Search

Energy forecasting plays a vital role in mitigating challenges in data rich smart grid (SG) systems involving various applications such as demand‐side management, load shedding, and optimum dispatch. Managing efficient forecasting while ensuring the least possible prediction error is one of the main challenges posed in the grid today, considering the uncertainty in SG data. This paper presents a comprehensive and application‐oriented review of state‐of‐the‐art forecasting methods for SG systems along with recent developments in probabilistic deep learning (PDL). Traditional point forecasting methods including statistical, machine learning (ML), and deep learning (DL) are extensively investigated in terms of their applicability to energy forecasting. In addition, the significance of hybrid and data pre‐processing techniques to support forecasting performance is also studied. A comparative case study using the Victorian electricity consumption in Australia and American electric power (AEP) datasets is conducted to analyze the performance of deterministic and probabilistic forecasting methods. The analysis demonstrates higher efficacy of DL methods with appropriate hyper‐parameter tuning when sample sizes are larger and involve nonlinear patterns. Furthermore, PDL methods are found to achieve at least 60% lower prediction errors in comparison to other benchmark DL methods. However, the execution time increases significantly for PDL methods due to large sample space and a tradeoff between computational performance and forecasting accuracy needs to be maintained. [ABSTRACT FROM AUTHOR]

In Australia and many other countries, distribution network service providers (DNSPs) have an obligation to their customers to provide electrical power that is reliable and of high quality. Failure to do so may have significant implications ranging from financial penalties theoretically through to the loss of a license to distribute electricity. In order to ensure the reliability and quality of supply are met, DNSPs engage in monitoring and reporting practice. This paper provides an overview of a large long-running power-quality monitoring project that has involved most of Australia's DNSPs at one time or another. This paper describes the challenges associated with conducting the project as well as some of the important outcomes and lessons learned. A number of novel reporting techniques that have been developed as part of the monitoring project are also presented. A discussion about large-volume data management, and issues related to reporting requirements in future distribution networks is included. [ABSTRACT FROM PUBLISHER]

Voltage dips are considered to be one of the costliest of all power quality disturbances due to their disruption of industrial and commercial operations. The ability to characterise the voltage dip performance of distribution networks has many benefits for industry. There is considerable potential for industry to make large economic gains if voltage dip behaviour can be better understood and planned for. To put strategies in place to deal with voltage dips, there is a need for extensive data collection and analysis so that correct planning decisions can be made. This study details the characteristics of voltage dip data which has been collected at low-voltage sites in Australia over a 9 year period. The data is displayed in a number of different formats to aid analysis. [ABSTRACT FROM AUTHOR]

The assumption of expected profit-maximizing bidding behavior in a multi-unit, multi-period auction with step-function supply curves is used to estimate cost functions for electricity generation units and derive tests of expected profit-maximizing behavior. Applying these techniques to data from the National Electricity Market in Australia reveals statistically significant evidence of output-dependent marginal costs within and across half-hours of the day, but no evidence against the hypothesis of expected profit-maximizing behavior. These cost function estimates quantify the economic significance of output-varying costs and how forward financial contract obligations impact the amount of these costs the generation unit owner incurs. This supplier's existing obligations imply average daily production costs that are 8% lower than the profit-maximizing pattern of output with no forward contract obligations. Copyright © 2007 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Investigates the divergence between electricity generation costs using current market prices of coal and natural gas in Australia. Application of the concept of full cost pricing to five different generation technologies in the electricity sector; Role of efforts to privatization and interconnection in promoting pricing closer to marginal private costs.