Cindy Goh

Forecasting of photovoltaic power yield using dynamic neural networks

The importance of predicting the output power of Photovoltaic (PV) plants is crucial in modern power system applications. Predicting the power yield of a PV generation system helps the process of dispatching the power into a grid with improved efficiency in generation planning and operation. This work proposes the use of intelligent tools to forecast the real power output of PV units. These tools primarily comprise dynamic neural networks which are capable of time-series predictions with good reliability. This paper begins with a brief review of various methods of forecasting solar power reported in literature. Results of preliminary work on a 5kW PV panel at King Fahd University of Petroleum and Minerals, Dhahran, Saudi Arabia, is presented. Focused Time Delay and Distributed Time Delay Neural Networks were used as a forecasting tool for this study and their performance was compared with each other.

Dynamic performance of IEEE 802.15.4 devices under persistent WiFi traffic

Recent studies have provided coexistence and interaction models between IEEE 802.15.4 and IEEE 802.11 standards. However, the performance of IEEE 802.15.4 devices under WiFi interference are evaluated based on limit parameters i.e. Packet Reception Rate, which does not exhibit the dynamic interactions in the wireless channel. In this paper, we conduct a series of experiments to demonstrate the dynamic interactions between the IEEE 802.15.4 and IEEE 802.11 bgn standards on relevant devices. The performance of four existing Link Quality Estimators (LQEs) of IEEE 802.15.4 nodes under the IEEE 802.11 bgn interference is analyzed. We show that IEEE 802.15.4 transmission failures are largely due to channel access failures rather than corrupted data packets. Based on the analysis, we propose a new LQE - Packet Reception Rate with Clear Channel Assessment - by merging the Clear Channel Assessment count with the Packet Reception Rate. In comparison to existing LQEs, results show that the new estimator distinguishes persistent IEEE 802.11 bgn traffic more robustly.

Evolutionary Neural Network Based Energy Consumption Forecast for Cloud Computing

The success of Hadoop, an open-source framework for massively parallel and distributed computing, is expected to drive energy consumption of cloud data centers to new highs as service providers continue to add new infrastructure, services and capabilities to meet the market demands. While current research on data center airflow management, HVAC (Heating, Ventilation and Air Conditioning) system design, workload distribution and optimization, and energy efficient computing hardware and software are all contributing to improved energy efficiency, energy forecast in cloud computing remains a challenge. This paper reports an evolutionary computation based modeling and forecasting approach to this problem. In particular, an evolutionary neural network is developed and structurally optimized to forecast the energy load of a cloud data center. The results, both in terms of forecasting speed and accuracy, suggest that the evolutionary neural network approach to energy consumption forecasting for cloud computing is highly promising.

Micromechanics model for predicting effective elastic moduli of porous ceramic matrices with randomly oriented carbon nanotube reinforcements

Multi-step micromechanics-based models are developed to predict the overall effective elastic moduli of porous ceramic with randomly oriented carbon nanotube (CNT) reinforcements. The presence of porosity in the ceramic matrix that has been previously neglected in the literature is considered in present analysis. The ceramic matrix with porosity is first homogenized using a classical Mori-Tanaka model. Then, the homogenized porous ceramic matrix with randomly oriented CNTs is analysed using two micromechanics models. The results predicted by the present models are compared with experimental and analytical results that have been reported in literature. The comparison shows that the discrepancies between the present analytical results and experimental data are about 10% for 4 wt% of CNTs and about 0.5% for 8 wt% CNTs, both substantially lower than the discrepancies currently reported in the literature.

Self-organizing tool for smart design with predictive customer needs and wants to realize Industry 4.0

Following the first three industrial revolutions, Industry 4.0 (I4) aims at realizing mass customization at a mass production cost. Currently, however, there is a lack of smart analytics tools for achieving such a goal. This paper investigates this issues and then develops a predictive analytics framework integrating cloud computing, big data analysis, business informatics, communication technologies, and digital industrial production systems. Computational intelligence in the form of a self-organizing map (SOM) is used to manage relevant big data for feeding potential customer needs and wants to smart designs for targeted productivity and customized mass production. The selection of patterns from big data with SOM helps with clustering and with the selection of optimal attributes. A car customization case study shows that the SOM is able to assign new clusters when growing knowledge of customer needs and wants. The self-organizing tool offers a number of features suitable to smart design that is required in realizing Industry 4.0.

Heuristic grey-box modelling for photovoltaic power systems

ABSTRACT Amongst non-conventional generators, photovoltaics (PVs) are becoming more popular owing to their relatively low costs and convenience. However, the intermittency of the PV generator outputs require accurate forecasting, planning, and optimal management. Existing forecasting methods, which are based on either clear-box or black-box modelling, have room for improvement, especially in the accuracy of capturing the underlying PV characteristics and forecasting of PV yields. This paper explores the use of a priori knowledge of PV systems to heuristically improve their clear-box and black-box models. The paper then further explores the use of heuristic grey-box modelling to identify uncertain parameters of physical principle. Incorporating black boxes to account for such un-modelled uncertainties inherent in a clear box provides the resultant grey box with improved forecasting performance and offers a new approach to practical system modelling. The experimental results on an installed PV system have confirmed the usefulness of this approach.

Identifying smart design attributes for Industry 4.0 customization using a clustering Genetic Algorithm

Industry 4.0 aims at achieving mass customization at a mass production cost. A key component to realizing this is accurate prediction of customer needs and wants, which is however a challenging issue due to the lack of smart analytics tools. This paper investigates this issue in depth and then develops a predictive analytic framework for integrating cloud computing, big data analysis, business informatics, communication technologies, and digital industrial production systems. Computational intelligence in the form of a cluster k-means approach is used to manage relevant big data for feeding potential customer needs and wants to smart designs for targeted productivity and customized mass production. The identification of patterns from big data is achieved with cluster k-means and with the selection of optimal attributes using genetic algorithms. A car customization case study shows how it may be applied and where to assign new clusters with growing knowledge of customer needs and wants. This approach offer a number of features suitable to smart design in realizing Industry 4.0.

Key challenges and opportunities in hull form design optimisation for marine and offshore applications

New environmental regulations and volatile fuel prices have resulted in an ever-increasing need for reduction in carbon emission and fuel consumption. Designs of marine and offshore vessels are more demanding with complex operating requirements and oil and gas exploration venturing into deeper waters and hasher environments. Combinations of these factors have led to the need to optimise the design of the hull for the marine and offshore industry. The contribution of this paper is threefold. Firstly, the paper provides a comprehensive review of the state-of-the-art techniques in hull form design. Specifically, it analyses geometry modelling, shape transformation, optimisation and performance evaluation. Strengths and weaknesses of existing solutions are also discussed. Secondly, key challenges of hull form optimisation specific to the design of marine and offshore vessels are identified and analysed. Thirdly, future trends in performing hull form design optimisation are investigated and possible solutions proposed. A case study on the design optimisation of bulbous bow for passenger ferry vessel to reduce wave-making resistance is presented using NAPA software. Lastly, main issues and challenges are discussed to stimulate further ideas on future developments in this area, including the use of parallel computing and machine intelligence.

Grey-box identification for photovoltaic power systems via particle-swarm algorithm

Amongst renewable generators, photovoltaics (PV) are becoming more popular as the appropriate low cost solution to meet increasing energy demands. However, the integration of renewable energy sources to the electricity grid possesses many challenges. The intermittency of these non-conventional sources often requires accurate forecast, planning and optimal management. Many attempts have been made to tackle these challenges; nonetheless, existing methods fail to accurately capture the underlying characteristics of the system. There exists scope to improve present PV yield forecasting models and methods. This paper explores the use of apriori knowledge of PV systems to build clear box models and identify uncertain parameters via heuristic algorithms. The model is further enhanced by incorporating black box models to account for unmodeled uncertainties in a novel grey-box forecasting and modeling of PV systems.

Evolutionary Neural Network Modeling for Energy Prediction of Cloud Data Centers

Accurate forecasts of data center energy consumptions can help eliminate risks caused by underprovisioning or waste caused by over-provisioning. However, due to nonlinearity and complexity, energy prediction remains a challenge. An added layer of complexity further comes from dynamically changing workloads. There is a lack of physical principle based clear-box models, and existing black-box based methods such neural networks are restrictive. In this paper, we develop an evolutionary neural network as a structurally optimal black-box model to forecast the energy consumption of a dynamic cloud data center. In particular, the approach to evolving an optimal network is developed from several novel mechanisms of a genetic algorithm, such as a structurally-inclusive matrix encoding and species parallelism that help maintain an overall increasing fitness to overcome slow convergence whilst preventing premature dominance. The model is trained using part of the data obtained from a set of MapReduce jobs on a 120-core Hadoop cluster and is then validated against unseen data. The results, both in terms of prediction speed and accuracy, suggest that this evolutionary neural network approach to cloud data center forecast is highly promising.