Algorithmic Bidding for Virtual Trading in Electricity Markets

We consider the problem of optimal bidding for virtual trading in two-settlement electricity markets. A virtual trader aims to arbitrage on differences between day-ahead and real-time market prices that are random and unknown to market participants. An online learning algorithm is proposed to maximize the cumulative payoff over a finite number of trading sessions by allocating the trader's budget among his bids for $K$ options in each session. It is shown that the expected payoff of the proposed algorithm converges, with an almost optimal convergence rate, to the expected payoff of the global optimal corresponding to the case when the underlying price distribution is known. The proposed algorithm is also generalized for trading strategies with a risk measure. By using both cumulative payoff and Sharpe ratio as performance metrics, evaluations were performed based on the historical data spanning ten year period of NYISO and PJM markets. It was shown that the proposed strategy outperforms standard benchmarks and the S&P 500 index over the same period.

[1]  Kameshwar Poolla,et al.  Virtual Bidding: Equilibrium, Learning, and the Wisdom of Crowds* , 2017 .

[2]  Colin McDiarmid,et al.  Surveys in Combinatorics, 1989: On the method of bounded differences , 1989 .

[3]  Aleksandrs Slivkins,et al.  Sharp dichotomies for regret minimization in metric spaces , 2009, SODA '10.

[4]  Chi-Keung Woo,et al.  Virtual Bidding, Wind Generation and California's Day-Ahead Electricity Forward Premium , 2015 .

[5]  Alexandre B. Tsybakov.  Lower bounds on the minimax risk , 2009 .

[6]  William W. Hogan,et al.  Virtual bidding and electricity market design , 2016 .

[7]  G. Gross,et al.  On the Economics of Power System Security in Multi-Settlement Electricity Markets , 2010, IEEE Transactions on Power Systems.

[8]  Vladimir Vapnik,et al.  Principles of Risk Minimization for Learning Theory , 1991, NIPS.

[9]  John R. Birge,et al.  Limits to arbitrage in electricity markets: A case study of MISO , 2018, Energy Economics.

[10]  Akshaya Jha,et al.  Testing for Market Eciency with Transactions Costs: An Application to Convergence Bidding in Wholesale Electricity Markets , 2013 .

[11]  Peter Auer,et al.  The Nonstochastic Multiarmed Bandit Problem , 2002, SIAM J. Comput..

[12]  Erin Mastrangelo,et al.  Financial Arbitrage and Efficient Dispatch in Wholesale Electricity Markets , 2015 .

[13]  Celeste Saravia.  Speculative Trading and Market Performance: The Effect of Arbitrageurs on Efficiency and Market Power in the New York Electricity Market , 2003 .

[14]  K. Dudzinski,et al.  Exact methods for the knapsack problem and its generalizations , 1987 .

[15]  Pravin Varaiya,et al.  Impact of virtual bidding on financial and economic efficiency of 1 wholesale electricity markets , 2017 .

[16]  Shmuel S. Oren,et al.  Efficiency impact of convergence bidding in the california electricity market , 2015 .

[17]  Christopher R. Knittel,et al.  Inefficiencies and Market Power in Financial Arbitrage: A Study of California's Electricity Markets , 2004 .

[18]  T. Ibaraki,et al.  THE MULTIPLE-CHOICE KNAPSACK PROBLEM , 1978 .

[19]  Vianney Perchet,et al.  Online learning in repeated auctions , 2015, COLT.

[20]  Pravin Varaiya,et al.  Model and data analysis of two-settlement electricity market with virtual bidding , 2016, 2016 IEEE 55th Conference on Decision and Control (CDC).