Search

The increase in the penetration rate of distributed renewable energy sources has brought unprecedented challenges to the economic and stable operation of the active distribution network (ADN). To improve the operating efficiency and total benefits of the ADN, it is necessary to establish an optimization model considering the stakeholders’ market behavior and the game relationship among them under the market environment. In this paper, a multi-stakeholder potential game model in the ADN considering the bounded rationality of small users is proposed. The game relationships among five stakeholders, including the distributed photovoltaic generation aggregators, the distributed wind power aggregators, the energy storage operators, the large users and the load aggregators, are modeled on an hourly time scale. Existing research has proved that the game equilibrium of the potential game model must exist. Based on the information transfer and the strategy update mode on the social network, a demand response evolutionary game model for small users is established. Moreover, a distributed algorithm is designed to obtain the pure strategy equilibrium. Finally, a case with five stakeholders and 160 small users is used to verify the rationality and feasibility of the proposed model.

To realize the rational planning of integrated energy stations, this paper introduce a planning method for integrated energy station which based on multiple energy system's basic planning. This planning method contains the approach which based on C-means algorithm for forecasting users' daily energy load, the approach which based on Voronoi diagram for locating new multiple power stations and the planning model which aims to reduce the annual cost (includs the costs of equipments, operation, maintenance and fuels) of the power stations for power stations' planning. The steps of locating and station planning are all included in this method. This paper solves the model with actual data. By comparing the planning results, the feasibility of the method and the economy of the integrated energy system are verified.

This paper presents a new system for singing melody transcription from polyphonic songs. Instead of operating solely on polyphonic audio of each song to be processed (as most existing systems do), our system takes as inputs additionally multiple monophonic recordings of people singing the song. To transcribe the singing melody in a song, our system first tracks the singing pitch from polyphonic audio of the song by using a deep neural network (DNN)-based method, and then uses the estimated pitch series as reference to select the pitch sequences extracted from the multiple monophonic singing recordings. The selected monophonic pitch sequences, as well as the DNN pitch series from the polyphonic audio, are then transcribed separately, and their transcriptions results are fused to form the final note sequence. Experimental results show that, by introducing monophonic singings into transcription, the performance of singing melody transcription from polyphonic songs can be significantly improved.