John Gow

Application of Artificial Neural Network and Support Vector Regression in cognitive radio networks for RF power prediction using compact differential evolution algorithm

Cognitive radio (CR) technology has emerged as a promising solution to many wireless communication problems including spectrum scarcity and underutilization. To enhance the selection of channel with less noise among the white spaces (idle channels), the a priory knowledge of Radio Frequency (RF) power is very important. Computational Intelligence (CI) techniques cans be applied to these scenarios to predict the required RF power in the available channels to achieve optimum Quality of Service (QoS). In this paper, we developed a time domain based optimized Artificial Neural Network (ANN) and Support Vector Regression (SVR) models for the prediction of real world RF power within the GSM 900, Very High Frequency (VHF) and Ultra High Frequency (UHF) FM and TV bands. Sensitivity analysis was used to reduce the input vector of the prediction models. The inputs of the ANN and SVR consist of only time domain data and past RF power without using any RF power related parameters, thus forming a nonlinear time series prediction model. The application of the models produced was found to increase the robustness of CR applications, specifically where the CR had no prior knowledge of the RF power related parameters such as signal to noise ratio, bandwidth and bit error rate. Since CR are embedded communication devices with memory constrain limitation, the models used, implemented a novel and innovative initial weight optimization of the ANNs through the use of compact differential evolutionary (cDE) algorithm variants which are memory efficient. This was found to enhance the accuracy and generalization of the ANN model.

MIMO-OFDM-based DVB-H systems: a hardware design for a PAPR reduction technique

Digital video broadcasting - handheld (DVB-H) is the technology driving mobile TV, which uses orthogonal frequency division multiplexing (OFDM) systems with multiple-input multiple-output technology (MIMO). These mobile communication systems have a promising future of supporting high data rate transmissions for both video and data. However, since the OFDM systems are sensitive to the peak-to-average power ratio (PAPR) problem, this work proposes a new technique (novel technique to reduce the PAPR based on turbo coding (NTRPT)), based on the turbo encoding technology, to reduce the PAPR effects for MIMO-OFDM-based DVB-H systems. This technique has been implemented and validated in hardware. It can support different types of modulation and coding techniques, and offers better results in reducing the PAPR than the conventional techniques currently proposed for this purpose, such as the clipping technique and the partial transmit sequence (PTS) technique, presented here using computer simulations

Optimal sizing and location of large PV plants on radial distribution feeders for minimum line losses

Suitable procedure for optimal sizing and location of multiple Photovoltaic Distributed Generators (PVDG) on radial distribution feeders has been developed. The optimization objective is to minimize the accumulated line power loss over the day (line energy loss) along the feeder, while keeping the voltage profile along the feeder with the statutory limits. A method has been applied to rate the line energy loss considering one time interval, namely Feasible Optimization Interval. An effective method to help determine feasible iterative steps has been developed. The procedure has been applied on actual 11kV feeder. The application showed obvious benefits in terms of line loss reduction and improvement of the voltage profile. Alternative feasible solutions have been produced in case the optimal solution cannot be applied for any reason -like inconvenience/limitation of land or investment.

Optimized artificial neural network using differential evolution for prediction of RF power in VHF/UHF TV and GSM 900 bands for cognitive radio networks

Cognitive radio (CR) technology has emerged as a promising solution to many wireless communication problems including spectrum scarcity and underutilization. The knowledge of Radio Frequency (RF) power (primary signals and/or interfering signals plus noise) in the channels to be exploited by CR is of paramount importance, not just the existence or absence of primary users. If a channel is known to be noisy, even in the absence of primary users, using such channels will demand large quantities of radio resources (transmission power, bandwidth, etc) in order to deliver an acceptable quality of service to users. Computational Intelligence (CI) techniques can be applied to these scenarios to predict the required RF power in the available channels to achieve optimum Quality of Service (QoS). While most of the prediction schemes are based on the determination of spectrum holes, those designed for power prediction use known radio parameters such as signal to noise ratio (SNR), bandwidth, and bit error rate. Some of these parameters may not be available or known to cognitive users. In this paper, we developed a time domain based optimized Artificial Neural Network (ANN) model for the prediction of real world RF power within the GSM 900, Very High Frequency (VHF) and Ultra High Frequency (UHF) TV bands. The application of the models produced was found to increase the robustness of CR applications, specifically where the CR had no prior knowledge of the RF power related parameters. The models used implemented a novel and innovative initial weight optimization of the ANNs through the use of differential evolutionary algorithms. This was found to enhance the accuracy and generalization of the approach.

Optimized Neural Network using differential evolutionary and swarm intelligence optimization algorithms for RF power prediction in cognitive radio network: A comparative study

Cognitive radio (CR) technology has emerged as a promising solution to many wireless communication problems including spectrum scarcity and underutilization. The a priory knowledge of Radio Frequency (RF) power (primary signals and/ or interfering signals plus noise) in the channels to be exploited by CR is of paramount importance. This will enable the selection of channel with less noise among idle (free) channels. Computational Intelligence (CI) techniques can be applied to these scenarios to predict the required RF power in the available channels to achieve optimum Quality of Service (QoS). In this paper, we developed a time domain based optimized Artificial Neural Network (ANN) model for the prediction of real world RF power within the GSM 900, Very High Frequency (VHF) and Ultra High Frequency (UHF) TV bands. The application of the models produced was found to increase the robustness of CR applications, specifically where the CR had no prior knowledge of the RF power related parameters such as signal to noise ratio, bandwidth and bit error rate. The models used, implemented a novel and innovative initial weight optimization of the ANNs through the use of differential evolutionary and swarm intelligence algorithms. This was found to enhance the accuracy and generalization of the ANN model. For this problem, DE/best/1/bin was found to yield a better performance as compared with the other algorithms implemented.

Minimizing line energy loss of radial distribution feeder with a PV Distributed Generation unit avoiding reverse power flow

A procedure for minimizing the accumulated line power losses of radial distribution feeder over the day, namely line energy loss, has been developed. It determines the optimal size and location of a Photovoltaic Distributed Generation (PVDG) unit that minimizes the line energy loss, while avoiding reverse power flow along the feeder. The procedure considers the concept that the PVDG production varies independently from the changes in feeder demand, which most likely results in a peak mismatch for both. With such mismatch the PVDG unit can produce only part of its capacity at the time the feeder meets its peak load demand. Hence, the objective of minimizing the line energy loss is more appropriate in this application than that of minimizing the line peak power loss. However, dealing with energy-based quantities needs a sort of calculations for each time interval over the whole daily duration. In this essence a suitable method has been derived to rate the line energy loss of the feeder at only one time interval over the day, namely Feasible Optimization Interval (FOI). The procedure has been applied successfully on two 11kV radial distribution feeders within Abu Dhabi network. The application demonstrated that the optimal solution resulting in minimum line power loss at the FOI is the same resulting in minimum line energy loss over the day.

Optimal sizing and location of a PV system on three-phase unbalanced radial distribution feeder avoiding reverse power flow

A suitable procedure for optimal sizing and location of a single Photovoltaic Distributed Generation (PVDG) unit on three-phase unbalanced radial distribution feeder has been developed. The procedure avoids reverse power flow along the feeder. It considers the peak mismatch of the feeder load curve and the PVDG production curve. With such mismatch, the PVDG system can produce only part of its capacity at the time the feeder meets its peak demand. Hence, solving the optimization problem for maximum line peak power loss reduction could make no sense. Alternatively, minimization of the accumulated line power losses over the day (line energy loss) is more appropriate in this application. A suitable derivation has been developed to rate the line energy loss reduction considering only one time interval, namely Feasible Optimization Interval (FOI). Thus, the optimization procedure can be solved for maximum line energy-based benefits considering only the FOI. This avoids running the calculations for each time interval over the whole duration. The procedure has been applied successfully on two 11kV feeders within the Abu Dhabi Distribution network.

User interaction based design of low power devices for ad-hoc networks

The design methodology presented in this paper proposes alternative strategies for increasing the battery life of devices in ad-hoc networks. It considers the operation of the device from the users perspective in terms of the expected response from the device and how this can be achieved for minimum power consumption. This information is used to specify the operation of the radio network and shutdown procedures for the device so that it still maintains the required response for the user. Application of these strategies gives a very long battery life as demonstrated in an example design.

Return loss prediction for category 8 cable using pseudorandom impedance generation

This paper examines the return loss predictions of category 8 cable using pseudorandom impedance generation over several cascaded scattering parameter matrices at 1cm length interval. The research applied the 40GBASE-T reference for category 8 cable to simulate the return loss using pseudo-randomly generated impedances in multiple cascaded scattering matrices across different cable lengths. The return loss results show that cable impedance variation of 85Ω to 115Ω does not exceed the limit provided by the 40GBASE-T. The aim of the paper is to provide cable researchers with a tool to investigate cable behavior under a wide variety of pseudorandom impedance variations at 1cm length interval, thereby providing a useful contribution to the ongoing 40GBASE-T developments.

A novel security/home automation gateway for domestic residences

Advances in embedded computing technologies has led to the development of residential gateways, and home automation systems. Installation and maintenance costs associated with such systems, however, are still relatively high. In addition, these systems have largely concentrated on applications such as control of multi-media home entertainment systems, domestic appliance control and automatic scene selection for dinners and parties. This paper presents a Lifestyle system that serves a much wider application range, yet at low cost. The system targets home automation, security, and elderly/disabled care markets.