In industrial and commercial sectors, numerous countries had successfully implemented the dynamic pricing as a solution to the problem of high power demand in peak hours. But, an extensive use of real-time pricing in the residential electricity sector is hugely missing. In order to boost the efficiency of electricity market by demand response, real-time pricing needs to be implemented into residential sector also. In this paper the proposed algorithm is implemented for residential consumers of different categories with real time pricing data of ComEd, Northern Illinois Power Company, and Alactra Utilities Corporation. The proposed algorithm incorporates single interval and multi interval programming for different power pricing schemes. The proposed algorithm is suggested using metaheuristic optimization techniques viz. cuckoo search (CS), adaptive cuckoo search (ACS) and Hybrid GA–PSO for the optimum scheduling of residential appliances. The objective of this paper is to minimize the monthly electricity bill cost as well as peak demand under uncertain electricity prices. The comparative analysis of optimal solutions obtained by various artificial intelligence techniques validates the high performance of proposed algorithm. It facilitates both the residential consumer and utilities with benefits.

在工商业领域，许多国家已经成功地实施了动态定价，以解决高峰时段的高电力需求问题。但是，在住宅电力部门中广泛使用实时定价的情况非常少。为了通过需求响应提高电力市场的效率，实时定价也需要在住宅领域实施。在本文中，所提出的算法是针对不同类别的住宅消费者实施的，具有 ComEd、北伊利诺伊州电力公司和 Alactra 公用事业公司的实时定价数据。所提出的算法结合了针对不同电力定价方案的单区间和多区间编程。建议的算法使用元启发式优化技术，即。布谷鸟搜索（CS），自适应布谷鸟搜索 (ACS) 和混合 GA-PSO，用于优化家用电器的调度。本文的目标是在不确定的电价下最小化每月的电费成本以及峰值需求。对各种人工智能技术得到的最优解进行对比分析，验证了所提算法的高性能。它为住宅消费者和公用事业提供了便利。