Search

With the continuous economic growth, the number of power customers has increased significantly, and consumers in the field of power marketing will inevitably have a credit crisis. In order to reduce the business risk of relevant departments and improve the risk prediction ability of the system, this paper evaluates and reviews the user credit system. In this paper, the basic structure of BP neural network is described firstly, and then, the traditional BP neural network model is optimized after analyzing its algorithm flow. Based on this point, this paper analyzes the characteristics of customers in the energy and electricity market in the research area, and referring to local experts who have been engaged in power sales for many years, this paper puts forward a new set of directly scored power system load forecasting index system and algorithm improvement scheme and discusses the evaluation of power market credit rating based on the credit evaluation suggestions of power customers. After establishing the judgment criteria, in this paper, the power load data of the target area are studied by empirical analysis method and select three different customers from the production area, commercial and residential areas and residential areas as cases to analyze the determination of their credit rating and then, discuss the results of regional power load forecasting. Finally, this paper puts forward a kind of power management method based on the user's credit rating, and in order to complete the modernization transformation of power management system and promote the market development. In this paper, after improving and optimizing the traditional BP neural network, it is applied to the power market to predict the target user credit system, so as to achieve the improvement of forecasting ability. [ABSTRACT FROM AUTHOR]

Humans have the ability to quickly identify their own environment, understand, judge and analyze it, which is one of the important reasons why human beings can survive in nature for a long time and gradually develop it into a prosperous society today. The key to human's ability to perceive and understand the environment lies in the ability to accurately find and identify objects, understand and describe visual scenes, and even express emotions on this basis. And if computers can realize automatic and accurate image recognition, and even understand the semantics of images correctly, it will surely improve and facilitate human life. Based on this, the author integrated and optimized the computer image recognition system and applied it in this paper. The core technology of the system is to improve the image algorithm, which can complete the training, testing and classification of target images. The experimental data are available. Choosing this algorithm to improve the learning and training of the data generated by the original image processing is more effective than directly training the original image. [ABSTRACT FROM AUTHOR]

In recent years, global climate change caused by carbon dioxide emissions has attracted more and more attention. Adjusting the energy mix by predicting energy demands is currently a more effective way to address climate issues and energy supply issues. Based on the panel data from 1999 to 2018 in China, this paper designed a new hybrid prediction model to predict the future electricity consumption of Chinese residents by double improvement of particle swarm optimization. By comparing with the BP neural prediction model without mixing and several BP neural prediction models with other improved and mixed forms, the results show that the BP neural network hybrid prediction model with DPSO-BP is more suitable for forecasting the electricity consumption of Chinese residents. At the same time, the prediction results of the DPSO-BP prediction model show that the annual electricity consumption of Chinese residents will increase from 9685 (100 million kWh) in 2018 to 13,171 (100 million kWh) in 2025 in the next 7 years. The research results provide a reference for future scholars in the design of algorithms and provide suggestions for the government to adjust energy and avoid severe power shortages or surpluses. [ABSTRACT FROM AUTHOR]

When performing hydrological model parameter calibration, equifinality inevitably reduces the simulation and prediction ability of hydrological models. To lessen the impact of equifinality, a novel algorithmic improvement framework is proposed in this paper. This framework allows the parameters to be searched hierarchically in order of sensitivity size and shrinks the original ranges of the parameters before the final search. The shuffled complex evolution (SCE_UA) algorithm, which is the most popular method for addressing hydrological model calibration issues, is improved using this new framework yielding HSRS_SCE algorithm, which stands for the SCE_UA algorithm with hierarchical search (HS) and range shrinkage (RS). A 26-dimensional parametric calibration problem is constructed and solved in this study utilizing 12 schemes based on the HSRS_SCE algorithm with various parameters and a control scheme based on the SCE_UA algorithm. The results show that the HSRS_SCE algorithm can not only produce calibrated parameter results significantly superior to those of the traditional scheme (p < 0.05) but also produce objective function values 26.1% better than those of the traditional scheme and reduce the search time through parallel computing. [ABSTRACT FROM AUTHOR]

The classification of land cover is the first step in the analysis and application of remote sensing data in land resources. How to solve the multi-category image recognition and meet certain precision is a key issue in remote sensing image research, which has very important theoretical significance and practical application value. In this study, the algorithm is improved on the basis of convolutional neural network, and experiments are carried out on multi-source remote sensing images with different geomorphologies taken under three different weather conditions to verify the effectiveness and scalability of the improved convolutional neural network. The research results show that the improved algorithm proposed in this paper has certain results in remote sensing image classification and can provide theoretical reference for subsequent related research. [ABSTRACT FROM AUTHOR]

Vehicle positioning and vehicle identification of natural scene images are an important part of intelligent transportation systems and unmanned driving research. In current situation, there are still some problems in vehicle intelligent wireless positioning. In order to improve the intelligent wireless positioning efficiency of vehicles, based on the convolutional neural network, this research combines the concept of deep learning to carry out algorithm innovation in the research. Moreover, this paper combines the actual vehicle positioning problem points to collect data, simulates the vehicle positioning situation in a variety of complex situations, and designs a controlled test to verify. The results show that the algorithm of this study has certain effects, which can provide reference for subsequent related research and has certain practical significance. [ABSTRACT FROM AUTHOR]

We present a Graphic Processing Units (GPU) implementation of non-Newtonian Hele-Shaw flow that models the displacement of Herschel-Bulkley fluids along narrow eccentric annuli. This flow is characteristic of many long-thin flows that require extensive calculation due to an inherent nonlinearity in the constitutive law. A common method of dealing with such flows is via an augmented Lagrangian algorithm, which is often painfully slow. Here we show that such algorithms, although involving slow iterations, can often be accelerated via parallel implementation on GPUs. Indeed, such algorithms explicitly solve the nonlinear aspects only locally on each mesh cell (or node), which makes them ideal candidates for GPUs. Combined with other advances, the optimized GPU implementation takes ≈ 2.5 % of the time of the original algorithm. [ABSTRACT FROM AUTHOR]

Wireless sensor networks (WSNs) are being employed in a growing variety of fields for efficient monitoring and data collection about events that would be impossible with conventional computing platforms. WSNs are self-organizing networks that collects and processes important information via their resource-constrained sensor nodes and provide valuable information about happening events. The unattended nature of sensor nodes in these networks makes them vulnerable to a wide range of threats, and the resource limitations imposed on their nodes complicate things even more while monitoring the target regions. This study relies on an identity-based encryption (IBE) approach to protect these nodes' resources while ensuring that they collect valuable data from the target regions. IBE simplifies the key generation process in these networks and at the same time improves the network security up to a sufficient level. For this purpose, an identity-based encryption online/offline (IBOOE) algorithm is proposed as a more acceptable solution to the security concerns of these nodes. IBOOE improves on the previous algorithm, i.e., IBE, by splitting the encryption into two phases: offline and online. The offline phase is mainly responsible for complicated and resource-intensive operations, e.g. exponential operation and pairing operation. The online phase, on the other hand, is mainly responsible for relatively easy calculations such as integer multiplication or hash operation. The comparison of the proposed IBOOE against the state of the art work, i.e., IBE, clearly demonstrates the efficiency and effectiveness of the proposed work. [ABSTRACT FROM AUTHOR]