Accurate short-term traffic state prediction is a crucial requisite for control and guidance of traffic flow in the intelligent traffic system, which has attracted increasing attention in the transportation field recently. This paper tests the optimization performances of two emerging bionic algorithms, known as Cuckoo Search Algorithm (CS) and Bat Algorithm (BA). Combined with the Support Vector Regression (SVR) principle, the two aforementioned algorithms are applied to optimize the kernel function parameters in SVR. At last, the speed data of a road network in Guangzhou are collected. The prediction performances of the CS-SVR and BA-SVR models are tested after preprocessing the data. From the overall prediction rates, the CS-SVR algorithm is slightly better than BA-SVR in terms of calculating speed. Furthermore, the two algorithms are significantly superior to the traditional SVR model and long short-term memory networks (LSTM), thereby verifying their effectiveness and practicability in short-term traffic state prediction.

To improve the accuracy of short-term traffic state prediction, this paper proposes a short-term traffic state prediction method based on the fusion of Gravitational search algorithm (GSA) and Support Vector Regression (SVR) to predict the average speed and traffic on urban roads. The average speed is predicted. This method combines the working mechanism of SVR in prediction and uses the GSA algorithm to optimize the relevant parameters in the SVR kernel function to improve the accuracy of the SVR kernel function, thereby obtaining more accurate prediction accuracy. Taking 4 road sections in a road network in Xuanwu District of Nanjing City as an example, using the measured traffic flow and speed data of urban roads to test the performance of the GSA-SVR model. Using 12 historical average data from 17:00-17:55 are recorded as training sample to predict road traffic flow and speed data from 18:00-18:25, the analysis results show that from the overall prediction rate, the GSA-SVR algorithm reduces the prediction error to less than 40% of the SVM algorithm, which verifies the GSA-SVR mentioned in this article. The effectiveness and practicality of the algorithm can provide a reliable basis for decision-making for the good management of urban roads.

The short-term power load forecasting is the understructure for energy optimization management of power system and coordinated scheduling of power resources. It is difficult to predict accurately due to the high randomness and periodicity of short-term load. To solve the shortcomings, the short-term forecasting method is proposed based on Ensemble Empirical Mode Decomposition-Adaptive Boosting Gated Recurrent Unit Neural Network (EEMD-ABGRU). First, the stable components are obtained by processing the nonstationary original series with EEMD, and then each component forecasting model is established by Gated Recurrent Unit neural network(GRU). Finally, Adaptive Boosting algorithm (Adaboost) is integrated with GRU neural network and the integrated model can extract the complex characteristics of load data more accurately, identify the law of load sequence variation and achieve high precision component forecasting. Taking actual load data of power grid as practical examples, the forecasting accuracy of proposed method reaches 97.18% which is higher than that of Long Short Term Memory Neural Network (LSTM) method. And the efficiency and adaptability of the algorithm is verified on different quarterly datasets.

With the continuous reform and innovation of science and technology, as well as the implementation of the comprehensive construction of smart grid strategic objectives, so that the development of the power industry has been a qualitative leap. Under the support of GPRS technology of mobile communication company in our country, the electricity meter reading system breaks the disadvantages of the traditional manual meter reading method, which saves a lot of labor cost and improves the quality and efficiency of the power meter reading, the centralized meter reading system has a series of advantages, such as high speed, high degree of automation and high accuracy, the electric power enterprise fully realized the importance of the centralized meter reading system under the GPRS technology. This paper will further analyze and discuss the centralized meter reading system based on GPRS technology.

Traveling wave fault location system is an important part in building strong smart grid. Global Positioning System( GPS)is now widely used as clock synchronization source. However, with the development of smart grid technology, GPS clock has exposed some limitations. A kind of traveling wave fault location network based on PTP(IEEE1588) is proposed in this paper. First, the synchronization principle of high-accuracy clock synchronization technology bades on IEEE1588 is analyzed. Then, structure of PTP(IEEE1588) based traveling wave fault location network is built. Last, redundancy scheme of PTP based time synchronization system for traveling wave fault location network is designed. Compared to GPS traveling wave fault location system, this one has such advantages as low cost, having nothing to do with climate, location and environment, and can meet the demand for clock synchronization among each traveling wave fault location system. Connected by Ethernet, GPS clock is not needed to be installed in each traveling wave fault location equipment. It is simple, reliable and of obvious superiority, playing great significance on maintaining safe operation of power and social stability.