Demand response (DR), which is the action voluntarily taken by a consumer to adjust amount or timing of its energy consumption, has an important role in improving energy efficiency. With DR, we can ...shift electrical load from peak demand time to other periods based on changes in price signal. At residential level, automated energy management systems (EMS) have been developed to assist users in responding to price changes in dynamic pricing systems. In this paper, a new intelligent EMS (iEMS) in a smart house is presented. It consists of two parts: a fuzzy subsystem and an intelligent lookup table. The fuzzy subsystem is based on its fuzzy rules and inputs that produce the proper output for the intelligent lookup table. The second part, whose core is a new model of an associative neural network, is able to map inputs to desired outputs. The structure of the associative neural network is presented and discussed. The intelligent lookup table takes three types of inputs that come from the fuzzy subsystem, outside sensors, and feedback outputs. Whatever is trained in this lookup table are different scenarios in different conditions. This system is able to find the best energy-efficiency scenario in different situations.
By using Demand Side Management (DSM) we can shift electrical load from peak demand time to other periods. An automated Intelligent Energy Management System (iEMS) was developed in this research ...where building energy consumption is modified in a dynamic setting. The system is able to not only manage renewable energy resources but also to consider users' preferences and behaviors. In addition, it finds optimal energy scheduling according to the dynamic notion of price. A new topology of neural network is introduced and acts as an associative memory with a crystal type structure, which can be modified easily. Two models for an automated iEMS in residential level are presented. The proposed systems have two subsystems: fuzzy subsystem and an intelligent lookup table. The best energy-efficiency scenarios in different situations can be automatically found. A combined enhanced model was developed. The actual potential of intelligent automated decisions in a residential home is demonstrated by coupling iEMS with Gridlab-D (a U.S. Department of Energy funded software). The iEMS program is able to regulate the energy consumption of appliances based on the different situations and rule scenarios. Typical home appliances (such as water heater, air conditioner, light, solar panel, battery storage, refrigerator, freezer, dishwasher, washer and dryer) are simulated in GridLab-D and their energy consumption, cost and representative savings are illustrated when the iEMS is implemented. Because of different weather conditions and configurations of residential homes across the United States, four (4) cities were chosen to represent the U.S Climate in the north, south, east and west (Madison, San Antonio, New York City and San Diego, respectively). This was also done at different times of the year (January and August) for one week to consider seasonal changes. Our findings show that savings in the order of 15-30% can be achieved when an intelligent Energy Management System ( iEMS) is used with controllable appliances.
