediction result based on the Gaussian process regression (GPR) method. Experiments' results show that the evaluation uncertainty is better than the prediction variance of GPR. The accuracy of the prediction model using the minimum evaluation uncertainty as the training data screening is an order of magnitude higher than that using all data for training. • A SOH prediction model is proposed by using the actual diverse data which come from different batches batteries. • Model only built by using the battery daily charging voltage, current and time. • An evaluation uncertainty method is proposed to evaluate the creadibility of the lithium battery SOH prediction. [ABSTRACT FROM AUTHOR]