Advanced Materials Research Vols. 860-863

Abstract: This paper puts forward a residential electricity forecasting method based on FOAGMNN. Correlation analysis was adopted to select the key influencing factors of residential electricity forecasting. Finally, annual disposable income, population, households, per capita floor space, preceding electricity consumption are choosed as the key influencing factors. Through simulation example using the data of Hangzhou residential electricity consumption from 2000 to 2011, the results showed that the proposed model outperformed the other models and is suitable for residential electricity prediction.

Abstract: Power system data distributed in different locations of heterogeneous information systems on the multiple network . These systems are different in the architecture and also in different areas of expertise. In view of the above questions thispaper has proposed a power system integrated research plan baseed on ontology, mainly discussed on local ontology mapping between the data source. Focus on how to convert from the database relational model to OWL ontology and gives the ER model to OWL ontology from the conversion algorithm. Compared with the similar method, this method is automated build ontology, and overcomed the manually created ontology can bring a lot of tedious work.

Abstract: The classification and prediction of load is very important, in the power market .In order to improve the accuracy and speed of forecast, it is proposed that the mixed algorithm of particle swarm and back propagation network and model. And model is established on the basis of one city electric power bureaus electric power load data. Using the PSO - BP algorithm to the load for forecasting .According to the results of prediction, this method converges fast, prediction accuracy improved significantly. Application in the power market analysis and forecasting have very good effect and prospect.

Abstract: While having been successfully applied in forecasting with many researches, back Propagation (BP) neural network are with problems such as permutation and premature convergence due to dependence on initial connection weights or other parameters. This paper investigates Genetic Algorithms (GA) evolved BP network and its application to wind power forecasting. Sample analysis with daily wind output data demonstrates that GA-based neural network is with better performance.

Abstract: The modern shipboard power system integrates heavy loads and has less fault tolerance than the terrestrial power system. Therefore, a fast and high-performance reconfiguration is needed when a fault occurs. This paper proposes a method to achieve a rapid and optimal reconfiguration for shipboard power system. This method at first employs graph theory to generate the topology of particles, which can construct a non-Clique topology. Then, the particle swarm optimization algorithm with the non-Clique topology is used to improve the restoration scheme while considering constraints. The proposed Particle Swarm Optimization algorithm enables to find the optimal combination of loads that can be supplied after the occurrence of the fault.

Abstract: EHV substation service power is an important load in the power grid which is meaningful to be examined for the energy saving and emission reduction of the power grid. Based on the analysis of EHV substation service power and the improvement of the least square method, this paper get a new set of optimization which is is highly general and can reach high accuracy.

Abstract: In order to solve comprehensive decision problem which exist in power grid planning, Analytic hierarchy process (AHP) is applied to distribution network planning is put forward to the selection of alternatives. Based on the actual case, Established hierarchical structure model and the attributes decision table, Form a judgment matrix one by one, then Calculate the synthesis weights and achieve the decision results.The results show that analytic hierarchy process can better combining expert experience and quantitative calculation, It is very well Solution to the comprehensive evaluation of the distribution network planning decisions. It is a practical solution of distribution network planning.

Abstract: The power cable is one of the most important infrastructures, which safety and reliability is of an important significance to the stability and development of urban. To the safety risk features of urban power cable infrastructure, this paper proposed the safety risk evaluation index system and quantitative identification method based on analyzing the composition and construction features, and established the fuzzy comprehensive evaluation model of underground cable infrastructure safety risk. A case study shows that this method is feasible, and consistent with the practical construction, and proposed the measures to prevent the occurrence of major hazards.

Abstract: From the perspective of interruptible load participating in the standby system, this paper studies the interruptible load in capacity vacancy. Taking account of the constraints of generator, the capacity the users can provide and the IL compensation price, taking minimized the total cost of the purchasing of interruptible load and network loss as the objective function, the paper establishes a optimization model with interruptible load participating in spare capacity. Matlab program is used to calculate network loss. Through a two-node and five-bus system, interruptible Load optimization dispatch is solved, of course considering the network loss. Introduction

Abstract: The subject addressed is the rush-repair scheme for distribution network fault. Organization structure of rush-repair scheme is first built and rush-repair process is proposed. Confronted with the need of higher quality and higher efficiency of distribution network fault rush-repair, rush-repair command platform is developed for command center to enhance the rush-repair efficiency. The information exchanged between command platform and related various application systems is also described in detail. The proposed rush-repair scheme will provide practical techniques for efficiency improvement of fault rush-repair work of distribution network, and thus mostly abbreviate power recovery time.