Australian Electricity Market Research Articles

Hybrid Empirical Mode Decomposition with Support Vector Regression Model for Short Term Load Forecasting

For operational management of power plants, it is desirable to possess more precise short-term load forecasting results to guarantee the power supply and load dispatch. The empirical mode decomposition (EMD) method and the particle swarm optimization (PSO) algorithm have been successfully hybridized with the support vector regression (SVR) to produce satisfactory forecasting performance in previous studies. Decomposed intrinsic mode functions (IMFs), could be further defined as three items: item A contains the random term and the middle term; item B contains the middle term and the trend (residual) term, and item C contains the middle terms only, where the random term represents the high-frequency part of the electric load data, the middle term represents the multiple-frequency part, and the trend term represents the low-frequency part. These three items would be modeled separately by the SVR-PSO model, and the final forecasting results could be calculated as A+B-C (the defined item D). Consequently, this paper proposes a novel electric load forecasting model, namely H-EMD-SVR-PSO model, by hybridizing these three defined items to improve the forecasting accuracy. Based on electric load data from the Australian electricity market, the experimental results demonstrate that the proposed H-EMD-SVR-PSO model receives more satisfied forecasting performance than other compared models.

Decoding the Australian electricity market: New evidence from three-regime hidden semi-Markov model

The hidden semi-Markov model (HSMM) is more flexible than the hidden Markov model (HMM). As an extension of the HMM, the sojourn time distribution in the HSMM can be explicitly specified by any distribution, either nonparametric or parametric, facilitating the modelling for the stylised features of electricity prices, such as the short-lived spike and the time-varying mean. By using a three-regime HSMM, this paper investigates the hidden regimes in five Australian States (Queensland, New South Wales, Victoria, South Australia, and Tasmania), spanning the period from June 8, 2008 to July 3, 2016. Based on the estimation results, we find evidence that the three hidden regimes correspond to a low-price regime, a high-price regime, and a spike regime. Running the decoding algorithm, the analysis systemically finds the timing of the three regimes, and thus, we link the empirical results to the policy changes in the Australian National Electricity Market. We further discuss the contributing factors for the different characteristics of the Australian electricity markets at the state-level.

Issues and mitigations of\xa0wind energy penetrated network: Australian network case study

Longest geographically connected Australian power system is undergoing an unprecedented transition, under the effect of increased integration of renewable energy systems. This change in generation mix has implications for the whole interconnected system designs, its operational strategies and the regulatory framework. Frequency control policies about real-time balancing of demand and supply is one of the prominent and priority operational challenge requiring urgent attention. This paper reviews the Australian electricity market structure in presence of wind energy and its governance. Various issues related to increased wind generation systems integration are discussed in detail. Currently applied mitigations along with prospective mitigation methods requiring new or improved policies are also discussed. It is concluded that developing prospective frequency regulation ancillary services market desires further encouraging policies from governing authority to keep pace with current grid transition and maintain its security.

Generalized FDIA-Based Cyber Topology Attack With Application to the Australian Electricity Market Trading Mechanism

This paper proposes a generalized false data injection attack-based cyber topology attack capable of disturbing conventional transactions in the electricity market. The proposed attack aims to mislead customers pay higher electricity bills in the wholesale market by making small, undetected price deviations during each attack interval over an extended period. In this paper, the Australian electricity market trading mechanism is considered, in which an extended attack over a single day is proposed, spanning totally 288 5-minute dispatch (attack) intervals. The proposed attack poses no security threat to the power system, affecting only the economic costs borne by customers. A defining feature of the proposed model is the joint consideration of both topology error processing and bad data detection constraints in order to ensure validity of the proposed attack. The rolling horizon optimization technique is used to make appropriate adjustment to the attacker’s strategy considering the practical operating condition. A new metaheuristic optimization algorithm previously proposed by the authors, Natural aggregation algorithm, is used to find the corresponding attack strategies in this paper. Case studies on the IEEE-118 benchmark system are conducted to validate the proposed attack methodology.

Wind Power Development and Energy Storage under China’s Electricity Market Reform—A Case Study of Fujian Province

This paper, based on the Fujian provincial 500 kV grid and part of the 220 kV grid and the key power plants, including hydro, coal, nuclear, gas, wind and pumping and storage hydro powers (PSHP) connected to the grid, constructs an independent electricity market model. Using data that are very close to reality about coal fired power production costs, along with data about power plants’ technical constraints, this paper studies the effect of wind power on Fujian’s provincial electricity market. Firstly, the paper analyzes the relationship between wind speed and wind power output and the effects of short-term power output fluctuation on frequency modulation and voltage regulation. Secondly, under supposition of the production costs following quadratic functions, the paper analyzes the effects of changes in wind power output on the electricity supply costs under optimal power flow. Thirdly, using the bidding model in the Australian Electricity Market Operator for reference and supposing that, in a competitive market, coal fired power plants can bid 6 price bands according to their capacity, the paper analyzes effects of wind power on electricity prices under optimal power flow, the stabilizing effects of PSHP and the minimum PSHP capacity needed to stabilize the electricity market. Finally, using a daily load curve, this paper simulates the electricity prices’ fluctuation under optimal power flow and PSHP’s stabilizing effect. The results show that, although PSHP has a large external social welfare effect, it can hardly make a profit. In the end, this paper puts forward some policy suggestions for Fujian province’s wind and nuclear power development, PSHP construction and electricity market development.

Applications of Hybrid EMD with PSO and GA for an SVR-Based Load Forecasting Model

Providing accurate load forecasting plays an important role for effective management operations of a power utility. When considering the superiority of support vector regression (SVR) in terms of non-linear optimization, this paper proposes a novel SVR-based load forecasting model, namely EMD-PSO-GA-SVR, by hybridizing the empirical mode decomposition (EMD) with two evolutionary algorithms, i.e., particle swarm optimization (PSO) and the genetic algorithm (GA). The EMD approach is applied to decompose the load data pattern into sequent elements, with higher and lower frequencies. The PSO, with global optimizing ability, is employed to determine the three parameters of a SVR model with higher frequencies. On the contrary, for lower frequencies, the GA, which is based on evolutionary rules of selection and crossover, is used to select suitable values of the three parameters. Finally, the load data collected from the New York Independent System Operator (NYISO) in the United States of America (USA) and the New South Wales (NSW) in the Australian electricity market are used to construct the proposed model and to compare the performances among different competitive forecasting models. The experimental results demonstrate the superiority of the proposed model that it can provide more accurate forecasting results and the interpretability than others.

An Ensemble Model Based on Machine Learning Methods and Data Preprocessing for Short-Term Electric Load Forecasting

The experience with deregulated electricity market has shown the increasingly important role of short-term electric load forecasting in the energy producing and scheduling. However, because of nonlinear, stochastic and nonstable characteristics associated with the electric load series, it is extremely difficult to precisely forecast the electric load. This paper aims to establish a novel ensemble model based on variational mode decomposition (VMD) and extreme learning machine (ELM) optimized by differential evolution (DE) algorithm for multi-step ahead electric load forecasting. The proposed model is novel in the sense that VMD is firstly applied to decompose the original electric load series into a set of components with different frequencies in order to effectively eliminate the stochastic fluctuation characteristic so as to improve the overall prediction accuracy. The proposed ensemble model is tested using two electric load series collected from New South Wales (NSW) and Queensland (QLD) in the Australian electricity market. The experimental results show that: (1) the data preprocessing by VMD can effectively decrease the stochastic fluctuation characteristics that existed in the electric load series, consequently improving the whole forecasting accuracy, and; (2) the proposed forecasting model performs better than all other benchmark models for both one-step and multi-step ahead electric load forecasting.

An optimal collaborative congestion management in national grid based on implementing demand response

This paper aims to provide a novel framework for optimal congestion management via encouraging a collaboration between the independent system operator (ISO) and Retail electricity companies (Recos) in implementing demand response (DR) programs based on the market mechanism. The merit of this paper is to increase the market efficiency. Three economic signals, namely, demand reduction, congestion elasticity, and electricity spot price values, specified by the ISO, are used for assisting Recos in evaluating any benefits from implementing DR in various network buses. A Stackelberg game is adopted for designing a DR trade between Recos and demand response aggregators to help Recos identifying their optimal demands in the market, which are then used by the ISO to analyze grid congestion and consequently to re-specify the new economic signals. The game is repeated until the Nash equilibrium point, the optimal congestion reduction, and the optimal Recos' demands are obtained. The performance of the proposed framework is assessed using a test power system, and the results are compared with the current practices in the Australian electricity market. This paper demonstrates an effective performance of the proposed framework.

Assessment of Market Participation Opportunities for Behind-the-meter PV/ Battery Systems in the Australian Electricity Market

Abstract We analyze the potential benefits for behind-the-meter PV/battery systems of wholesale energy market participation in the Australian energy market. Using historic energy market price and demand data we show that PV / battery systems have the potential for significant financial benefit if operated so as to export during periods of peak wholesale pricing. The annual cost advantage over simple retail tariff optimization based operation, which is shared between electricity retailer and battery owner,varies considerably between regions and from year to year. No clear trends are evident over the last 10 years. We show that South Australia and Queensland are the most attractive markets for wholesale market participation. A 3 kW / 6 kWh behind-the-meter battery system, operated under reasonable and practical assumptions would have yielded around $80 per year on average over the most recent 5 years, or up to $150 per year if perfect look-ahead operationcould be achieved. The same battery system operating in Victoria or New South Wales, where price volatility is considerably less pronounced, would have yielded around $30 per year (up to only $40 per year with perfect look-ahead operation), while in Tasmania this would have been less than $10 per year. Weexplore a simple benefit sharing arrangement between battery owner and electricity retailer, using a pre-defined fixed price paid by retailers to battery owners for any exports occurring during periods of high markets prices. We find that a payment price (and accompanying export threshold) of $1.50 per kWh typically results in an even sharing of benefits. Finally, we speculate on the medium term outlook for battery system wholesale market participation, confirming the intuition that a high degree of participation is likely to result in the desired impact of ‘flattening’ the market and suppressing further market opportunity.

Short term electricity price forecast based on environmentally adapted generalized neuron

The liberalization of the power markets gained a remarkable momentum in the context of trading electricity as a commodity. With the upsurge in restructuring of the power markets, electricity price plays a dominant role in the current deregulated market scenario which is majorly influenced by the economics being governed. In the deregulated environment price forecasting is an important aspect for the power system planning. The problem of price forecasting can be entirely viewed as a signal processing problem with proper estimation of model parameters, modeling of uncertainties, etc. Among the different existing models the artificial neural network based models have gained wide popularity due their black box structure but it too has its own limitations. In the proposed work in order to overcome the limitations of the classical artificial neural network model, generalized neuron model is used for forecasting the short term electricity price of Australian electricity market. The pre-processing of the input parameters is accomplished using wavelet transform for better representation of the low and high frequency components. The free parameters of the generalized neuron model are tuned using environment adaptation method algorithm for increasing the generalization ability and efficacy of the model.

Simultaneous Electricity Price and Demand Forecasting in Smart Grids

Today's competitive world and economy is heavily dependent on electrical energy. Since electricity cannot be stored and producing more or less than the required needs may lead to some losses. The electric charge forecasting and pricing are considered as the main factors in planning and decision-making for future development plans and operation of power systems. In the future smart grids, electricity consumers will be able to react to changes in electricity prices. The total response of consumers to price could potentially shift the demand curve in the market. As a result, prices may vary from original projections. In this paper, a forecasting framework is proposed that offers such dynamics in predicting the electricity price demand. In this framework, a mechanism based on principles of data mining data mining to determine the patterns in response to changes in consumer demand and prices are used. In this model, the weather conditions (temperature and humidity), the days and special holidays are considered. And the results are expected to be done hourly, daily. Simulation results of the proposed method for forecasting demand and prices, which were obtained using the Australian electricity market, indicates that error is less compared to the previous methods.

Structural breaks and electricity prices: Further evidence on the role of climate policy uncertainties in the Australian electricity market

The primary objectives and the strategies of a national electricity market are the efficient delivery of network services and the electricity infrastructure to meet the long-term consumer's interests. Therefore, the objective of this study is to explore whether electricity prices across the six Australian States display instability. Such instability is closely associated with the presence of structural breaks in relevance to policy events on Australian carbon policies. The study makes use of weekly Australian wholesale electricity prices spanning the period from June 8th, 2008 to March 30th, 2014 along with linear and non-linear unit root testing methodologies. The results provide supportive evidence that the Australian electricity market can be described as a less stable electricity market, which implies that a high degree of market power is exercised by generators across regional markets. These findings are expected to have substantial consequences for the effectiveness of carbon dioxide mitigating policies, especially, when there is uncertainty as to whether the planned environmental policy is put in place for the lifespan of undertaken investments.

Game-Theoretic Frameworks for Demand Response in Electricity Markets

This paper presents game-theoretic frameworks for demand response at both electricity market and consumer levels. First, the interaction between a demand response aggregator (DRA) and electricity generators is modeled as a Stackelberg game in which the DRA, as the leader of the game, makes demand reduction bids, and generators, as followers, compete for maximizing their profits based on the reduced demand. Next, the interaction between the DRA and consumers is modeled as a mechanism design problem wherein the DRA seeks to minimize the aggregate inconvenience of consumers while achieving the targeted load curtailment. The inconvenience function of each consumer is captured by a type value, which is used by the DRA to solve the load curtailment problem. A Vickrey-Clarke-Groves-based mechanism is proposed, which guarantees that each consumer reveals its true type value to the DRA. A case study of the Stackelberg game shows that, in the South Australian electricity market where there is significant renewable penetration, peak period demand response provides the maximum potential profit, but off-peak demand response even in a concentrated market is not financially attractive.

Electricity price forecasts using a Curvelet denoising based approach

Price movement in the electricity market can be viewed as a nonlinear and dynamic system, exhibiting significant chaotic and multiscale characteristics. To conduct more accurate analysis and forecasting, this paper proposes a new Curvelet denoising based algorithm to analyze these characteristics and predict its future movement. We project the original electricity price into its time delay embedding domain to reveal its chaotic characteristics. The Curvelet denoising method is introduced to separate and suppress the noise disruptions in the transformed phase space. Empirical studies using the typical Australian electricity market prices data show that the proposed algorithm demonstrates more robust and superior performance than the traditional benchmark models.

Copula modelling of dependence in multivariate time series

Almost all existing nonlinear multivariate time series models remain linear, conditional on a point in time or latent regime. Here, an alternative is proposed, where nonlinear serial and cross-sectional dependence is captured by a copula model. The copula defines a multivariate time series on the unit cube. A drawable vine copula is employed, along with a factorization which allows the marginal and transitional densities of the time series to be expressed analytically. The factorization also provides for simple conditions under which the series is stationary and/or Markov, as well as being parsimonious. A parallel algorithm for computing the likelihood is proposed, along with a Bayesian approach for computing inference based on model averages over parsimonious representations of the vine copula. The model average estimates are shown to be more accurate in a simulation study. Two five-dimensional time series from the Australian electricity market are examined. In both examples, the fitted copula captures a substantial level of asymmetric tail dependence, both over time and between elements in the series.

Models for short-term forecasting of spike occurrences in Australian electricity markets: a comparative study

Understanding the dynamics of extreme observations, so called spikes, in real-time electricity prices has a crucial role in risk-management and trading. Yet the contemporaneous literature appears to be at the beginning of understanding the dierent mechanisms that drive spike probabilities. We reconsider the problem of short-term, i.e., half hourly, forecasts of spike occurrence in the Australian electricity market and develop models, tailored to capture the data properties. These models are variations of a dynamic binary response model, extended to allow for regime specic eects and an asymmetric link function. Furthermore, we study a recently proposed approach based on the autoregressive conditional hazard model. The proposed models use load forecasts and lagged log-prices as exogenous variables. Our in- and out-of-sample results suggest that some specications dominate and can therefore be recommended for the problem of spike forecasting.

A Hybrid Approach for Probabilistic Forecasting of Electricity Price

The electricity market plays a key role in realizing the economic prophecy of smart grids. Accurate and reliable electricity market price forecasting is essential to facilitate various decision making activities of market participants in the future smart grid environment. However, due to the nonstationarities involved in market clearing prices (MCPs), it is rather difficult to accurately predict MCPs in advance. The challenge is getting intensified as more and more renewable energy and other new technologies emerged in smart grids. Therefore transformation from traditional point forecasts to probabilistic interval forecasts can be of great importance to quantify the uncertainties of potential forecasts, thus effectively supporting the decision making activities against uncertainties and risks ahead. This paper proposes a hybrid approach to construct prediction intervals of MCPs with a two-stage formulation. In the first stage, extreme learning machine (ELM) is applied to estimate point forecasts of MCPs and model uncertainties involved. In the second stage, the maximum likelihood method is used to estimate the noise variance. A generalized and comprehensive evaluation framework for probabilistic electricity price forecasting is proposed in this paper. The effectiveness of the proposed hybrid method has been validated through comprehensive tests using real price data from Australian electricity market.

Modeling Dependence of Price Spikes in Australian Electricity Markets

Price spikes are of particular importance due to their severe impacts on consumers, businesses and industry. They constitute a major source of price risk to market participants, e.g., electricity retailers with commitments to meet customers' daily electricity demands. To those trading in several electricity markets simultaneously, the probability of simultaneous price spikes termed as tail dependence is of great importance when computing risks. For this purpose, the problem of modeling joint price spikes in the Australian electricity market is considered. A common measure of tail dependence measure is the so-called tail dependence coefficient (TDC). We present a nonparametric estimator of the tail dependence and further, the point estimation is complemented with an hypotheses test. We find significant tail dependence in electricity prices that cannot be ignored. Accurate characterization of this tail dependence is important for a variety of risk management purposes. These include hedging activities of market participants.

Improving Wind Farm Dispatch in the Australian Electricity Market With Battery Energy Storage Using Model Predictive Control

This paper presents a novel wind farm dispatch control scheme by integrating a battery energy storage system (BESS) to manage the amount of net energy generation sold to the electricity market. The scheme is based on model predictive control to ensure the optimal operation of BESS in the presence of practical system constraints. The proposed scheme follows a decision policy to efficiently sell more energy at peak demand/price times and store it at off-peak periods in compliance with the electricity rules of the Australian National Electricity Market. The performance of the proposed control scheme is assessed under different scenarios in terms of a key performance index and earning comparison from power sale using actual wind farm and electricity price data.

A System and Method for Electricity Price Forecasting with a Novel Forecast Error Correction

This technical article presents the concepts for improving the electricity price forecasting which were patented (application no. IN236/MUM/2011). A novel system and method for electricity price forecasting are also disclosed to set the context for explaining the technicalities involved in the invention. The invention relates to forecasting, and particularly to price forecasting by employing error correction techniques external to the algorithm chosen to solve the forecasting problem. Existing mechanisms do not offer effective error correction mechanisms external to the forecasting engine. The proposed technique uses the stochastic formulations and golden search methods to improve the final forecast. The method initially employs a forecasting module which consists of SVM, robust regressions, and neural network based mechanisms to determine the initial forecasts. In case there is an error, it determines if the error is within the permissible values through various probability checks. Further, if the error is outside the permissible values then a correction factor is applied to the computed values and prediction is updated. The correction factor is determined using the golden search technique. The framework for the proposed approach has been tested on the Indian and Australian electricity market data to prove its efficacy. Keywords: Electricity Price Forecasting, error Correction, golden Search, wholesale Electricity Market