by O'Yang Wiley. / Thesis (M.B.A.)--Chinese University of Hong Kong, 1990. / Bibliography: leaves 44-45. / ABSTRACT --- p.ii / TABLE OF CONTENTS --- p.iv / ACKNOWLEDGEMENTS --- p.v / Chapter / Chapter I. --- INTRODUCTION --- p.1 / Chapter II. --- TIME SERIES AND UNIT ROOT --- p.5 / Definitions --- p.5 / Difference Between 1(0) and 1(1) Processes --- p.8 / Chapter III. --- FORMULATION OF LONG RUN FISHER OPEN HYPOTHESIS … --- p.10 / Chapter IV. --- UNIT ROOT TESTS --- p.14 / Dickey and Fuller Test --- p.14 / Augmented Dickey and Fuller Test --- p.16 / Phillips and Perron Test --- p.16 / Finite Sample Properties of Regression / Unit Root Tests --- p.18 / Chapter V. --- UNIT ROOT TEST RESULTS --- p.20 / Tentative ARIMA Model for the Interest Rate Series --- p.21 / Hong Kong --- p.21 / Singapore --- p.22 / Malaysia --- p.22 / Philippines and Japan --- p.23 / Tentative ARIMA Model for the Interest Rate Differentials --- p.23 / Hong Kong-Malaysia --- p.23 / Hong Kong-Singapore --- p.24 / Singapore-Malaysia --- p.24 / Others --- p.24 / Unit Root Test Results --- p.24 / Discussions and Findings --- p.36 / Chapter VI. --- CONCLUSIONS AND AREAS OF FURTHER RESEARCH --- p.40 / APPENDIX --- p.43 / BIBLIOGRAPHY --- p.44

Sun Yuekang. / Thesis submitted in: October 1999. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2000. / Includes bibliographical references (leaves 40-44). / Abstracts in English and Chinese.

Previsões probabilísticas de precipitação foram obtidas a partir de um conjunto de simulações pelo modelo WRF e utilizadas como condição de contorno no modelo hidrológico TopModel para previsão hidrometeorológica na bacia do Rio Iguaçu, no estado do Paraná. Nas simulações de cheias, durante o período de elevação do volume de precipitação, o erro médio aritmético do conjunto de previsões foi menor que cada um dos membros utilizados nesse conjunto, indicando melhor destreza do conjunto médio em relação a qualquer previsão determinística. Na dissipação dos sistemas precipitantes, alguns membros obtiveram resultados melhores que o conjunto médio e, em geral, as previsões são confluentes. As melhores previsões de precipitação com o WRF foram obtidas com as combinações de microfísica Lin e convecção de Kain Fritsch, microfísica WSM 5 e convecção de Kain Fritsch e simulações defasadas em 6 horas. As simulações inicializadas em horários mais próximos da ocorrência do fenômeno não garantiram uma melhoria na distribuição de precipitação na bacia. A avaliação do sistema de previsão por conjuntos pelo índice de Brier (IB) e seus termos demonstrou níveis suficientes de confiabilidade e destreza para ser utilizada na maioria dos eventos de precipitação sobre a bacia do rio Iguaçu. Os valores do IB estiveram entre 0,15 e 0,3 com picos isolados. Os valores obtidos para o termo de incerteza estiveram entre 0,1 e 0,25 indicando bons resultados visto que o desejável é o mais próximo de zero. Nos eventos de chuva, o termo de confiabilidade apresentou valores próximos a 0,2 no período da manhã e valores entre 0,3 e 0,4 no período da tarde, com um acréscimo no final da integração. O índice de acerto foi de 60 % a 90 % durante o período de integração (48 horas) para o conjunto médio de previsões e entre 50 a 80% para a previsão determinística. Em todos os horários de simulação o erro de fase foi maior que o erro de amplitude, possivelmente devido aos atrasos da propagação dos sistemas precipitantes e aos efeitos de ajuste das condições físicas iniciais da atmosfera. Os erros de fase e amplitude foram menores na previsão probabilística em todo o período de integração. Assim como na previsão de precipitação, nas simulações de vazão o erro de fase foi maior que o erro de amplitude, indicando que o atraso nas previsões de variação da vazão ainda é o um desafio na previsão hidrometeorológica. Observou-se que o modelo hidrológico é bastante sensível a previsão de precipitação e, portanto, a melhoria das previsões de vazão é diretamente proporcional a diminuição dos erros nas previsões de precipitação. / Probabilistic forecast of precipitation from WRF model simulations was used as input in hydrological TopModel for streamlines forecast in Iguaçu Basin, Parana, southern Brazil. The arithmetic error of precipitation ensemble forecast was smaller than each individual member forecast error in the streamflow increase stage. It means the use of ensemble forecast was better than any deterministic forecast. But when the streamflow decreases, the results are confluent and some individual member forecast was better than ensemble. Simulations using Lin microphysical parameterization and Kain Fritsch, WSM 5 and Kain Fritsch and 6h lagged obtained the better results of precipitation over the basin. The use of runs with initial conditions near the precipitation time did not guarantee better results in the distribution of precipitation on the basin. The Brier Score (BS) of the ensemble system demonstrated that the system is very skillful with values between 0.15 and 0.3. Both uncertainty and reliability terms of BS, 0.1 0.25 and 0.2- 0.4, respectively, were encouraging for use hourly ensemble forecast of precipitation on the watershed. Ensemble forecast provide high values of hit scores (0.6 to 0.9) than deterministic forecast (0.5 to 0.8) at all period of integration. Due the delay in the forecasts of the precipitation systems, the phase error is predominant over amplitude during all time. Both errors were reduced using the ensemble forecasts. The phase errors in hydrological were greater than amplitude such as precipitation forecasts. Thus, for increase streamflow forecast it should reduced the errors in QPF forecasts.

by Leung Kwok Chu, Wong Cheuk Fung. / Thesis (M.B.A.)--Chinese University of Hong Kong, 2002. / Includes bibliographical references (leaves 54-55). / ABSTRACT --- p.ii / TABLE OF CONTENTS --- p.iv / ACKNOWLEDGMENTS --- p.vi / Chapter / Chapter I. --- INTRODUCTION --- p.1 / Technical Analysis --- p.2 / The Characteristics and Efficiency of China's Equity Markets --- p.3 / Market Participants --- p.4 / Transaction Costs and Tradability of Shares --- p.5 / Availability of Information --- p.7 / Implication on Weak Form Market Efficiency --- p.8 / Relative Strength Index --- p.10 / Chapter II. --- LITERATURE REVIEW --- p.12 / Chapter III. --- METHODOLOGY --- p.15 / Primary Research --- p.15 / Source of Data --- p.15 / Spreadsheet Calculation Procedure --- p.16 / Hypothesis Testing --- p.18 / The First Type of Tests --- p.18 / The Second Type of Tests --- p.19 / The Third Type of Tests --- p.20 / Chapter IV. --- RESEARCH FINDINGS --- p.21 / Abnormal Returns Obtained by Following RSI Trading Rules --- p.21 / A-shares --- p.21 / Buy signals --- p.21 / Interpretations of buy signals in A-share markets --- p.22 / Sell signals --- p.22 / Interpretations of sell signals in A-share markets --- p.23 / B-shares --- p.25 / Buy signals --- p.25 / Interpretations of buy signals in B-share markets --- p.25 / Sell signals --- p.26 / Interpretations of sell signals in B-share markets --- p.27 / Chapter V. --- ADDITIONAL RESEARCHES ON B-SHARE MARKETS --- p.30 / Findings on Additional Researches on B-share Markets --- p.30 / Interpretations of Findings on Additional Researches on B-share Markets --- p.31 / Chapter VI. --- ADDITIONAL RESEARCHES ON A-SHARE MARKETS --- p.32 / Correlation between Abnormal Return and Volume Turnover --- p.33 / Findings on Correlation between Abnormal Return and Volume Turnover --- p.33 / Interpretations of Findings on Correlation between Abnormal Return and Volume Turnover --- p.33 / Correlation between Abnormal Return and Market Value --- p.34 / Findings on Correlation between Abnormal Return and Market Value --- p.34 / Interpretations of Findings on Correlation between Abnormal Return and Market Value --- p.35 / Chapter VII. --- CONCLUSIONS --- p.37 / Chapter VIII. --- LIMITATIONS --- p.39 / Chapter IX. --- FURTHER STUDIES RECOMMENDED --- p.42 / APPENDIX --- p.44 / BIBLIOGRAPHY --- p.54

abstract: The students of Arizona State University, under the mentorship of Dr George Karady, have been collaborating with Salt River Project (SRP), a major power utility in the state of Arizona, trying to study and optimize a battery-supported grid-tied rooftop Photovoltaic (PV) system, sold by a commercial vendor. SRP believes this system has the potential to satisfy the needs of its customers, who opt for utilizing solar power to partially satisfy their power needs. An important part of this elaborate project is the development of a new load forecasting algorithm and a better control strategy for the optimized utilization of the storage system. The built-in algorithm of this commercial unit uses simple forecasting and battery control strategies. With the recent improvement in Machine Learning (ML) techniques, development of a more sophisticated model of the problem in hand was possible. This research is aimed at achieving the goal by utilizing the appropriate ML techniques to better model the problem, which will essentially result in a better solution. In this research, a set of six unique features are used to model the load forecasting problem and different ML algorithms are simulated on the developed model. A similar approach is taken to solve the PV prediction problem. Finally, a very effective battery control strategy is built (utilizing the results of the load and PV forecasting), with the aim of ensuring a reduction in the amount of energy consumed from the grid during the “on-peak” hours. Apart from the reduction in the energy consumption, this battery control algorithm decelerates the “cycling aging” or the aging of the battery owing to the charge/dis-charges cycles endured by selectively charging/dis-charging the battery based on need. ii The results of this proposed strategy are verified using a hardware implementation (the PV system was coupled with a custom-built load bank and this setup was used to simulate a house). The results pertaining to the performances of the built-in algorithm and the ML algorithm are compared and the economic analysis is performed. The findings of this research have in the process of being published in a reputed journal. / Dissertation/Thesis / Masters Thesis Electrical Engineering 2018

This PhD thesis focuses on using time series models for counts in modelling and forecasting a special type of count series called intermittent series. An intermittent series is a series of non-negative integer values with some zero values. Such series occur in many areas including inventory control of spare parts. Various methods have been developed for intermittent demand forecasting with Croston’s method being the most widely used. Some studies focus on finding a model underlying Croston’s method. With none of these studies being successful in demonstrating an underlying model for which Croston’s method is optimal, the focus should now shift towards stationary models for intermittent demand forecasting. This thesis explores the application of a class of models for count data called the Integer Autoregressive Moving Average (INARMA) models. INARMA models have had applications in different areas such as medical science and economics, but this is the first attempt to use such a model-based method to forecast intermittent demand. In this PhD research, we first fill some gaps in the INARMA literature by finding the unconditional variance and the autocorrelation function of the general INARMA(p,q) model. The conditional expected value of the aggregated process over lead time is also obtained to be used as a lead time forecast. The accuracy of h-step-ahead and lead time INARMA forecasts are then compared to those obtained by benchmark methods of Croston, Syntetos-Boylan Approximation (SBA) and Shale-Boylan-Johnston (SBJ). The results of the simulation suggest that in the presence of a high autocorrelation in data, INARMA yields much more accurate one-step ahead forecasts than benchmark methods. The degree of improvement increases for longer data histories. It has been shown that instead of identification of the autoregressive and moving average order of the INARMA model, the most general model among the possible models can be used for forecasting. This is especially useful for short history and high autocorrelation in data. The findings of the thesis have been tested on two real data sets: (i) Royal Air Force (RAF) demand history of 16,000 SKUs and (ii) 3,000 series of intermittent demand from the automotive industry. The results show that for sparse data with long history, there is a substantial improvement in using INARMA over the benchmarks in terms of Mean Square Error (MSE) and Mean Absolute Scaled Error (MASE) for the one-step ahead forecasts. However, for series with short history the improvement is narrower. The improvement is greater for h-step ahead forecasts. The results also confirm the superiority of INARMA over the benchmark methods for lead time forecasts.

No description available.

This thesis contains a manuscript describing the implementation of a high resolution wave forecasting model for the coasts of Washington and Oregon. The purpose of this project was to advance the wave predictive capabilities of the states of Oregon and the southwest part of Washington by including the effects of local bathymetric features in the operational forecasts. A 30 arc-second resolution wave forecasting model was implemented making use of the WAVEWATCH III numerical code covering the coastal region from Klamath, CA to Taholah, WA. The wave forecasts extend to the continental shelf at this resolution. To assess the performance of the model, its output was compared against in situ data, with normalized root-mean-squared errors in significant wave height in the vicinity of 0.20 and linear correlation coefficients greater than 0.80. Making use of the resulting validated regional scale wave forecasting system, an evaluation of the model sensitivity to the inclusion of bottom friction and wind input at the shelf level was performed. Results suggest that neither dissipation due to bottom friction or wind generation are significant for long term forecasting/hindcasting in the region. Results from a series of hindcasts suggest that several significant offshore features may affect the nearshore wave field. To evaluate it, a shelf scale SWAN model was implemented and a series of numerical experiments performed. Results suggest that the Astoria and McArthur Canyons; the Stonewall, Perpetua, and Heceta Banks; and Cape Blanco are significant bathymetric features that are capable of producing significant alongshore variability in wave heights nearshore. / Graduation date: 2013

Under deregulated electric market, electricity price is no longer set by the monopoly utility company rather it responds to the market and operating conditions. Offering the right amount of electricity at the right time with the right bidding price has become the key for utility companies pursuing maximum profits under deregulated electricity market. Therefore, electricity market clearing price (MCP) forecasting became essential for decision making, scheduling and bidding strategy planning purposes. However, forecasting electricity MCP is a very difficult problem due to uncertainties associated with input variables.<p> Neural network based approach promises to be an effective forecasting tool in an environment with high degree of non-linearity and uncertainty. Although there are several techniques available for short-term MCP forecasting, very little has been done to do mid-term MCP forecasting. Two new artificial neural networks have been proposed and reported in this thesis that can be utilized to forecast mid-term daily peak and mid-term hourly electricity MCP. The proposed neural networks can simulate the electricity MCP with electricity hourly demand, electricity daily peak demand, natural gas price and precipitation as input variables. Two situations have been considered; electricity MCP forecasting under real deregulated electric market and electricity MCP forecasting under deregulated electric market with perfect competition. The PJM interconnect system has been utilized for numerical results. Techniques have been developed to overcome difficulties in training the neural network and improve the training results.

Under deregulated electric market, electricity price is no longer set by the monopoly utility company rather it responds to the market and operating conditions. Offering the right amount of electricity at the right time with the right bidding price has become the key for utility companies pursuing maximum profits under deregulated electricity market. Therefore, electricity market clearing price (MCP) forecasting became essential for decision making, scheduling and bidding strategy planning purposes. However, forecasting electricity MCP is a very difficult problem due to uncertainties associated with input variables.<p> Neural network based approach promises to be an effective forecasting tool in an environment with high degree of non-linearity and uncertainty. Although there are several techniques available for short-term MCP forecasting, very little has been done to do mid-term MCP forecasting. Two new artificial neural networks have been proposed and reported in this thesis that can be utilized to forecast mid-term daily peak and mid-term hourly electricity MCP. The proposed neural networks can simulate the electricity MCP with electricity hourly demand, electricity daily peak demand, natural gas price and precipitation as input variables. Two situations have been considered; electricity MCP forecasting under real deregulated electric market and electricity MCP forecasting under deregulated electric market with perfect competition. The PJM interconnect system has been utilized for numerical results. Techniques have been developed to overcome difficulties in training the neural network and improve the training results.