Search

In the data analysis of the existing short-term forecasting system, it lacks logic, and relies on artificial judgment, which leads to the large error of prediction results. Therefore, the short-term prediction system of power user interaction potential is designed based on artificial intelligence. In the hardware part, the high-precision processor d78f0537a-nec is used as the auxiliary processing system. Att7022bu is a special high-precision three-phase electric energy measuring chip. It is used in the three-phase three wire and three-phase four wire connection occasions when measuring the electrical energy information. In the software part, the response characteristics of user interaction potential are extracted, and the user interaction potential data management scheduling module is designed by artificial intelligence technology, and the data mining and logical analysis are carried out for data management scheduling. The prediction model is established to predict the potential of future user interaction by using the existing power data. The experimental results show that the overall prediction error of the system is 14.28% in the peak cutting scenario, 36.43% and 37.81% in the existing prediction system. In the case of reducing the wind abandonment, the overall prediction error of the system is 13.26%, and the overall prediction error of the existing forecasting system is 31.11% and 33.08%. The fitting effect of the predictive interactive capacity and the actual interactive capacity of the system is better than that of the existing prediction system, and has a good prospect in practical application.

Considering the advantages of mobile edge computing (MEC), such as low latency, high bandwidth, etc., more and more mobile services are cached to mobile edge servers. However, due to limited computing resources and storage capacity of mobile edge servers, it is hard to guarantee that all services are cached and all computation offloading requests are satisfied. In this paper, we jointly optimize service caching and computation offloading to maximize system profits in mobile edge-cloud computing (MECC). The problem is formalized as a nonconvex optimization problem with discrete variables. We propose a Dynamic Joint computation Offloading and Service Caching algorithm (DJOSC) to solve the problem. Specifically, a regularization technique and Lyapunov optimization theory are used to transform the problem into two subproblems, which are solved by convex optimization techniques. Numerical evaluations show that the maximum system profits can be achieved under different computing resources, storage capacities and bandwidth capacities.

The shortage of traditional fossil energy and intensified ecological deterioration have made the utilization of renewable energy become an irresistible development trend and a global consensus. High penetration rate of distributed generations (DG) and the significant uncertainty of their output power pose a certain risk to the safe and stable operation of distribution networks, and the optimal capacity configuration needs to be further studied. This paper aims to establish a model to maximize the capacity penetration of DG considering operational risks. Probabilistic load flow based on the cumulant method is applied to deal with the randomness of wind power and load demand. On this basis, indices of node overvoltage risk (ROV), node undervoltage risk (RUV), and line overload risk (RLO) are established to assess the risk level of the distribution network. Then an optimal planning model which intends to maximize the penetrated capacity of wind power is presented considering multi-risk factors. The case study is conducted on the modified IEEE 33-bus radial test system and the results reveal that the proposed strategy is effective and practical.

In order to optimize the adding scheme of metal passivator, this paper reported the effects of temperature, DBPC (2,6-di-tert- butyl-4-methyl phenol) concentration, DBDS (dibenzyl disulfide) concentration, copper surface area, paper surface area, oil state and copper corrosion degree on the consumption of metal passivator Irgamet 39 in transformer oil. Irgamet 39 concentration in transformer oil was determined by high performance liquid chromatography (HPLC). The results showed that the temperature is a key factor for Irgamet 39 consumption. Irgamet 39 concentration remains stable at low temperature (below 60 °C) and decreases rapidly at high temperature(above 90°C); paper, fresh copper, corroded copper, oil in service and DBDS increases the consumption rate of Irgamet 39; DBPC has little effect on the consumption of Irgamet 39. According to the protective mechanism of Irgamet 39, the transformer oil and insulation paper are important factors in the consumption of Irgamet 39.

Aiming at the problem of tracking bias and deteriorating robustness due to background interference and sudden change of object movement state in video tracking, this study proposed a new object tracking algorithm based on multichannel extraction of AHLBP texture features. This algorithm took into account the local visual information of the image, proposed an AHLBP texture extraction method with adaptive threshold. The method overcame the limitations caused by a single fixed threshold in texture extraction. In order to mine image texture information in depth, textures were extracted from the three color channels in the HSV color space. Then the paper fully used the texture to establish an accurate and complete object model as a description of the object, and achieved object tracking. Experimental results show that the algorithm can effectively improve the accuracy and stability of tracking and make the tracking algorithm has a better robustness.

The quality of image collected under severe weather such as fog and haze is badly damaged due to the atmospheric scattering. In order to solve the problem that image dehazing algorithms have poor adaptability, which will occur contrast distortion after restoration or cannot eliminating the influence of dense haze, a self-adaption single image dehaze method based on clarity evaluation is proposed to effectively recover the visual effects of the scene. The innovation points of this paper lied in that, first, the haze image is disposed separately according to average value, standard deviation, average gradient, information entropy and other clarity judgment features of the input image; then, the method of self-adaption image quality evaluation and coding decision is introduced to the dehaze results, to output the best effects obtained through comparison of many methods; finally, the clarity judgment is carried out again to output the final results. Experimental results demonstrate that the proposed method can achieve a better dehazing effect, and its chromaticity, luminance and contrast are improved to a certain extent. The universality of dehaze method is further improved.

Image defogging method based on non physical model (the image contrast enhancement method) and image dehazing method based on physical model (the atmospheric scattering model method), it is the two kinds of method that is focused on at present. The innovation of this article is: the estimation value of parameter achieved by atmospheric scattering model image dehazing method is not optimal; and the method of contrast enhancement makes the part of clear image and the depth of information distortion. On the basis of the theoretical analysis this paper gives an improved linear model which is proposed to describe the fog removal principle based on the atmospheric scattering model and the contrast enhancement method, and the fog removal problems of models were converted into the optimization searching in parameter space. Initial estimates parameters of atmospheric scattering model method based on linear model in the aspect of solving the problem, and the genetic algorithm and the clarity decision function are introduced to optimize the parameters. And then obtain defogging image. Experimental results demonstrate that the proposed method can achieve a better dehazing effect and applicability compared to some state-of-the-art methods.

The invention, gesture recognition technology uses cameras to collect images which contains the information of face posture, then identifying then track automatically the posture of face, and control correspondingly the car camera's rotation according to facial gestures, It is convenient and safe. In addition, the invention enhances the practicability of the system itself by adding the image processing technology such as antiglare, defog vision, night vision. Naked eye 3D will also be used in automobiles to observe the surrounding environment.

Natural ester as a substitute for mineral insulating oil has been used more and more widely in distribution transformers and large power transformers. The reliable operation of the natural ester transformer is essential to the safety and stability of the power grid. And the safe operation of the natural ester transformer relays the good dielectric properties of oil-pressboard insulation. In recent, the effect of moisture content on the dielectric properties of natural ester has been studied, while the research on the influence of moisture content on dielectric properties of pressboard impregnated is not detailed. In this paper, the temperature characteristics of permittivity, dissipation factor and resistivity at power frequency of pressboard impregnated respectively both in mineral insulating oil and natural ester with the moisture content about from 0.2% to 6% were studied. And the authors also studied the AC breakdown characteristic of oil-impregnated pressboard. The results were important for the safe and reliable operation of natural ester transformers.

It has been found that the presence of corrosive sulfur species in mineral insulation oil leads to a large number of failures in power transformers and shunt reactors. The method of adding metal deactivators particularly Irgamet 39TM into insulating oil is widely used to prevent the reaction of corrosive sulfur with copper by forming a passive film on the copper surface. Nevertheless, the influences of paper layers and atmospheric conditions on suppressive effect of metal deactivator are not clear. In this paper, the thermal aging tests in hermetic air and nitrogen conditions are separately designed to investigate the suppressive effect of Irgamet 39TM. Copper plates wrapped up in different number of paper layers are immersed in mineral oil samples with different Irgamet 39TM concentrations and aged at 150°C for 72 hours. the effectiveness of forming passivation layers is evaluated by analyzing the atomic concentration of nitrogen, oxygen and sulfur on copper surface using an X-ray photoelectron spectroscopy (XPS). It has been found that under nitrogen condition, the content of sulfur on copper surface increases with the number of paper layers, and the nitrogen content on the samples wrapped in paper is less than the ones unwrapped. While under air condition, compared to nitrogen condition, the content of sulfur on copper surface is greater. The results show that paper layers and atmosphere conditions have significant influence on the formation of passivation film.

As the growing emphasis on high voltage direct current (HVDC) transmission in power system, the reliability of converter transformer that is the vital equipment in DC transmission system becomes more important. The insulation system of converter transformer is mainly composed of insulating oil and pressboard, therefore the studies on DC voltage endurance (V-t) characteristics of the oil-impregnated pressboard are of great guiding significance for the insulation system design. In this paper, V-t characteristics of unused mineral insulation oil-impregnated pressboard have been studied in a completely seal V-t characteristics test system at 50°C. Firstly, the oil needs undergo a treating process to diminish the impurities, water and oxygen content in oil, and satisfy the requirements of water content