论文部分内容阅读
采用迭代思想设计电力市场的竞价机制可以促进发电商之间的竞争,促使其调整成本,降低报价,提高电能交易效率,但其应用可能由于迭代时间太长而受到限制。为此,研究了如何利用动态市场信息来缩短迭代时间,建立了发电商在迭代竞价机制下的贝叶斯学习报价模型。以系统边际出清价格的分布区间为学习对象,发电商在每轮报价结束后,根据所获取的新交易信息修改其对系统边际出清价格分布区间的先验认识,不断缩小学习范围,以更精确的预期修改报价,从而减少不必要的时间浪费。结合算例证明,发电商运用贝叶斯学习结果进行报价可以有效减少迭代次数,缩短迭代时间,提高竞价效率。
The iterative design of bidding mechanism in the electricity market can promote the competition among generators, and make it adjust the cost, lower the quotation and improve the efficiency of electric energy transaction. However, its application may be limited due to too long iteration time. To this end, we study how to use the dynamic market information to shorten the iteration time, and establish a Bayesian learning quotation model under the iterative bidding mechanism. Taking the distribution range of the system margin clearing price as the learning object, the generator modifies the a priori knowledge of the distribution margin of the system marginal clearing price according to the new transaction information obtained after the end of each round of quotation, and continuously narrows the learning range More accurate expectation is to modify quotes, thereby reducing unnecessary waste of time. Combining with the examples, it is proved that using the Bayesian learning results to generate quotations can effectively reduce the number of iterations, shorten the iteration time and improve the bidding efficiency.