Wind energy is a renewable energy source with great development potential, and a reliable and accurate prediction of wind speed is the basis for the effective utilization of wind energy. Aiming at hyperparameter optimization in a combined forecasting method, a wind speed prediction model based on the long short‐term memory (LSTM) neural network optimized by the firework algorithm (FWA) is proposed. Focusing on the real‐time sudden change and dependence of wind speed data, a wind speed prediction model based on LSTM is established, and FWA is used to optimize the hyperparameters of the model so that the model can set parameters adaptively. Then, the optimized model is compared with the wind speed prediction based on other deep neural architectures and regression models in experiments, and the results show that the wind speed model based on FWA‐improved LSTM reduces the prediction error when compared with other wind speed prediction‐based regression methods and obtains higher prediction accuracy than other deep neural architectures.

Homomorphic signature is an extremely important public key authentication technique for network coding to defend against pollution attacks. As a public key cryptographic primitive, it also encounters the same problem of how to confirm the relationship between some public key pk and the identity ID of its owner. In the setting of distributed network coding, the intermediate and destination nodes need to use the public key of source node S to check the validity of vector-signature pairs. Therefore, the binding of S and its corresponding public key becomes crucial. The popular and traditional solution is based on certificates which are issued by a trusted certification authority (CA) center. However, the generation and management of certificates is extremely cumbersome. Hence, in recent work, Lin et al. proposed a new notion of identity-based homomorphic signature, which intends to avoid using certificates. But the key escrow problem is inevitable for identity-based primitives. In this article, we propose another new notion (for network coding): certificateless homomorphic signature (CLHS), which is a compromise for the above two techniques. In particular, we first describe the definition and security model of certificateless homomorphic signature. Then based on bilinear map and the computational Diffie-Hellman (CDH) assumption, give a concrete implementation and detailedly analyze its security. Finally, performance analysis illustrates that our construction is practical.

Cloud-fog computing is a novel computing model that expands the functionality of cloud computing, which provides various services through fog nodes. The issue of traditional data integrity auditing are low data security, slow data processing speed and low communication efficiency. To solve these problems, this paper proposes a data integrity audit scheme based on data blinding. This scheme uses the edge devices in the transmission node to establish a fog computing layer between the cloud service provider and the data owner to reduce transmission delay. The subordinate distribution relationship and weight between fog nodes dynamically allocate the optimal path and transmit the data to reduce transmission delay. At the same time, a blind factor is added to the integrity audit in the evidence generation process to avoid data leakage. This paper gives a security model and security proof based on computational Diffie-Hellman (CDH) assumptions. The experimental results show that the fog computing layer and blind factor are introduced into the data integrity audit process, which can reduce the data communication delay effectively and improve the security of data audit.

Natural gas load forecasting provides decision‐making support for natural gas dispatch and management, pipeline network construction, pricing, and sustainable energy development. To explain the uncertainty and volatility in natural gas load forecasting, this study predicts the natural gas load volatility. As the natural gas load volatility has the time‐series features, along with long‐term memory, volatility aggregation, asymmetry, and nonnormality, this study proposes a natural gas load volatility prediction model by combining generalized autoregressive conditional heteroscedasticity (GARCH) family models, XGBoost algorithm, and long short‐term memory (LSTM) network. The model first takes the GARCH family models parameters of sliding estimation and meteorological factors as the influencing factors of volatility, and then it screens these influencing factors through the extreme gradient boosting (XGBoost) algorithm. Finally, the selected important features are input into the LSTM network to predict the volatility, and the 90% confidence interval of the volatility is calculated. Compared with a variety of single and combined models, the model proposed in this study has an average reduction of 45.404% in the evaluation index of mean squared error. The experimental results show that the model proposed in this study has a good performance and accuracy in predicting the volatility of natural gas load.

The remote data possession checking mechanism can effectively verify the integrity of outsourced data, which can usually be divided into public verification and private verification. The verifier of public verification can be any cloud user, while private verification can only be the data owner. However, in most practical situations, the data owner expects that only a specific verifier can perform integrity checking tasks and that verifier cannot gain any knowledge about the data. Yan et al. proposed a remote data possession checking scheme with the designated verifier, which can guarantee that only the designated verifier can check data integrity, whereas others cannot do it. However, this scheme relies on public key infrastructure technology and does not consider data privacy protection issues. To overcome these shortcomings, we propose an identity-based remote data possession checking scheme that satisfies the data owner’s requirement to specify a unique verifier. Moreover, in this scheme, we use a random integer to blind data integrity proof to protect data privacy and use Merkle hash tree structure to achieve dynamic update of data. At the same time, our scheme can avoid the complex certificate management in public key infrastructure. We proved the safety of our scheme based on the discrete logarithm assumption and the computational Diffie-Hellman assumption. Theoretical analysis and experimental results show that our scheme is feasible and effective in practical applications.

With economic development and scientific and technological progress, people's requirements for the ecological environment are increasing day by day. As a clean energy, natural gas is favored by many countries all over the world. As an important part of natural gas industry planning, load forecasting plays a vital role in the optimal dispatching and operation of the natural gas network. From the perspective of prediction technology, this paper selects the literature related to natural gas load prediction from the Web of Science and CNKI database as the research object. Firstly, the literature chronology distribution and background, research institutions, and academic communities were analyzed by CiteSpace scientific knowledge mapping software. Secondly, the research hotspots and cutting-edge technologies were presented and analyzed visually, and the hot spot migration process in this field was summarized. In the end, the paper puts forward some problems that should be paid attention to in natural gas load prediction, including data processing in prediction, prediction of prediction model, adaptive prediction method and combination prediction method, which are also the direction of development in the future.