Search

This paper describes very short-term wind prediction for power generation, utilizing a case study from Tasmania, Australia. Windpower presently is the fastest growing power generation sector in the world. However, windpower is intermittent. To be able to trade efficiently, make the best use of transmission line capability, and address concerns with system frequency in a re-regulated system, accurate very short-term forecasts are essential. The research introduces a novel approach—the application of an adaptive neuro-fuzzy inference system to forecasting a wind time series. Over the very short-term forecast interval, both windspeed and wind direction are important parameters. To be able to be gain the most from a forecast on this time scale, the turbines must be directed toward on oncoming wind. For this reason, this paper forecasts wind vectors, rather than windspeed or power output. [ABSTRACT FROM AUTHOR]

Short‐term load forecasting is essential to power systems management. However, most existing forecasting methods fail to fully consider how to rationally integrate the intrinsic time‐related dimensions of electric load data and the decomposition methods into machine learning models so that their prediction accuracy and robustness still have much room for improvement. To solve this problem, this paper proposes a decomposition‐based multi‐time dimension long short‐term memory (DB‐MTD‐LSTM) model for short‐term electric load forecasting (STELF). In DB‐MTD‐LSTM, empirical mode decomposition with adaptive noise (CEEMDAN) is first introduced to smooth non‐linear non‐stationary electric load data and constrain the modal aliasing or noise of decomposed electric load data in the traditional decomposed method. A joint relevant time dimensions method (JRTDM) is then developed using autocorrelation analysis to rationally extract the temporal characteristics of decomposed data in multiple time dimensions. An improved LSTM called MTD‐LSTM is developed by combining JRTDM with LSTM, which can effectively apply multi‐dimensional time characteristics of the decomposed load to improve the predictive accuracy and robustness. Several datasets from Australia and China are performed to check the predictive performance of DB‐MTD‐LSTM. Experimental results verify that DB‐MTD‐LSTM has better predictive accuracy and satisfactory robustness compared with state‐of‐the‐art and conventional predictive models. [ABSTRACT FROM AUTHOR]

The Lake Margaret Power Scheme located on Tasmania's rugged west coast commenced operations in November 1914. It is a rare example of an early 20th century hydroelectric scheme in Australia, and was the largest private generator in the state prior to the start of large-scale public generation in Tasmania with the commissioning of Waddamana in 1916. This paper examines the history and heritage significance of the Lake Margaret Power Scheme, together with a description of recent developments that will see a refurbished and restored scheme continue to operate well into the future. The history includes a description of major refurbishments, replacements and upgrades that have taken place through the life of the scheme. The paper is based on information drawn from early papers written about the scheme, information supplied by Hydro Tasmania and the personal knowledge of Peter Schulze who worked at Mt Lyell from 1961 to 1988. [ABSTRACT FROM AUTHOR]

The Australian electricity sector is expected to undergo major changes to reduce the current sectoral CO2 emission of 190 million tons to 96 million tons by 2050. This paper summarizes two major modeling studies that have been undertaken since 2006 to understand the full set of investment, price and financial impact on existing generators, especially coal-based generators. We have used a long-term capacity and dispatch optimization model to comprehensively analyze both least-cost and market-led expansion of the system to accommodate alternative emission reduction targets from a shallow cut to a deep cut. The modeling results demonstrate the cost of meeting the target can be over $30 billion in NPV terms. A mix of clean coal technologies, gas and nuclear technologies is expected to displace the existing stock of conventional coal which varies significantly depending on the emission reduction target. The analysis also show that mandatory renewable targets or technology standards are inefficient policies in comparison to a market-based policy such as the proposed emissions trading scheme. [ABSTRACT FROM AUTHOR]

In this paper, a property rights model for electric transmission is proposed and its properties analyzed. The proposed rights, called "border flow rights," support financial hedging of transmission risk and merchant transmission expansion through associated financial rights, called "contracts for differences of differences." These financial rights allow for forward trading of both energy and transmission by a unified exchange, avoiding the bifurcation in current markets between decentralized long-term energy trading and centralized long-term transmission trading. Such long-term trading can help to support the financing of both generation and transmission assets. We consider incentive properties of such a right in the absence of lumpiness, economies of scale, and market power. [ABSTRACT FROM AUTHOR]

The article discusses the origin and development of hydraulic power equipment and systems in Great Britain and Australia. It discusses the formation of the Melbourne Hydraulic Power Co., a public utility company, in 1888 and also states its early success and competition faced by the company from electricity distributors. It also states the acquisition of the company through legislation by the Melbourne City Council, a City Corporation. The customer base of the company is also discussed.

Load forecasting is of crucial importance for operations of electric power systems. In recent years, deep learning based methods are emerging for load forecasting because their strong nonlinear approximation capabilities can provide more forecasting precision than conventional statistical methods. However, they usually suffer from some problems, e.g., the gradient vanishment and over-fitting. In order to address these problems, an unshared convolution based deep learning model with densely connected network is proposed. In this model, the backbone is the unshared convolutional neural network and a densely connected structure is adopted, which could alleviate the gradient vanishment. What is more, we use a regularization method named clipped $L_2$ -norm to overcome over-fitting, and design a trend decomposition strategy to address the possible distribution differences between the training and validation data. Finally, we conduct five case studies to verify the outperformance of our proposed deep learning model for deterministic and interval load forecasting. Two high-voltage and an medium-voltage real load datasets from Australia, Germany and America are used for model training and validation, respectively. Results show that the proposed model can achieve higher load forecasting accuracy, compared with other existing methods including the popular conventional methods such as naive forecast and generalized additive model, and deep learning methods, e.g., long short-term memory network, convolutional neural network, fully connected network, etc. [ABSTRACT FROM AUTHOR]

The large-scale integration of wind power into electrical power systems is likely to require significant improvements to transmission infrastructure over coming years. Planning for these developments may involve modeling of power systems using estimates of the time-varying power output of proposed wind farms. Such estimates may be derived from wind measurements, although it is rarely the case that measurements are available simultaneously for all sites of interest. In the present work, a method is developed to produce synthetic time-series of wind power at several locations based on a measured time-series of wind speed from a reference site. The stochastic properties of the modeled time-series are shown to be comparable with those of measured data from south-eastern Australia. It is anticipated that with appropriate tuning for local conditions, the method could be applied in other geographical regions. [ABSTRACT FROM PUBLISHER]