Fig 3 - uploaded by Hao Wang
Content may be subject to copyright.
![Categories of Analytics [16, Fig.3]](profile/Hao-Wang-71/publication/283488213/figure/fig3/AS:614303359062041@1523472742495/Categories-of-Analytics-16-Fig3.png)
Source publication
![Fig. 3. Categories of Analytics [16, Fig.3]](profile/Hao-Wang-71/publication/283488213/figure/fig3/AS:614303359062041@1523472742495/Categories-of-Analytics-16-Fig3_Q320.jpg)
Despite being popularly referred to as the ultimate solution for all problems of our current electric power system, smart grid is still a growing and unstable concept. It is usually considered as a set of advanced features powered by promising technological solutions. In this paper, we describe smart grid as a socio-technical transition and illustr...
Context in source publication
Context 1
... the point of view of analytics-as-a-service [16], [20], there are three categories of analytics: descriptive analyt- ics, predictive analytics, and prescriptive analytics. They are depicted in Figure 3: (1) descriptive analytics reports on "what is happening or happened", which could help the business identify opportunites and challenges; (2) predictive 0.31MB Fig. 4. Data generating potential estimated for 1M end-users. The ratio between the high voltage nodes, low voltage nodes, and the end-users is equal to the current ratio in the Netherlands (provided in [17]). The data size per sample and the sampling frequency are adapted from the study conducted in [17]. Interestingly, the data generated by an end-user each day is comparable to that of an average Facebook ...
Citations
... Lunde, Røpke, and Heiskanen (2016) define a smart grid as an upgraded electricity network that has enhanced two-way digital communication between supplier and consumer, intelligent metering, and a monitoring system. The smart grid is often perceived as the answer to many challenges of the current energy system, albeit in much need of development (Dang-Ha, Olsson, and Wang 2015). Like the abstract layer of cloud computing, making the energy grid intelligent requires material transformations to the existing arrangements in the grid. ...
Which societal functions should be prioritized when the electricity grid reaches its maximum capacity? By using Sweden as an example, this policy brief discusses the societal negotiations that arise around capacity deficits of the electricity grid. By introducing the term energy gentrification, we aim to highlight the potential dangers of failing to recognize that energy also constitutes a societal resource, and like any other resource of the built environment, it is exposed to the risk of exploitation if left unprotected. We propose energy gentrification as an analytical perspective, through which negotiations and potential conflicts can be studied when grid owners must prioritize who should be connected to the grid. In relation to previous research on gentrification, we identify several parallels to the Swedish case of data centers, such as the relative prioritization of global versus local capital, the competition over resources, the allusion to promises of job opportunities and regional development for justification, and the tradeoffs between common goods versus private interests. The perspective of energy gentrification offers a useful approach for inquiring into the ethical dimensions of energy policies and for highlighting the bureaucratic nature of energy policy decision-making. The policy brief concludes by proposing opportunities for future research.
... Studies in [14] revealed that energy consumption results from complex factors, such as socioeconomic and demographic factors. In addition, some households may not have been equipped with smart meters [15] or no historical data are available for new tenants. A few recent studies [16,17] took a new perspective to investigate the relationship between energy consumption and socioeconomic features, i.e., characteristics of the occupants. ...
... Specifically, noticeable inaccuracy occurs in benchmark 2 for #59 and #4310 on the weekend. We also use MSEs in Equation (15) to measure the errors of all compared methods, as shown in TABLE 3 for both weekday and weekend. The error reduction is shown in the table as well. ...
This paper models residential consumers' energy-consumption behavior by load patterns and distributions and reveals the relationship between consumers' load patterns and socioeconomic features by machine learning. We analyze the real-world smart meter data and extract load patterns using K-Medoids clustering, which is robust to outliers. We develop an analytical framework with feature selection and deep learning models to estimate the relationship between load patterns and socioeconomic features. Specifically, we use an entropy-based feature selection method to identify the critical socioeconomic characteristics that affect load patterns and benefit our method's interpretability. We further develop a customized deep neural network model to characterize the relationship between consumers' load patterns and selected socioeconomic features. Numerical studies validate our proposed framework using Pecan Street smart meter data and survey. We demonstrate that our framework can capture the relationship between load patterns and socioeconomic information and outperform benchmarks such as regression and single DNN models.
... The development of a smart grid is fully associated with the big data flow. There are various prospective applications of big data analytics on smart grid data such as real-time and automatic processing of the electrical consumers' energy consumption, automatic billing, intelligent energy planning and pricing analysis, detection of outages due to faults and anomalies, load and generation forecast under high unpredictability, load management with demand response, and asset management [2]. A high volume of data obtained from various smart grid sources satisfies the characteristics of big data. ...
Smart grids have been gradually replacing the traditional power grids since the last decade. Such transformation is linked to adding a large number of smart meters and other sources of information extraction units. This provides various theopportunities of havingassociated with the collected big data.Now, Hence, the triumph of the smart grid utilizationenergy paradigm depends on the factor of smart gridbig data analytics. which wouldThis includes the effective acquisition, transmission, processing,and effective visualization, interpretation, and utilization of big dataof the data that would bring benefits and increase efficiency of the power systems. The paper provides deep insights aboutinto various big data technologies and discusses the literature onbig data analytics in the context of the smart grid. Also, itThe paper also presents the challenges and opportunities , tools and emerging technologiesbrought by the advent ofthe internet of things, machine learning and big data from smart gridsand cloud platforms.
... This layer also includes but is not limited to generators, intelligent electronic devices, telemetry devices, smart meters, protection coordination, and grid synchronization devices. This layer is complemented by a communications infrastructure layer that also includes data management [11]. The role of this layer is to enable the transmission and reception of the data collected and consumed by devices in the lower layer. ...
... Many of the parts of the standard have been withdrawn, so the focus will be active parts with relevance to the paper. This includes parts 8[63],11 ...
Big data standards and capability maturity models (CMMs) help developers build applications with reduced coupling and increased breadth of deployment. In smart grids, stakeholders currently work with data management techniques that are unique and customized to their own goals, thereby posing challenges for grid-wide integration and deployment. Although big data standards and CMMs exist for other domains, no work in the literature considers adapting them to smart grids, which will benefit from both. Further, existing smart grid standards and CMMs do not fully account for big data challenges. This paper bridges the gap by analyzing the role of big data in smart grids, and explores if and how big data standards and CMMs can be adapted specifically to 10 distributed generation use-cases that use big data. In doing so, this work provides a useful starting point for researchers and industry members developing standards and CMM assessments for smart grid distributed generation.
... The electricity or power is considered to be the backbone of every country. It has been witnessed many recent developments in research and infrastructure to benefit the socioeconomic development at large in the field of power [1,2]. With the technology progress in the area of energy, traditional power grids are transforming into an intelligent system called smart power grids. ...
... • Cost effective big data solutions for the whole solution including data center, tools, storage, control algorithms, warehouses, etc. The current power grid stakeholders cannot easily accept cost of the massive sensors and the new infrastructure [174]. ...
The prospering Big data era is emerging in the power grid. Multiple world-wide studies are emphasizing the big data applications in the microgrid due to the huge amount of produced data. Big data analytics can impact the design and applications towards safer, better, more profitable, and effective power grid. This paper presents the recognition and challenges of the big data and the microgrid. The construction of big data analytics is introduced. The data sources, big data opportunities, and enhancement areas in the microgrid like stability improvement, asset management, renewable energy prediction, and decision-making support are summarized. Diverse case studies are presented including different planning, operation control, decision making, load forecasting, data attacks detection, and maintenance aspects of the microgrid. Finally, the open challenges of big data in the microgrid are discussed.
... Several references such as [4] summarize the critical issues of this research direction. While recent surveys have outlined some selected aspects of big data issues in smart power systems, such as the role of big data technology and management in smart power grids and future challenges [3], [5]- [7], to the best knowledge of the authors, there is no prior similar review published paper on the subject of big data issues in SGs, considering nearly all technical, analytical, and standardization features in a classified fashion with a mostly SGoriented viewpoint, rather than the conventional information and communication technology (ICT) oriented approach presented in the existing survey papers. The lack of the joint SG-oriented and ICT-oriented viewpoint in the existing review papers in this area is the motivation to provide a review paper with a holistic viewpoint for both expert scientific communities and general public as users of big data applications results with restricted knowledge of big data issues. ...
... The lack of the joint SG-oriented and ICT-oriented viewpoint in the existing review papers in this area is the motivation to provide a review paper with a holistic viewpoint for both expert scientific communities and general public as users of big data applications results with restricted knowledge of big data issues. This review article bridges the gaps in the reviewed literature [3], [5]- [7] by adopting a general and comprehensive viewpoint for investigating the impacts of big data analytics in modern power systems and SGs. Table I presents the comparison of the research areas covered in previous survey papers and in this article. ...
The smart power systems are based upon information and communication technologies, which lead to a deluge of data originating from various sources. To address these challenges concerning accumulated voluminous data, big data analysis in smart power systems is inevitable. This article comprehensively surveys the literature related to the big data issues in smart power systems. The background and motivation of the big data paradigm in smart power systems are first provided, and then the major issues related to the architectures, the key technologies, and standardizations of big data analytics in smart power systems are analyzed. Also, the potential applications of big data in smart power systems based upon the state-of-the-art research are highlighted. Finally, the future issues and challenges of the big data issues in modern power systems are discussed.
... [2]- [11], heavily relied on the data analysis of each individual's historical load profile to perform various operations. It is often costly for utility companies to deploy a massive AMI, and some households may not have been equipped with smart meters [12]. Han et al. in [12] took the first step to consider the impact of socio-economic factors of users in the power load forecasting but the discussions were limited to the peak loads and total energy consumption of users. ...
... It is often costly for utility companies to deploy a massive AMI, and some households may not have been equipped with smart meters [12]. Han et al. in [12] took the first step to consider the impact of socio-economic factors of users in the power load forecasting but the discussions were limited to the peak loads and total energy consumption of users. In this paper, we aim to study richer characterizations of users' loads, e.g. ...
Advanced metering infrastructure systems record a high volume of residential load data, opening up an opportunity for utilities to understand consumer energy consumption behaviors. Existing studies have focused on load profiling and prediction, but neglected the role of socioeconomic characteristics of consumers in their energy consumption behaviors. In this paper, we develop a prediction model using deep neural networks to predict load patterns of consumers based on their socioeconomic information. We analyze load patterns using the K-means clustering method and use an entropy-based feature selection method to select the key socioeconomic characteristics that affect consumers' load patterns. Our prediction method with feature selection achieves a higher prediction accuracy compared with the benchmark schemes, e.g. 80% reduction in the prediction error.
... [2]- [11], heavily relied on the data analysis of each individual's historical load profile to perform various operations. It is often costly for utility companies to deploy a massive AMI, and some households may not have been equipped with smart meters [12]. Han et al. in [12] took the first step to consider the impact of socio-economic factors of users in the power load forecasting but the discussions were limited to the peak loads and total energy consumption of users. ...
... It is often costly for utility companies to deploy a massive AMI, and some households may not have been equipped with smart meters [12]. Han et al. in [12] took the first step to consider the impact of socio-economic factors of users in the power load forecasting but the discussions were limited to the peak loads and total energy consumption of users. In this paper, we aim to study richer characterizations of users' loads, e.g. ...
Advanced metering infrastructure systems record a high volume of residential load data, opening up an opportunity for utilities to understand consumer energy consumption behaviors. Existing studies have focused on load profiling and prediction, but neglected the role of socioeconomic characteristics of consumers in their energy consumption behaviors. In this paper, we develop a prediction model using deep neural networks to predict load patterns of consumers based on their socioeconomic information. We analyze load patterns using the K-means clustering method and use an entropy-based feature selection method to select the key socioeconomic characteristics that affect consumers' load patterns. Our prediction method with feature selection achieves a higher prediction accuracy compared with the benchmark schemes, e.g. 80% reduction in the prediction error.
... Moreover, the CPES requires the physical infrastructure and computational cyber-infrastructure to holistically and consistently coordinate to ensure its efficient and reliable functionality. It introduces a huge data influx for which big data analytic and applications are therefore of paramount importance [9]. Co-simulation framework, gathering data and analysis from multiple sources and domains, is potentially the solution to experiment such big data applications over large scale systems. ...
Co-simulation is an emerging method for cyber-physical energy system (CPES) assessment and validation. Combining simulators of different domains into a joint experiment, co-simulation provides a holistic framework to consider the whole CPES at system level. In this paper, we present a systematic structuration of co-simulation based on a conceptual point of view. A co-simulation framework is then considered in its conceptual, semantic, syntactic, dynamic and technical layers. Coupling methods are investigated and classified according to these layers. This paper would serve as a solid theoretical base for specification of future applications of co-simulation and selection of coupling methods in CPES assessment and validation.
