Building Marginal Pattern Library With Unbiased Training Dataset for Enhancing Model-Free Load-ED Mapping

Abstract

Input-output mapping for a given power system problem, such as loads versus economic dispatch (ED) results, has been demonstrated to be learnable through artificial intelligence (AI) techniques, including neural networks. However, the process of identifying and constructing a comprehensive dataset for the training of such input-output mapping remains a challenge to be solved. Conventionally, load samples are generated by a predefined distribution, and then ED is solved based on those load samples to form training datasets, but this paper demonstrates that such dataset generation is biased regarding load-ED mapping. The marginal unit and line congestion (i.e., marginal pattern) exhibit a unique characteristic called "step change" in which the marginal pattern changes when the load goes from one critical loading level (CLL) to another, and there is no change of marginal units within the interval of the two adjacent CLLs. Those loading intervals differ significantly in size. The randomly generated training dataset overfills intervals with large sizes and underfits intervals with small sizes, so it is biased. In this paper, three algorithms are proposed to construct a marginal pattern library to examine this bias according to different computational needs, and an enhancement algorithm is proposed to eliminate the bias for the load-ED dataset generation. Three illustrative test cases demonstrate the proposed algorithms, and comparative studies are constructed to show the superiority of the enhanced, unbiased dataset.

Coupling Analysis for Multienergy Systems by Self and Cross Critical Load Level

“…In the wholesale electricity market, LMPs are calculated to settle the payments of participants. For the MES model, a similar process has been considered to clear the market by applying the LMP at each energy network, such as in [17], [19], and [27]. Following the formulation of the electricity LMP as shown in (1), the LMPs of heat and gas are shown in ( 2) and (3).…”

“…The electricity LMP experiences step changes over the increasing electric loading level under the same load participating factor. The concept of CLL has been widely analyzed and applied by various research works, such as efficient CLL estimations [22] and new pricing schemes [27]. The phenomenon of CLL also exists in the electricity-heat-gas MES model, as analyzed in Property 6.…”