Matching Items (2)
Filtering by
- Creators: Lei, Qin
Description
Over the years, the growing penetration of renewable energy into the electricity market has resulted in a significant change in the electricity market price. This change makes the existing forecasting method prone to error, decreasing the economic benefits. Hence, more precise forecasting methods need to be developed. This paper starts with a survey and benchmark of existing machine learning approaches for forecasting the real-time market (RTM) price. While these methods provide sufficient modeling capability via supervised learning, their accuracy is still limited due to the single data source, e.g., historical price information only. In this paper, a novel two-stage supervised learning approach is proposed by diversifying the data sources such as highly correlated power data. This idea is inspired by the recent load forecasting methods that have shown extremely well performances. Specifically, the proposed two-stage method, namely the rerouted method, learns two types of mapping rules. The first one is the mapping between the historical wind power and the historical price. The second is the forecasting rule for wind generation. Based on the two rules, we forecast the price via the forecasted generation and the first learned mapping between power and price. Additionally, we observed that it is not the more training data the better, leading to our validation steps to quantify the best training intervals for different datasets. We conduct comparisons of numerical results between existing methods and the proposed methods based on datasets from the Electric Reliability Council of Texas (ERCOT). For each machine learning step, we examine different learning methods, such as polynomial regression, support vector regression, neural network, and deep neural network. The results show that the proposed method is significantly better than existing approaches when renewables are involved.
ContributorsLuo, Shuman (Author) / Weng, Yang (Thesis advisor) / Lei, Qin (Committee member) / Qin, Jiangchao (Committee member) / Arizona State University (Publisher)
Created2019
Description
This thesis investigates different unidirectional topologies for the on-board charger in an electric vehicle and proposes soft-switching solutions in both the AC/DC and DC/DC stage of the converter with a power rating of 3.3 kW. With an overview on different charger topologies and their applicability with respect to the target specification a soft-switching technique to reduce the switching losses of a single phase boost-type PFC is proposed. This work is followed by a modification to the popular soft-switching topology, the dual active bridge (DAB) converter for application requiring unidirectional power flow. The topology named as the semi-dual active bridge (S-DAB) is obtained by replacing the fully active (four switches) bridge on the load side of a DAB by a semi-active (two switches and two diodes) bridge. The operating principles, waveforms in different intervals and expression for power transfer, which differ significantly from the basic DAB topology, are presented in detail. The zero-voltage switching (ZVS) characteristics and requirements are analyzed in detail and compared to those of DAB. A small-signal model of the new configuration is also derived. The analysis and performance of S-DAB are validated through extensive simulation and experimental results from a hardware prototype.
Secondly, a low-loss auxiliary circuit for a power factor correction (PFC) circuit to achieve zero voltage transition is also proposed to improve the efficiency and operating frequency of the converter. The high dynamic energy generated in the switching node during turn-on is diverted by providing a parallel path through an auxiliary inductor and a transistor placed across the main inductor. The paper discusses the operating principles, design, and merits of the proposed scheme with hardware validation on a 3.3 kW/ 500 kHz PFC prototype. Modifications to the proposed zero voltage transition (ZVT) circuit is also investigated by implementing two topological variations. Firstly, an integrated magnetic structure is built combining the main inductor and auxiliary inductor in a single core reducing the total footprint of the circuit board. This improvement also reduces the size of the auxiliary capacitor required in the ZVT operation. The second modification redirects the ZVT energy from the input end to the DC link through additional half-bridge circuit and inductor. The half-bridge operating at constant 50% duty cycle simulates a switching leg of the following DC/DC stage of the converter. A hardware prototype of the above-mentioned PFC and DC/DC stage was developed and the operating principles were verified using the same.
Secondly, a low-loss auxiliary circuit for a power factor correction (PFC) circuit to achieve zero voltage transition is also proposed to improve the efficiency and operating frequency of the converter. The high dynamic energy generated in the switching node during turn-on is diverted by providing a parallel path through an auxiliary inductor and a transistor placed across the main inductor. The paper discusses the operating principles, design, and merits of the proposed scheme with hardware validation on a 3.3 kW/ 500 kHz PFC prototype. Modifications to the proposed zero voltage transition (ZVT) circuit is also investigated by implementing two topological variations. Firstly, an integrated magnetic structure is built combining the main inductor and auxiliary inductor in a single core reducing the total footprint of the circuit board. This improvement also reduces the size of the auxiliary capacitor required in the ZVT operation. The second modification redirects the ZVT energy from the input end to the DC link through additional half-bridge circuit and inductor. The half-bridge operating at constant 50% duty cycle simulates a switching leg of the following DC/DC stage of the converter. A hardware prototype of the above-mentioned PFC and DC/DC stage was developed and the operating principles were verified using the same.
ContributorsKulasekaran, Siddharth (Author) / Ayyanar, Raja (Thesis advisor) / Karady, George G. (Committee member) / Qin, Jiangchao (Committee member) / Lei, Qin (Committee member) / Arizona State University (Publisher)
Created2017