Knowledge distribution nodes and home based businesses : role of local business associations and local council in Casey LGA

This paper examines the structure, function and role of local business associations in home based business development within an urban region. Casey local government area (LGA), Victoria, is the focus, where nine local business associations in the area (as well as the local council) are evaluated in the context of support for local-based business development. The evaluation draws upon primary data collected by surveys of local home based businesses, and follows up by semi-structured interviews of representatives from these business associations and the local council. This paper identifies that local business associations are fragmented and have significant overlap in their activities, of which the commonest activity is acting as a knowledge distribution node. The cash strapped local council is the most important node. All are restricted by vision and resources. As a result, the services provided have little impact on sustainable business development in Casey.

Hybrid neural-evolutionary model for electricity price forecasting

Evolving artificial neural networks has attracted much attention among researchers recently, especially in the fields where plenty of data exist but explanatory theories and models are lacking or based upon too many simplifying assumptions. Financial time series forecasting is one of them. A hybrid model is used to forecast the hourly electricity price from the California Power Exchange. A collaborative approach is adopted to combine ANN and evolutionary algorithm. The main contributions of this thesis include: Investigated the effect of changing values of several important parameters on the performance of the model, and selected the best combination of these parameters; good forecasting results have been obtained with the implemented hybrid model when the best combination of parameters is used. The lowest MAPE through a single run is 5. 28134%. And the lowest averaged MAPE over 10 runs is 6.088%, over 30 runs is 6.786%; through the investigation of the parameter period, it is found that by including future values of the homogenous moments of the instant being forecasted into the input vector, forecasting accuracy is greatly enhanced. A comparison of results with other works reported in the literature shows that the proposed model gives superior performance on the same data set.

Construction of neural network-based prediction intervals using particle swarm optimization

Prediction intervals (PIs) are excellent tools for quantification of uncertainties associated with point forecasts and predictions. This paper adopts and develops the lower upper bound estimation (LUBE) method for construction of PIs using neural network (NN) models. This method is fast and simple and does not require calculation of heavy matrices, as required by traditional methods. Besides, it makes no assumption about the data distribution. A new width-based index is proposed to quantitatively check how much PIs are informative. Using this measure and the coverage probability of PIs, a multi-objective optimization problem is formulated to train NN models in the LUBE method. The optimization problem is then transformed into a training problem through definition of a PI-based cost function. Particle swarm optimization (PSO) with the mutation operator is used to minimize the cost function. Experiments with synthetic and real-world case studies indicate that the proposed PSO-based LUBE method can construct higher quality PIs in a simpler and faster manner.

A new hybrid method for Bayesian network learning With dependency constraints

A Bayes net has qualitative and quantitative aspects: The qualitative aspect is its graphical structure that corresponds to correlations among the variables in the Bayes net. The quantitative aspects are the net parameters. This paper develops a hybrid criterion for learning Bayes net structures that is based on both aspects. We combine model selection criteria measuring data fit with correlation information from statistical tests: Given a sample d, search for a structure G that maximizes score(G, d), over the set of structures G that satisfy the dependencies detected in d. We rely on the statistical test only to accept conditional dependencies, not conditional independencies. We show how to adapt local search algorithms to accommodate the observed dependencies. Simulation studies with GES search and the BDeu/BIC scores provide evidence that the additional dependency information leads to Bayes nets that better fit the target model in distribution and structure.

Prediction intervals for electricity load forecasting using neural networks

Most of the research in time series is concerned with point forecasting. In this paper we focus on interval forecasting and its application for electricity load prediction. We extend the LUBE method, a neural network-based method for computing prediction intervals. The extended method, called LUBEX, includes an advanced feature selector and an ensemble of neural networks. Its performance is evaluated using Australian electricity load data for one year. The results showed that LUBEX is able to generate high quality prediction intervals, using a very small number of previous lag variables and having acceptable training time requirements. The use of ensemble is shown to be critical for the accuracy of the results.

An effective VAR planning to improve dynamic voltage profile of distribution networks with distributed wind generation

This paper proposes an effective VAR planning based on reactive power margin for the enhancement of dynamic voltage stability in distribution networks with distributed wind generation. The analysis is carried over a distribution test system representative of the Kumamoto area in Japan. The detailed mathematical modeling of the system is also presented. Firstly, this paper provides simulation results showing the effects of composite load on voltage dynamics in the distribution network through an accurate time-domain analysis. Then, a cost-effective combination of shunt capacitor bank and distribution static synchronous compensator (D-STATCOM) is selected to ensure fast voltage recovery after a sudden disturbance. The analysis shows that the proposed approach can reduce the size of compensating devices, which in turn, reduces the cost. It also reduces power loss of the system.

Dynamic load variation and stability analysis in distribution networks with distributed generators

In this paper, the modeling of the distribution network is done in a different way where the distributed generator and dynamic loads are considered. Based on this modeling, this paper presents an analysis to investigate the dynamic and static load variation effect on the distribution network. Graphical interface industry software is used to conduct all the aspects of model implementation and carry out the extensive simulation studies. Here also focuses on the worst case scenario and the different fault effect on the generator. Finally, this paper presents the voltage profile for different penetration with different network configurations.

Effects of load modeling in power distribution system with distributed wind generation

This paper presents the impact of different types of load models in distribution network with distributed wind generation. The analysis is carried out for a test distribution system representative of the Kumamoto area in Japan. Firstly, this paper provides static analysis showing the impact of static load on distribution system. Then, it investigates the effects of static as well as composite load based on the load composition of IEEE task force report [1] through an accurate time-domain analysis. The analysis shows that modeling of loads has a significant impact on the voltage dynamics of the distribution system with distributed generation.

Characteristics and applications of energy storage system to power network - A review

Maintaining reliability and stability of a power systems in transmission and distribution level becomes a big challenge in present scenario. Grid operators are always responsible to maintain equilibrium between available power generation and demand of end users. Maintaining grid balance is a bigger issue, in case of any unexpected generation shortage or grid disturbance or integration of any renewable energy sources like wind and solar power in the energy mix. In order to compensate such imbalance and to facilitate more renewable energy sources with the grid, energy storage system (ESS) started to be playing an important role with the advancement of the state of the art technology. ESS can also help to get reduction in greenhouse gas (GHG) emission by means of integrating more renewable energy sources to the grid. There are various types of Energy Storage (ES) technologies which are being used in power systems network from large scale (above 50MW) to small scale (up to 100KW). Based on the characteristics, each storage technology has their own merits and demerits. This paper carried out extensive review study and verifies merits and demerits of each storage technology and identifies the suitable technology for the future. This paper also has conducted feasibility study with the aid of E-SelectTM tool for various ES technologies in applications point of view at different grid locations. This review study helps to evaluate feasible ES technology for a particular electrical application and also helps to develop smart hybrid storage system for grid applications in efficient way.

Uncertainty handling using neural network-based prediction intervals for electrical load forecasting

The complexity and level of uncertainty present in operation of power systems have significantly grown due to penetration of renewable resources. These complexities warrant the need for advanced methods for load forecasting and quantifying uncertainties associated with forecasts. The objective of this study is to develop a framework for probabilistic forecasting of electricity load demands. The proposed probabilistic framework allows the analyst to construct PIs (prediction intervals) for uncertainty quantification. A newly introduced method, called LUBE (lower upper bound estimation), is applied and extended to develop PIs using NN (neural network) models. The primary problem for construction of intervals is firstly formulated as a constrained single-objective problem. The sharpness of PIs is treated as the key objective and their calibration is considered as the constraint. PSO (particle swarm optimization) enhanced by the mutation operator is then used to optimally tune NN parameters subject to constraints set on the quality of PIs. Historical load datasets from Singapore, Ottawa (Canada) and Texas (USA) are used to examine performance of the proposed PSO-based LUBE method. According to obtained results, the proposed probabilistic forecasting method generates well-calibrated and informative PIs. Furthermore, comparative results demonstrate that the proposed PI construction method greatly outperforms three widely used benchmark methods. © 2014 Elsevier Ltd.

Retention of the original LLC structure in a cross-linked poly(ethylene glycol) diacrylate hydrogel with reinforcement from a silica network

Cross-linked poly(ethylene glycol) diacrylate (PEGDA) hydrogels with uniformly controlled nanoporous structures templated from hexagonal lyotropic liquid crystals (LLC) represent separation membrane materials with potentially high permeability and selectivity due to their high pore density and narrow pore size distribution. However, retaining LLC templated nanostructures is a challenge as the polymer gels are not strong enough to sustain the surface tension during the drying process. In the current study, cross-linked PEGDA gels were reinforced with a silica network synthesized via an in situ sol-gel method, which assists in the retention of the hexagonal LLC structure. The silica precursor does not obstruct the formation of hexagonal phases. After surfactant removal and drying, these hexagonal structures in samples with a certain amount of tetraethoxysilane (TEOS) loading are well retained while the nanostructures are collapsed in samples without silica reinforcement, leading to the hypothesis that the reinforcement provided by the silica network stabilizes the LLC structure. The study examines the conditions necessary for a sufficient and well dispersed silica network in PEGDA gels that contributes to the retention of original LLC structures, which potentially enables broad applications of these gels as biomedical and membrane materials.

Electricity load and price forecasting with influential factors in a deregulated power industry

With the emergence of smart power grid and distributed generation technologies in recent years, there is need to introduce new advanced models for forecasting. Electricity load and price forecasts are two primary factors needed in a deregulated power industry. The performances of the demand response programs are likely to be deteriorated in the absence of accurate load and price forecasting. Electricity generation companies, system operators, and consumers are highly reliant on the accuracy of the forecasting models. However, historical prices from the financial market, weekly price/load information, historical loads and day type are some of the explanatory factors that affect the accuracy of the forecasting. In this paper, a neural network (NN) model that considers different influential factors as feedback to the model is presented. This model is implemented with historical data from the ISO New England. It is observed during experiments that price forecasting is more complicated and hence less accurate than the load forecasting.

On addressing the imbalance problem : A correlated KNN approach for network traffic classification

With the arrival of big data era, the Internet traffic is growing exponentially. A wide variety of applications arise on the Internet and traffic classification is introduced to help people manage the massive applications on the Internet for security monitoring and quality of service purposes. A large number of Machine Learning (ML) algorithms are introduced to deal with traffic classification. A significant challenge to the classification performance comes from imbalanced distribution of data in traffic classification system. In this paper, we proposed an Optimised Distance-based Nearest Neighbor (ODNN), which has the capability of improving the classification performance of imbalanced traffic data. We analyzed the proposed ODNN approach and its performance benefit from both theoretical and empirical perspectives. A large number of experiments were implemented on the real-world traffic dataset. The results show that the performance of “small classes” can be improved significantly even only with small number of training data and the performance of “large classes” remains stable.