Question

What is the explanation of Energy Management and the function of Energy Management System in Smart City?

Answer 1

Around the globe, innovation with integrating information and communication technologies (ICT) with physical infrastructure is a top priority for governments in pursuing smart, green living to improve energy efficiency, protect the environment, improve the quality of life, and bolster economy competitiveness. Cities today faces multifarious challenges, among which energy efficiency of homes and residential dwellings is a key requirement. Achieving it successfully with the help of intelligent sensors and contextual systems would help build smart cities of the future. In a Smart home environment Home Energy Management plays a critical role in finding a suitable and reliable solution to curtail the peak demand and achieve energy conservation. In this paper, a new method named as Home Energy Management as a Service (HEMaaS) is proposed which is based on neural network based Q-learning algorithm. Although several attempts have been made in the past to address similar problems, the models developed do not cater to maximize the user convenience and robustness of the system. In this paper, authors have proposed an advanced Neural Fitted Q-learning method which is self-learning and adaptive. The proposed method provides an agile, flexible and energy efficient decision making system for home energy management. A typical Canadian residential dwelling model has been used in this paper to test the proposed method. Based on analysis, it was found that the proposed method offers a fast and viable solution to reduce the demand and conserve energy during peak period. It also helps reducing the carbon footprint of residential dwellings. Once adopted, city blocks with significant residential dwellings can significantly reduce the total energy consumption by reducing or shifting their energy demand during peak period. This would definitely help local power distribution companies to optimize their resources and keep the tariff low due to curtailment of peak demand.

Smart cities in brief can be defined as a city which uses information and communication technologies (ICT) such as smart sensors, cognitive learning, and context awareness to make lives more comfortable, efficient, and sustainable. Cities today face multifarious challenges, including environmental sustainability, low carbon solutions and providing better services to their citizens. Given these trends, it is critical to understand how ICT can help make future cities more sustainable. As microcosms of the smart cities, smart and green buildings and homes stand to benefit the most from connecting people, process, data, and things. The Internet of Things (IoT) is a key enabler for smart cities, in which sensing devices and actuators are major components along with communication and network devices. Management of smart homes often requires analyzing IoT data from the interconnected networked devices to optimize efficiency, comfort, safety, and to make decisions faster and more precise. Internet of Things (IoT) is a decade-old term for the interconnection of a plethora of heterogeneous objects and things over a global network so that they can exchange data and interact in real-time. Technologies, such as radio frequency identification, wireless sensor networks, artificial intelligence and machine learning, form the backbone of such interactions. The telecommunications sector estimates that by 2020 more than a half billion devices will be connected with each other.

The significant efficiency gains from home automation can make cities sustainable in terms of resources. Importantly, the IoT ambitions and scope are designed to respond to the need for real-time, context-specific information intelligence and analytics to address specific local imperatives. Further, realization of smart, energy-efficient and green home infrastructure would allow the development of “livable” interconnected communities, which will form the backbone of a futuristic green city architecture. Hence, energy management in smart homes is a key aspect of building efficient smart cities. Energy management consists of demand side management (dsm), peak load reduction and reducing carbon emissions. In an industrialized country, residential and commercial loads in urban centers consume a significant amount of electrical energy. As per the survey report nearly 39–40% of the total energy consumption in Canada is consumed by the residential and commercial complexes. It is evident from various load surveys that the demand of electricity in these residences is highly variable and changes throughout the day. Therefore, finding suitable strategies for efficient management of home energy demand and to help reduce the energy consumption during peak period will make the communities’ more energy efficient. The Canada Green Building Council is working towards finding ways of making buildings greener and community sustainable. Therefore, the need for energy efficient buildings is growing rapidly.

The power systems require equilibrium between electricity generation and demand. Power system operators dispatch generating units primarily based on operating cost or market bid price. In order to meet the increased demand during peak period, more resources are often required to increase the generation capacity. Since addition of resources to meet the peak demand is an expensive investment, distribution system planners and utility engineers very often consider the reduction in peak load as a feasible solution to the problem. However, peak load reduction is mostly valuable for utilities and most popular only in a purely market-driven energy management environment. Under these circumstances, Demand Response (DR) offers an opportunity for consumers to play a significant role in the operation of the electric grid by reducing or shifting their electricity consumption during peak periods in response to time-based rates or other forms of financial incentives. In most of the cases, DR is a voluntary program that compensates the consumers. There are many modern methods that reduce the peak load and load at peak time which is referred as Demand Side Management (DSM). Current market framework and lack of experience and understanding of the nature of demand response are the most common challenges in DSM nowadays.

Newer technologies like energy management using smart meters are now becoming popular in places like Ontario, Canada where few utilities have introduced energy tariff based on the Time-Of-Use (TOU) model in which a consumer pays differently for the energy consumption at the different time of the day. This has been possible due to the implementation of smart meters which track the energy usage in a home on an hourly basis and then consumption information is bundled into multiple TOU price brackets. However, all these processes mostly help the local distribution company and in order to take advantages of the TOU, each household has to adopt a change in the use of the appliances which may cause significant discomfort to the consumers. In this scenario home appliance scheduling with electrical energy services for residential consumers is useful.

Recent developments in the area of information and communication technologies have provided an advanced technical foundation and reliable infrastructures for the smart house with a home energy management system. Development of low power, cost-efficient and high performance smart sensor technologies have provided us with the tools to build smart homes. As a result, a service platform can be implemented in a smart home to control the DR intelligently. This type of system should also give the users enough flexibility to input their choices while deciding on control of home devices This makes the system more coherent, user friendly and scalable. In this paper, a home energy management system named as Home Energy Management as a Service (HEMaaS) is proposed which provides intelligent decisions, is interactive with the environment, scalable and user friendly. Wi-Fi connected smart sensors with centralised decision-making mechanism can identify peak load conditions and employ the automatic switching to divert or reduce power demand during peak period, thereby reducing the energy consumption. While different hardware, software, communication architectures have been proposed and compared by their power consumption, performance, etc., the cost of implementing the infrastructure like: hardware devices, software framework, communication interfaces, etc. are still high enough that hinder the process of implementing the smart home technology for ordinary users. Moreover, the hardware and software architectures may not be able to handle the growing number of sensors and actuators with their heterogeneity. Therefore, by implementing monitoring and controlling sections of the HEMaaS platform using web services, one may achieve the agility, flexibility, scalability, and other features required for a feasible and affordable HEMaaS platform.

In this paper, peak reduction DR problem is formulated based on an agent-learning framework. Many authors have attempted to address this problem using multiple tools such as model predictive control, particle swarm optimization, iterative dynamic programming-based and gradient-based methods. However, these models are probabilistic and do not constitute learning from interaction with the environment. Further, these models are mostly price based, where cost saving instead of user preferences is a predominant factor. Some other solutions proposed in do consider Q-learning based agent interaction system, however they target only particular appliances like air conditioners and LED lights.

In, authors have proposed a fully-automated energy management system based on the classical Q-learning based Reinforcement Learning (RL). The modelling is delay based, where users have a way of inputting their energy requests via time-scheduling and the agent learns gradually with time to find the optimal solution. However, this approach has several limitations. The author assumes mathematical disutility fuction and consumer initiated energy usage. Finding disutility function for each home or residence is costly and difficult and too much user interaction is not desired for a interoperable energy management system. Reference focuses on applying a batch RL algorithm to control a cluster of electric water heaters. A more relevant work is reported in, which proposes device-based Markov Decision Process (MDP) models. It assumes that the user behaviour and grid control signals are known. However, these assumptions are not realistic in practice as described in this paper. This paper uses neural networks to learns this behaviour from historical data. In, authors use a discrete-time MDP based framework to facilitate the use of adaptive strategies to control a population of heterogenous thermostatically controlled loads to provide DR services to the power grid using Q-learning. Again the application here is specific to load controlled by ambient temperature.

In this paper, authors have used a typical canadian residential apartment to investigate the effectiveness of the proposed home energy management service. The main objective of HEMaaS is to shift and curtail household appliance usages so the peak demand and total energy consumption can be reduced. A new neural network based reinforcement learning algorithm has been proposed in this paper to achieve the objectives. The classical Q-learning problem of the reinforcement learning has been formulated as a neural fitted supervised learning problem here and is named Neural Fitted Q-based Home Energy Management (NFQbHEM) algorithm. This paper designs a node-red framework based user interface for controlling home appliance action based on NFQbHEM algorithm. The reward matrix incorporates user convenience parameters for state-action transition and includes user preference, power cost savings, robustness measure and user input preferences to initialize the algorithm. Peak demand reduction is of major goal of this paper maximizing user convenience. In summary the contributions of the paper are as follows:

• User interface: Using a node-red development framework (Node-RED is a web-based programming tool for wiring together hardware devices, APIs and online services.) and message queue telemetry protocol secure broker, a user interface has been designed. It incorporates intelligent energy management capability and provides user input options. Temperature control of appliances, operation rescheduling and On/Off commands are initiated through the interface.

• Peak demand reduction: Using the proposed HEMaaS methodology, a reward matrix is generated for each peak reduction threshold. There are four peak reduction thresholds considered in this paper: 5%, 10%, 15% and 20%. Based on the user convenience suitable load reduction decisions are obtained.

• Fault tolerance and user privacy: Taking different random combinations of robustness measure, it has been shown how the user convenience is affected when user privacy is compromised and system has hardware fault. This part of the results is specific to this paper and not shown anywhere in state-of-art literature.

• Energy saving and Carbon-footprint reduction: The energy savings and carbon emmission reduction has been shown for a community of 85 houses over a year.