Conference Paper

Towards a Scalable Cloud Enabled Smart Home Automation Architecture for Demand Response

Authors:
To read the full-text of this research, you can request a copy directly from the authors.

Abstract

As smart homes and smart grids become ubiquitous their interactions will become crucial for optimizing energy consumption at large scale at residential level. Scalable solutions will be required to enable fast and reliable control during demand response. While management solutions have been proposed they do not focus on the scalability issues of the processing system. Handling continuous and variable Big Data streams can easily saturate existing systems. In this paper we propose a scalable cloud based architecture and prototype system for handling smart home data flows. The system can support near real time decisions for 10,000 customers each having 10 sensors with only 35 commodity machines running free cloud software. The platform is automated and can be used to directly control the customers’ smart home or to send recommendations. Some initial experiments are performed to show the benefits of smart recommendations.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

... Our use of open source is similar to the work proposed in [8], which makes use of Apache Storm. However, scalability is enabled with local logic. ...
... In [70], optimal energy demand data management for smart homes is studied. The system can support near real-time decisions for 10,000 customers, each of which has 10 sensors with only 35 basic machines running free software in the cloud. ...
Article
Full-text available
In this work, a systematic review of the literature has been carried out to analyse the design of intelligent networks in environments inhabited by people and the applications of sensors to improve quality of life and aid human activities. This study aims to answer three research questions. The first question is whether the design of smart grids is made with people in mind. The second question focuses on whether intelligent networks are being taken account of in the research on human activity recognition, the Internet of Things, and the recognition of activities of daily living. The third question looks at whether there are synergies and multidisciplinary teams studying state-of-the-art technologies applied to environments inhabited by elderly or disabled people. Installations with sensors deployed for the improvement of the quality of human life will also help to improve the quality of the intelligent network, thus integrating the Human–Technology binomial. This study concludes with an analysis of the results of the sources examined, putting forward a protocol of seven proposals to guide future work.
... According to [5], the typical electric utility/consumer model encapsulates the services of power planning, power transmission, power distribution, power management, home management and power demand. Demand Response (DR) is a popular technique used by utility providers for managing energy consumption during peak hours, by accounting for the power demand of households and generating the energy required via power planning [6]. DR requires Big Data analytics to accurately forecast power demand and predict peak power demands, and this is beneficial for users as their pricing and access to reliable energy is tied to operational practices of utility providers. ...
... The impact of the IoT on the life of users can consider as its essential feature [4]. In [26], a scalable structure for home automation is introduced using Apache Storm. Though, they rely on local reasoning for enabling scalability. ...
Conference Paper
Full-text available
The massive deployment of Internet of Things (IoT) is allowing Smart City projects and initiatives all over the world. The IoT is a modular approach to merge various sensors with all the ICT solutions. With over 50 billion objects will be connected and deployed in smart cities in 2020. The heart of smart cities operations is the IoT communications. IoT is designed to support Smart City concept, which aims at utilizing the most advanced communication technologies to promote services for the administration of the city and the citizens. This paper is presenting a comprehensive review of the concepts of IoT and smart cities and their motivations and applications. Moreover, this paper describes the main challenges and weaknesses of applying the IoT technologies based on smart city paradigms,
... In [10], a scalable architecture for home automation is proposed using Apache Storm. However, they rely on local logic for enabling scalability. ...
... The authors also evaluated different methods with respect to efficiency and cost. Other researchers [13] focused on how to improve communications and functions of automation system methods by analyzing feedback information gathered from IoT. They proposed or updated existing standards/ frameworks based on the results. ...
Conference Paper
The rapid influx of smart devices into the home has caused a shift in the way the entertainment industry envisions TV viewing experiences. The traditional TV-watching experience is now being superseded by multi-device experiences where TV viewers increasingly use companion devices as second-screens to interact with content on the television. To improve user engagement, many TV broadcasters are investigating/standardising technologies for multi-device next-generation content production and presentation on commodity devices. We believe that technological innovation to enable richer experiences is still in its infancy. In this paper, we introduce an ongoing work to enable immersive and interactive multi-device online TV experiences. Our project covers three essential aspects: content authoring, device discovery, and cross-device media orchestration.
Article
Demand Response (DR) is becoming a cornerstone element in the current energy sector, particularly for the EU energy markets. For this reason, considerable effort has been spent on standardising demand response data models. As a result, there is an ever-growing number of demand response proposals based on these standards. However, these proposals are usually centralised, and those that rely on cloud solutions use the cloud as a centralised data store assuming that the data is already homogenised when stored, i.e. all the data has the same format and model. Nevertheless, in practise, DR proposals rely on several components that provide data in heterogeneous formats and models. Furthermore, the different DR standards define models for different data formats that hinder data exchange between different DR systems. In this article, a generic tool called CIM is presented, which allows existing DR systems to distribute their components in the cloud, providing a solid security and privacy framework for data exchange. In addition, the CIM implements a semantic interoperability layer that is capable of translating data into a normalised form when exchanged so that it can be transparently consumed by DR components. Experiments advocate the CIM as a solution for DR systems to decentralise their architectures and exchange heterogeneous data even with other DR systems that follow different DR standards.
Chapter
The idea of smart cities is attracting support each day and has emerged as a solution to solve the unprecedented problems of accelerated urban development and growing population explosion and, at the same time, give residents and tourists a better lifestyle. The smart city bears some responsibility for both planned and unforeseen circumstances, and the potential of alleviating the influence of instability on the causes of disturbance by evaluating all possible data produced by the city introduces new opportunities for resilience activity. The Internet of Everything (IoE) alongside advanced networking technology is an important means of achieving smartness in every smart city system. Companies and policymakers around the world are making a great deal of effort to support the value of lowering electricity use and carbon emissions, as well as the green IoE for smart cities. Therefore, this chapter lays out a new system for upgrading smart cities that have lowered power usage at each level to ensure the implementation of IoT towards a green climate. The chapter also identifies core innovations, resources, threats, and potential prospects in these fields.
Conference Paper
Full-text available
Demand response (DR) is a technique used in smart grids to shape customer load during peak hours. Automated DR offers utilities a fine grained control and a high degree of confidence in the outcome. However the impact on the customer's comfort means this technique is more suited for industrial and commercial settings than for residential homes. In this paper we propose a system for achieving automated controlled DR in a heterogeneous environment. We present some of the main issues arising in building such a system, including privacy, customer satisfiability, reliability, and fast decision turnaround, with emphasis on the solutions we proposed. Based on the lessons we learned from empirical results we describe an integrated automated system for controlled DR on the USC microgrid. Results show that while on a per building per event basis the accuracy of our prediction and customer selection techniques varies, it performs well on average when considering several events and buildings.
Article
Full-text available
This paper develops an energy management system with integration of smart meters for electricity consumers in a smart grid context. The integration of two types of smart meters (SM) are developed: (i) consumer owned SM and (ii) distributor owned SM. The consumer owned SM runs over a wireless platform–ZigBee protocol and the distributor owned SM uses the wired environment–ModBus protocol. The SM are connected to a SCADA system (Supervisory Control And Data Acquisition) that supervises a network of Programmable Logic Controllers (PLC). The SCADA system/PLC network integrates different types of information coming from several technologies present in modern buildings. The developed control strategy implements a hierarchical cascade controller where inner loops are performed by local PLCs, and the outer loop is managed by a centralized SCADA system, which interacts with the entire local PLC network. In order to implement advanced controllers, a communication channel was developed to allow the communication between the SCADA system and the MATLAB software.
Conference Paper
Full-text available
The smart grid changes the way energy is produced and distributed. In addition both, energy and information is exchanged bidirectionally among participating parties. Therefore heterogeneous systems have to cooperate effectively in order to achieve a common high-level use case, such as smart metering for billing or demand response for load curtailment. Furthermore, a substantial amount of personal data is often needed for achieving that goal. Capturing and processing personal data in the smart grid increases customer concerns about privacy and in addition, certain statutory and operational requirements regarding privacy aware data processing and storage have to be met. An increase of privacy constraints, however, often limits the operational capabilities of the system. In this paper, we present an approach that automates the process of finding an optimal balance between privacy requirements and operational requirements in a smart grid use case and application scenario. This is achieved by formally describing use cases in an abstract model and by finding an algorithm that determines the optimum balance by forward mapping privacy and operational impacts. For this optimal balancing algorithm both, a numeric approximation and – if feasible – an analytic assessment are presented and investigated. The system is evaluated by applying the tool to a real-world use case from the University of Southern California (USC) microgrid.
Conference Paper
Full-text available
Smart grids are becoming popular with the advent of sophisticated smart meters. They allow utilities to optimize energy consumption during peak hours by applying various demand response techniques including voluntary curtailment, direct control and price incentives. To sustain the curtailment over long periods of time of up to several hours utilities need to make fast and accurate consumption predictions on a large set of customers based on a continuous flow of real time data and huge historical data sets. Given the numerous consumption patterns customers exhibit, different prediction methods need to be used to reduce the prediction error. The straightforward approach of testing each customer against every method is unfeasible in this large volume and high velocity environment. To this aim, we propose a neural network based approach for automatically selecting the best prediction method per customer by relying only on a small subset of customers. We also introduce two historical averaging methods for consumption prediction that take advantage of the variability of the data and continuously update the results based on a sliding window technique. We show that once trained, the proposed neural network does not require frequent retraining, ensuring its applicability in online scenarios such as the sustainable demand response.
Technical Report
Full-text available
Recent years have seen an increasing interest in providing accurate prediction models for electrical energy consumption. In Smart Grids, energy consumption optimization is critical to enhance power grid reliability, and avoid supply-demand mismatches. Utilities rely on real-time power consumption data from individual customers in their service area to forecast the future demand and initiate energy curtailment programs. Currently however, little is known about the differences in consumption characteristics of various customer types, and their impact on the prediction method's accuracy. While many studies have concentrated on aggregate loads, showing that accurate consumption prediction at the building level can be achieved, there is a lack of results regarding individual customers consumption prediction. In this study, we perform an empirical quantitative evaluation of various prediction methods of kWh energy consumption of two distinct customer types: 1) small, highly variable individual customers, and 2) aggregated, more stable consumption at the building level. We show that prediction accuracy heavily depends on customer type. Contrary to previous studies, we consider the consumption data granularity to be very small (i.e., 15-min interval), and focus on very short term predictions (next few hours). As Smart Grids move closer to dynamic curtailment programs, which enables demand response (DR) events not only on weekdays, but also during weekends, existing DR strategies prove to be inadequate. Here, we relax the constraint of workdays, and include weekends, where ISO models consistently under perform. Nonetheless, we show that simple ISO baselines, and short-term Time Series, which only depend on recent historical data, achieve superior prediction accuracy. This result suggests that large amounts of historical training data are not required, rather they should be avoided.
Conference Paper
Full-text available
Regulating the power consumption to avoid peaks in demand is a known method. Demand Response is used as tool by utility providers to minimize costs and avoid network overload during peaks in demand. Although it has been used extensively there is a shortage of solutions dealing with real-time scheduling of DR events. Past attempts focus on minimizing the load demand while not dealing with the uncertainty induced by customer intervention which hinder sustainability of the reduced load. In this paper we describe a smart selection algorithm that solves the problem of scheduling DR events in a broad spectrum of customers observed in common Smart Grid Infrastructures. We deal both with the problem of real-time operation and sustainability of the reduced load while factoring customer comfort levels. Real Data were used from the USC campus micro grid in our experiments. On the overall achievable reduction the results produced a maximum average approximation error ≈ 0.7%. Sustainability of the targeted load was achieved with maximum average error of less than 3%. It is also shown that our solution fulfils the requirements for Dynamic Demand Response providing a solution in a reasonable amount of time.
Conference Paper
Full-text available
Curtailment prediction and efficient demand response (DR) strategy selection challenge the effectiveness of developing smart grid applications. Here we present solutions to both challenges, taking a bottom-up approach to demonstrate that curtailment at the equipment-level determined based on the equipment mechanical properties and models can be used to efficiently estimate curtailment and to optimize human comfort during a DR event across a subset of energy consumers. We focus on a controlled microgrid environment present on the University of Southern California campus and address two HVAC oriented DR strategies: variable frequency drive and global temperature reset. Strong correlation between equipment and building level consumption was found to exist in less than half the cases, showing that global consumption can be successfully used as well for those scenarios. Several fast heuristics aiming to optimizing human comfort during equipment level DR proved to be successful and showed that the best method depends on the DR strategy. Finally, relying on the equipment specifications and consumption models for our analyses circumvents the common challenges associated with statistical and machine-learning algorithm approaches that rely on large amounts of historical data.
Article
Full-text available
This paper proposes an appliance scheduling scheme for residential building energy management controllers, by taking advantage of the time-varying retail pricing enabled by the two-way communication infrastructure of the smart grid. Finite-horizon scheduling optimization problems are formulated to exploit operational flexibilities of thermal and non-thermal appliances using a model predictive control (MPC) method which incorporates both forecasts and newly updated information. For thermal appliance scheduling, the thermal mass of the building, which serves as thermal storage, is integrated into the optimization problem by modeling the thermodynamics of rooms in a building as constraints. Within the comfort range modeled by the predicted mean vote (PMV) index, thermal appliances are scheduled smartly together with thermal mass storage to hedge against high prices and make use of low-price time periods. For non-thermal appliance scheduling, in which delay and/or power consumption flexibilities are available, operation dependence of inter-appliance and intra-appliance is modeled to further exploit the price variation. Simulation results show that customers have notable energy cost savings on their electricity bills with time-varying pricing. The impact of customers' preferences of appliances usage on energy cost savings is also evaluated.
Article
Full-text available
The smart grid initiative and electricity market operation drive the development known as demand-side management or controllable load. Home energy management has received increasing interest due to the significant amount of loads in the residential sector. This paper presents a hardware design of smart home energy management system (SHEMS) with the applications of communication, sensing technology, and machine learning algorithm. With the proposed design, consumers can easily achieve a real-time, price-responsive control strategy for residential home loads such as electrical water heater (EWH), heating, ventilation, and air conditioning (HVAC), electrical vehicle (EV), dishwasher, washing machine, and dryer. Also, consumers may interact with suppliers or load serving entities (LSEs) to facilitate the load management at the supplier side. Further, SHEMS is designed with sensors to detect human activities and then a machine learning algorithm is applied to intelligently help consumers reduce total payment on electricity without or with little consumer involvement. Finally, simulation and experiment results are presented based on an actual SHEMS prototype to verify the hardware system.
Article
Full-text available
Smart homes have been viewed with increasing interest by both home owners and the research community in the past few years. One reason for this development is that the use of modern automation technology in the home or building promises considerable savings of energy, therefore, simultaneously reducing the operational costs of the building over its whole lifecycle. However, the full potential of smart homes still lies fallow, due to the complexity and diversity of the systems, badly engineered and configured installations, as well as the frequent problem of suboptimal control strategies. Summarized, these problems converge to two undesirable conditions in the "not-so-smart" home: energy consumption is still higher than actually necessary and users are unable to yield full comfort in their automated homes. This work puts its focus on alleviating the current problems by proposing a comprehensive system concept, that shall ensure that smart homes can keep their promise in the future. The system operates on an extensive knowledge base that stores all information needed to fulfill the goals of energy efficiency and user comfort. Its intelligence is implemented as and within a multiagent system that also caters for the system's openness to the outside world. As a first evaluation, a profile-based control strategy for thermal comfort is developed and verified by means of simulation.
Conference Paper
Full-text available
The goal of the MavHome (Managing An Intelligent Versatile Home) project is to create a home that acts as an intelligent agent. In this paper we introduce the MavHome architecture. The role of prediction algorithms within the architecture is discussed, and a meta-predictor is presented which combines the strengths of multiple approaches to inhabitant action prediction. We demonstrate the effectiveness of these algorithms on smart home data.
Article
Over the last twenty years, energy conservation has always been of great importance to individuals, societies and decision makers around the globe. As a result, IT researchers have shown a great interest in providing efficient, reliable and easy-to-use IT services which help users saving energy at home by making use of the current advances in Information and Communications Technology (ICT). Driven by the aforementioned motivation, we developed SMARTENERGY.KOM, our framework for realizing energy efficient smart homes based on wireless sensor networks and human activity detection. Our work is based on the idea that most of the user activities at home are related to a set of electrical appliances which are necessary to perform these activities. Therefore, we show how it is possible to detect the user's current activity by monitoring his fine-grained appliance-level energy consumption. This relation between activities and electrical appliances makes it possible to detect appliances which could be wasting energy at home. Our framework is organized in two components. On one hand, the activity detection framework which is responsible for detecting the user's current activity based on his energy consumption. On the other hand, the EnergyAdvisor framework which utilizes the activity detection for the purpose of recognizing the appliances which are wasting energy at home and informing the user about optimization potential.
Conference Paper
As the carbon dioxide emission and global warming become the world serious issues, many researches are performed to reduce the energy consumption. Therefore, there are many new devices for energy saving scheme in the smart home area, such as smart plug, AMI, and IHD. Using them, users can recognize and reduce the amount of energy consumption, and the appliances can be controlled considering the energy efficiency. In this paper, we propose a home energy management system for an energy-efficient smart home. First, the data of energy consumption for a smart home is collected and analyzed. And energy conservation measures are generated and performed while maintaining comfort of users. Using these methods, energy management services for smart homes can be provided more easily and efficiently.
Conference Paper
Optimization of energy use is a vital concept in providing solutions to many of the energy challenges in our world today. Large chemical, mechanical, pneumatic, hydraulic, and electrical systems require energy efficiency as one of the important aspects of operating systems. At the micro-scale, the built environment experiences progressive changes in energy consumption. There is steady increase in the annual energy consumption of households as a result of population growth, increase of economic activity and increased use of domestic appliances. The drive to reduce this growing trend has stimulated many mechanisms such as the use of energy labels on domestic appliances. Home appliance manufacturers research into developing energy-efficient products with the end-goal of making consumer devices more energy efficient. One important step towards energy efficiency and savings in the built environment is the introduction of Smart Home Energy Management Systems. (SHEMS). This paper analyses how the implementation of such solutions could contribute to energy savings and enhance efficiency for residential customers. The paper presents a general overview of energy efficiency measures focusing on residential loads. It further highlights, via modelling and simulation the potentials of Smart Home Energy Management Solutions for future domestic applications.
Article
Demand response (DR), distributed generation (DG), and distributed energy storage (DES) are important ingredients of the emerging smart grid paradigm. For ease of reference we refer to these resources collectively as distributed energy resources (DER). Although much of the DER emerging under smart grid are targeted at the distribution level, DER, and more specifically DR resources, are considered important elements for reliable and economic operation of the transmission system and the wholesale markets. In fact, viewed from transmission and wholesale operations, sometimes the term ??virtual power plant?? is used to refer to these resources. In the context of energy and ancillary service markets facilitated by the independent system operators (ISOs)/regional transmission organizations (RTOs), the market products DER/DR can offer may include energy, ancillary services, and/or capacity, depending on the ISO/RTO market design and applicable operational standards. In this paper we first explore the main industry drivers of smart grid and the different facets of DER under the smart grid paradigm. We then concentrate on DR and summarize the existing and evolving programs at different ISOs/RTOs and the product markets they can participate in. We conclude by addressing some of the challenges and potential solutions for implementation of DR under smart grid and market paradigms.
Article
Conventional cost-based load management ignores the rate structure offered to customers. The resulting cost savings may cause revenue loss. In a deregulated power industry where utilities absorb the ultimate consequence of their decision making, reexamination of load management must be conducted. In this paper, profit-based load management is introduced to examine generic direct load control scheduling. Based upon the cost/market price function, the approach aims to increase the profit of utilities. Instead of determining the amount of energy to be deferred or to be paid back, the algorithm controls the number of groups power customer/load type to maximize the profit. In addition to the advantage of better physical feel on how the control devices should operate, the linear programming algorithm provides a relatively inexpensive and powerful approach to the scheduling problem
Faulttolerant and elastic streaming mapreduce with decentralized coordination
  • A Kumbhare
  • M Frincu
  • Y Simmhan
  • V K Prasanna
A. Kumbhare, M. Frincu, Y. Simmhan, and V. K. Prasanna, "Faulttolerant and elastic streaming mapreduce with decentralized coordination," in Distributed Computing Systems (ICDCS), 2015 IEEE 35th International Conference on, 2015, pp. 328-338.
distributed and fault-tolerant realtime computation
  • Storm
Storm, distributed and fault-tolerant realtime computation. Last accessed April 2, 2016. [Online]. Available: http://storm.apache.org/
Model-based assessment for balancing privacy requirements and operational capabilities in the smart grid
  • F Knirsch
  • D Engel
  • M Frincu
  • V Prasanna
F. Knirsch, D. Engel, M. Frincu, and V. Prasanna, "Model-based assessment for balancing privacy requirements and operational capabilities in the smart grid," in Innovative Smart Grid Technologies Conference (ISGT), 2015 IEEE Power Energy Society, 2015, pp. 1-5.
Automated demand response strategies and commissioning commercial building controls
  • M A Piette
  • D S Watson
  • N Motegi
  • S Kiliccote
  • E Linkugel
M. A. Piette, D. S. Watson, N. Motegi, S. Kiliccote, and E. Linkugel, "Automated demand response strategies and commissioning commercial building controls," in 14th National Conference on Building Commissioning, 2006.
Empirical comparison of prediction methods for electricity consumption forecasting
  • S Aman
  • M Frincu
  • C Charalampos
  • U Noor
  • Y Simmhan
  • V Prasanna
S. Aman, M. Frincu, C. Charalampos, U. Noor, Y. Simmhan, and V. Prasanna, "Empirical comparison of prediction methods for electricity consumption forecasting," University of Southern California, Tech. Rep. 14-942, 2014, uRL: http://www.cs.usc.edu/assets/007/89887.pdf (accessed Mar 6, 2014).
Accurate and efficient selection of the best consumption prediction method in smart grids
  • M Frincu
  • C Chelmis
  • M U Noor
  • V Prasanna
M. Frincu, C. Chelmis, M. U. Noor, and V. Prasanna, "Accurate and efficient selection of the best consumption prediction method in smart grids," in Big Data (Big Data), 2014 IEEE International Conference on, 2014, pp. 721-729.