Real-time scheduling of embedded applications on multi-core platforms

For the past several decades, we have experienced the tremendous growth, in both scale and scope, of real-time embedded systems, thanks largely to the advances in IC technology. However, the traditional approach to get performance boost by increasing CPU frequency has been a way of past. Researchers from both industry and academia are turning their focus to multi-core architectures for continuous improvement of computing performance. In our research, we seek to develop efficient scheduling algorithms and analysis methods in the design of real-time embedded systems on multi-core platforms. Real-time systems are the ones with the response time as critical as the logical correctness of computational results. In addition, a variety of stringent constraints such as power/energy consumption, peak temperature and reliability are also imposed to these systems. Therefore, real-time scheduling plays a critical role in design of such computing systems at the system level. We started our research by addressing timing constraints for real-time applications on multi-core platforms, and developed both partitioned and semi-partitioned scheduling algorithms to schedule fixed priority, periodic, and hard real-time tasks on multi-core platforms. Then we extended our research by taking temperature constraints into consideration. We developed a closed-form solution to capture temperature dynamics for a given periodic voltage schedule on multi-core platforms, and also developed three methods to check the feasibility of a periodic real-time schedule under peak temperature constraint. We further extended our research by incorporating the power/energy constraint with thermal awareness into our research problem. We investigated the energy estimation problem on multi-core platforms, and developed a computation efficient method to calculate the energy consumption for a given voltage schedule on a multi-core platform. In this dissertation, we present our research in details and demonstrate the effectiveness and efficiency of our approaches with extensive experimental results.

Synthesis and characterization of photochromic indolyl substituted fulgides and fulgimides

The fulgide and fulgimide family constitutes an important class of organic photochromic compounds. The ability of fulgides and fulgimides to interconvert between two key forms by irradiation of different wavelength of light has made them promising material in optical memory devices, optical switches and sensors, and specialty dyes and inks. Thermal stability and hydrolytic stability of fulgides and fulgimides are essential for their practical applications. A deuterated trifluoromethyl indolylfulgide was synthesized based on the synthetic pathway of the proteo trifluoromethyl indolylfulgide using commercially available deuterated starting materials. Deuteration of the isopropylidene group improved the thermal stability of the indolylfulgide by a factor of 7. ^ Fulgimides are the most important fulgide derivatives. Fulgimides improve the hydrolytic stability of fulgides by replacing the succinic anhydride ring with a succinimide ring. A novel trifluoromethyl N-ethoxycarbonylmethyl indolylfulgimide was synthesized from trifluoromethyl indolylfulgide. The trifluoromethyl indolylfulgide was synthesized on a large scale in five steps with an overall yield of 18%. The indolylfulgide was then converted to indolylfulgimide by aminolysis follow by dehydration. The N-ethoxycarbonylmethyl indolylfulgimide showed enhanced hydrolytic stability and photochemical stability in 70/30 ethanol/water. ^ Three novel aqueous soluble fulgimides, trifluoromethyl carboxylic acid indolylfulgimide, dicarboxylic acid indolylfulgimide, and H-carboxylic acid indolylfulgimide, were synthesized. In sodium phosphate buffer (pH 7.4) at 37 ºC, an unusual hydrolysis of the trifluoromethyl group of the closed form of the carboxylic acid indolylfulgimide resulted in the dicarboxylic acid indolylfulgimide which has an additional carboxylic acid group. The closed form of dicarboxylic acid indolylfulgimide was further decarboxylated to generate H-carboxylic acid indolylfulgimide which was not photochromic. The trifluoromethyl dicarboxylic acid indolylfulgimide is the most robust fulgimide yet reported in aqueous solution. ^ A novel aqueous soluble methyl carboxylic acid indolylfulgimide was synthesized from methyl indolylfulgide. The methyl indolylfulgide was synthesized in five steps with an overall yield of 21%. The methyl carboxylic acid indolylfulgimide was synthesized by aminolysis follow by dehydration. The methyl carboxylic acid indolylfulgimide is expected to have improved thermal and photochemical stability in aqueous solutions relative to the trifluoromethyl analog.^

Synthesis and Characterization of Photochromic Copolymers Containing 3-Indolylfulgides/Indolylfulgimides

Fulgides and fulgimides are important organic photochromic compounds and can switch between the open forms and the closed forms with light. The 3-indolylfulgides and 3-indolylfulgimides exhibit promising photochromic properties and have great potential in optical memory devices, optical switches and biosensors. Copolymers containing 3-indolylfulgides/indolylfulgimides synthesized via free radical polymerizations increase conformation changes and allow the photochromic compounds to be uniformly distributed in the polymer matrix. A trifluoromethyl 3-indolylfulgide and two trifluoromethyl 3-indolylfulgimides with one or two polymerizable N-stryryl group(s) were prepared. Copolymerization with methyl methacrylate provided two linear copolymers or a cross-linked copolymer. The properties of the monomeric fulgide/fulgimides and copolymers in toluene or as thin films were characterized. In general, the photochromic monomers and copolymers revealed similar photochromic properties and exhibited good thermal and photochemical stability. All compounds absorb visible light in both open forms and closed forms. The closed form copolymers were more stable than the open form copolymers and showed little or no degradation after 400 h. The photochemical degradation rate was less than 0.03% per cycle. In films, conformational restrictions were observed for the open forms suggesting that the preparation of films from the closed forms is advantageous. Two novel methyl 3-indolylfulgimides with one or two polymerizable N-stryryl group(s) were prepared. Copolymerization of acrylamide with the methyl indolylfulgimides or the trifluoromethyl indolylfulgimides yielded two aqueous soluble linear copolymers and two photochromic hydrogels. The closed form copolymers containing trifluoromethyl indolylfulgimides were hydrolyzed in aqueous solution by replacing the trifluoromethyl group with a carboxylic acid group. The resulting carboxylic copolymers were also photochromic. The copolymers containing methyl fulgimides were stable in aqueous solutions and did not hydrolyze. Both methyl and carboxylic copolymers exhibited good stability in aqueous solutions. In general, the open form copolymers were more stable than the closed form copolymers, and the copolymers revealed better stability in acidic solution than neutral solution. The linear copolymers displayed better photochemical stability in neutral solution and degraded up to 22% after 105 cycles. In contrast, the hydrogels showed enhanced fatigue resistance in acidic condition and underwent up to 60 cycles before degrading 24%.

Essays on exchange rate economics

Exchange rate economics has achieved substantial development in the past few decades. Despite extensive research, a large number of unresolved problems remain in the exchange rate debate. This dissertation studied three puzzling issues aiming to improve our understanding of exchange rate behavior. Chapter Two used advanced econometric techniques to model and forecast exchange rate dynamics. Chapter Three and Chapter Four studied issues related to exchange rates using the theory of New Open Economy Macroeconomics. ^ Chapter Two empirically examined the short-run forecastability of nominal exchange rates. It analyzed important empirical regularities in daily exchange rates. Through a series of hypothesis tests, a best-fitting fractionally integrated GARCH model with skewed student-t error distribution was identified. The forecasting performance of the model was compared with that of a random walk model. Results supported the contention that nominal exchange rates seem to be unpredictable over the short run in the sense that the best-fitting model cannot beat the random walk model in forecasting exchange rate movements. ^ Chapter Three assessed the ability of dynamic general-equilibrium sticky-price monetary models to generate volatile foreign exchange risk premia. It developed a tractable two-country model where agents face a cash-in-advance constraint and set prices to the local market; the exogenous money supply process exhibits time-varying volatility. The model yielded approximate closed form solutions for risk premia and real exchange rates. Numerical results provided quantitative evidence that volatile risk premia can endogenously arise in a new open economy macroeconomic model. Thus, the model had potential to rationalize the Uncovered Interest Parity Puzzle. ^ Chapter Four sought to resolve the consumption-real exchange rate anomaly, which refers to the inability of most international macro models to generate negative cross-correlations between real exchange rates and relative consumption across two countries as observed in the data. While maintaining the assumption of complete asset markets, this chapter introduced endogenously segmented asset markets into a dynamic sticky-price monetary model. Simulation results showed that such a model could replicate the stylized fact that real exchange rates tend to move in an opposite direction with respect to relative consumption. ^

Lightweight middleware for SDR inter-components communication

The ability to use Software Defined Radio (SDR) in the civilian mobile applications will make it possible for the next generation of mobile devices to handle multi-standard personal wireless devices and ubiquitous wireless devices. The original military standard created many beneficial characteristics for SDR, but resulted in a number of disadvantages as well. Many challenges in commercializing SDR are still the subject of interest in the software radio research community. Four main issues that have been already addressed are performance, size, weight, and power. ^ This investigation presents an in-depth study of SDR inter-components communications in terms of total link delay related to the number of components and packet sizes in systems based on Software Communication Architecture (SCA). The study is based on the investigation of the controlled environment platform. Results suggest that the total link delay does not linearly increase with the number of components and the packet sizes. The closed form expression of the delay was modeled using a logistic function in terms of the number of components and packet sizes. The model performed well when the number of components was large. ^ Based upon the mobility applications, energy consumption has become one of the most crucial limitations. SDR will not only provide flexibility of multi-protocol support, but this desirable feature will also bring a choice of mobile protocols. Having such a variety of choices available creates a problem in the selection of the most appropriate protocol to transmit. An investigation in a real-time algorithm to optimize energy efficiency was also performed. Communication energy models were used including switching estimation to develop a waveform selection algorithm. Simulations were performed to validate the concept.^

Fair and QoS-oriented resource management in heterogeneous networks

In this paper, a heterogeneous network composed of femtocells deployed within a macrocell network is considered, and a quality-of-service (QoS)-oriented fairness metric which captures important characteristics of tiered network architectures is proposed. Using homogeneous Poisson processes, the sum capacities in such networks are expressed in closed form for co-channel, dedicated channel, and hybrid resource allocation methods. Then a resource splitting strategy that simultaneously considers capacity maximization, fairness constraints, and QoS constraints is proposed. Detailed computer simulations utilizing 3GPP simulation assumptions show that a hybrid allocation strategy with a well-designed resource split ratio enjoys the best cell-edge user performance, with minimal degradation in the sum throughput of macrocell users when compared with that of co-channel operation.

Essays on Exchange Rate Economics

Exchange rate economics has achieved substantial development in the past few decades. Despite extensive research, a large number of unresolved problems remain in the exchange rate debate. This dissertation studied three puzzling issues aiming to improve our understanding of exchange rate behavior. Chapter Two used advanced econometric techniques to model and forecast exchange rate dynamics. Chapter Three and Chapter Four studied issues related to exchange rates using the theory of New Open Economy Macroeconomics. Chapter Two empirically examined the short-run forecastability of nominal exchange rates. It analyzed important empirical regularities in daily exchange rates. Through a series of hypothesis tests, a best-fitting fractionally integrated GARCH model with skewed student-t error distribution was identified. The forecasting performance of the model was compared with that of a random walk model. Results supported the contention that nominal exchange rates seem to be unpredictable over the short run in the sense that the best-fitting model cannot beat the random walk model in forecasting exchange rate movements. Chapter Three assessed the ability of dynamic general-equilibrium sticky-price monetary models to generate volatile foreign exchange risk premia. It developed a tractable two-country model where agents face a cash-in-advance constraint and set prices to the local market; the exogenous money supply process exhibits time-varying volatility. The model yielded approximate closed form solutions for risk premia and real exchange rates. Numerical results provided quantitative evidence that volatile risk premia can endogenously arise in a new open economy macroeconomic model. Thus, the model had potential to rationalize the Uncovered Interest Parity Puzzle. Chapter Four sought to resolve the consumption-real exchange rate anomaly, which refers to the inability of most international macro models to generate negative cross-correlations between real exchange rates and relative consumption across two countries as observed in the data. While maintaining the assumption of complete asset markets, this chapter introduced endogenously segmented asset markets into a dynamic sticky-price monetary model. Simulation results showed that such a model could replicate the stylized fact that real exchange rates tend to move in an opposite direction with respect to relative consumption.

Lightweight Middleware for Software Defined Radio (SDR) Inter-Components Communication

The ability to use Software Defined Radio (SDR) in the civilian mobile applications will make it possible for the next generation of mobile devices to handle multi-standard personal wireless devices and ubiquitous wireless devices. The original military standard created many beneficial characteristics for SDR, but resulted in a number of disadvantages as well. Many challenges in commercializing SDR are still the subject of interest in the software radio research community. Four main issues that have been already addressed are performance, size, weight, and power. This investigation presents an in-depth study of SDR inter-components communications in terms of total link delay related to the number of components and packet sizes in systems based on Software Communication Architecture (SCA). The study is based on the investigation of the controlled environment platform. Results suggest that the total link delay does not linearly increase with the number of components and the packet sizes. The closed form expression of the delay was modeled using a logistic function in terms of the number of components and packet sizes. The model performed well when the number of components was large. Based upon the mobility applications, energy consumption has become one of the most crucial limitations. SDR will not only provide flexibility of multi-protocol support, but this desirable feature will also bring a choice of mobile protocols. Having such a variety of choices available creates a problem in the selection of the most appropriate protocol to transmit. An investigation in a real-time algorithm to optimize energy efficiency was also performed. Communication energy models were used including switching estimation to develop a waveform selection algorithm. Simulations were performed to validate the concept.