Ma Hongyan
School of Humanities and Social Sciences, Xi'an Jiaotong University, Xi'an, Shaanxi Province, 710049, China.
School of Business, Xi'an Fanyi University, Xi'an, Shaanxi Province, 710105, China.
PLoS One. 2021 Mar 11;16(3):e0246718. doi: 10.1371/journal.pone.0246718. eCollection 2021.
The purposes are to evaluate the Distributed Clustering Algorithm (DCA) applicability in the power system's big data processing and find the information economic dispatch strategy suitable for new energy consumption in power systems. A two-layer DCA algorithm is proposed based on K-Means Clustering (KMC) and Affinity Propagation (AP) clustering algorithms. Then the incentive Demand Response (DR) is introduced, and the DR flexibility of the user side is analyzed. Finally, the day-ahead dispatch and real-time dispatch schemes are combined, and a multi-period information economic dispatch model is constructed. The algorithm performance is analyzed according to case analyses of new energy consumption. Results demonstrate that the two-layer DCA's calculation time is 5.23s only, the number of iterations is small, and the classification accuracy rate reaches 0.991. Case 2 corresponding to the proposed model can consume the new energy, and the income of the aggregator can be maximized. In short, the multi-period information economic dispatch model can consume the new energy and meet the DR of the user side.
目的是评估分布式聚类算法（DCA）在电力系统大数据处理中的适用性，并找到适合电力系统新能源消纳的信息经济调度策略。提出了一种基于K均值聚类（KMC）和亲和传播（AP）聚类算法的两层DCA算法。然后引入激励需求响应（DR），并分析用户侧的DR灵活性。最后，结合日前调度和实时调度方案，构建了多周期信息经济调度模型。根据新能源消纳的案例分析对算法性能进行了分析。结果表明，两层DCA的计算时间仅为5.23秒，迭代次数少，分类准确率达到0.991。所提模型对应的案例2能够消纳新能源，且聚合商的收益可最大化。简而言之，多周期信息经济调度模型能够消纳新能源并满足用户侧的DR。
