Advanced Materials Research Vols. 986-987

Abstract: Elman Neural Network is a typical neural-network which shares the characteristics of multiple-layer and dynamic recurrent, and it’s more suitable than BP Neural Network when it’s applied to forecast the short-term load with periodicity and similarity. To solve the problem that Elman Neural Network lacks learning efficiency, GA-Elman model is established by optimizing the weights and thresholds using Genetic Algorithm. An example is then given to prove the effectiveness of GA-Elman model, using the load data of a certain region. Relative error and MSE have been considered as criterions to analyze the results of load forecasting. By comparing the results calculated by BP, Elman and GA-Elman model, the effectiveness of GA-Elman model is verified, which will improve the accuracy of short-term load forecasting.

Abstract: This paper proposes a short-term wind power dynamic prediction model based on GA-BP neural network. Different from conventional prediction models, the proposed approach incorporates a prediction error adjusting strategy into neural network based prediction model to realize the function of model parameters self-adjusting, thus increase the prediction accuracy. Genetic algorithm is used to optimize the parameters of BP neural network. The wind power prediction results from different models with and without error adjusting strategy are compared. The comparative results show that the proposed dynamic prediction approach can provide more accurate wind power forecasting.

Abstract: Aiming at problems which were brought by large-scale wind power integration, and the problem of multi-objective reactive power optimization considering the coexistence of discrete variables and continuous variables, a method of simulation based on genetic algorithm with adaptive weight is brought out. A solving thinking presents that capacitor switching and transformer tap adjusting and other discrete equipments are first, and the action sequence of generator and dynamic reactive power compensation (DRPC) devices and other continuous equipments setting follows, which is presented that optimization problem is decomposed into continuous variable optimization and discrete variable optimization, then they are solved respectively and cross iteration until convergence. In view of the optimization complexity and the coexistence of discrete variables and continuous variables, genetic algorithm with adaptive weight is presented for finding global optimal solution. Case studies show that the proposed thinking and algorithm for solving multi-objective reactive power optimization are reasonable.

Abstract: Smart grid could meet the electricity demand against the rapid development of economy and society. The idea to implement smart grid is fully in accordance with the energy developing strategy and it will exert far-reaching impact on the adjustment of energy structure, the sustainable development of society as well as low-carbon economy. Currently, smart grid has attracted wide attention around the world and major countries in the world have been carrying out related researches. This paper describes the background and basic concepts of the smart grid, and takes the United States, European Union and China for example to introduce the development characteristics and typical projects. Besides, this paper analyzes and compares the smart grid in U.S., E.U. and China and gives related suggestions on the key issues of the development of smart grid in China.

Abstract: The concept of Smart Grid is created this century, with the focus of whole world. With the social development, the requirement of power security is growing fast. China, as a great power towards to industrialized country, its requirement is more intense. This paper introduces the generation of the concept ‘smart grid’, as well as the inevitable trend of future development, plans of China for smart grid construction and some achievements, finally explains the advantages of China's smart grid development and prospects of the future.

Abstract: This paper proposes a new spatial load forecasting method for distribution network based on least squares support vector machine. The method adopt data, the characteristic of which is similar with forecast sample, to training in order to obtain the regression coefficients and bias, which we need to do the forecasting.Atthe same time,compare with artificial neural network model,The least squares support vector machine transforms quadratic programming problems into linear equations, thus avoiding the insensitive loss function, greatly reducing the computational complexity and further improving the accuracy of the prediction model. Finally, the effectiveness and practicality are verified by examples.

Abstract: The grid-connected wind farms bring power quality problems to power system due to the volatility and random of wind power generation. Analysis and calculation are carried out in this paper for the main influence factors of wind power harmonics, voltage fluctuations and flicker, and the assessment methods of the above power quality problems. For a certain wind farm, the corresponding power quality index limits can be calculated. Assessment conclusions can also be given by comparing the calculated power quality index values and the index limits.

Abstract: In view of the teaching requirements of the new curriculums about new energy power generation technology in electrical engineering field, this paper has proposed and designed a rated 3kW wind power system under the environment of PSIM9.0 software. Through systematically analyzing the mathematics and theory knowledge of the small and medium sized permanent-magnet direct-drive wind power system (PDWPS for short), the wind power system model has been built and the back-to-back double-PWM control circuit has been designed. Then the whole PDWPS has been established based on PSIM. The simulation results show that, when the wind speed changes, the output power of the generator is stable and the DC voltage of the inverter is constant. The results prove that the control strategy is correct and valid. As a powerful auxiliary teaching tool, PSIM can be used to strengthen student's understanding of theoretical knowledge and improve the students' learning interest and enthusiasm. The contents in this paper provide a new method to the teaching and practice in electrical engineering courses.

Abstract: This thesis applies the thought of cooperative game and studies on the best mode of cooperation and benefit distribution in the charging market in supply chain. Firstly by researching the relationship between the unit cost and the number of charging pile construction, the thesis concludes that grid, gas station and car park three party will participate at the same time. Then, with the data of Beijing charging market, it makes specific accounting of five unions of profit model, and finds out the best program in which the three-party union could be established. Finally, it uses classic Shapley method, getting the distribution models of enterprise union.

Abstract: The climate change and the shortage of energy have made the solar energy as the priority renewable energy in many countries, and solar energy is under the fast development. Since the solar energy has the intrinsic intermittence and fluctuation, its integration into the power grid will lead to the power fluctuations. The paper proposes a method of deploying the photovoltaic generation which is the main solar generation technology in China to meet the load demand in order to reduce the storage investment. The analysis shows that there is a strong correlation between daytime solar generation fluctuations and grid load fluctuations, and it is able to use solar plant instead of some peek-load regulating generator units. Therefore, solar generation technology also has great potential of integration ability even without the use of energy storage, and the purpose of solar generation is to increase the share of solar electriciy at the lowest unit cost rather than to guarantee 100% utilization factor.