Browsing by Author "Afzalan, Milad"

Now showing 1 - 5 of 5
  • Thumbnail Image
    Building Energy Profile Clustering Based on Energy Consumption Patterns
    Afzalan, Milad (Virginia Tech, 2020-06)
    With the widespread adoption of smart meters in buildings, an unprecedented amount of high- resolution energy data is released, which provides opportunities to understand building consumption patterns. Accordingly, research efforts have employed data analytics and machine learning methods for the segmentation of consumers based on their load profiles, which help utilities and energy providers for customized/personalized targeting for energy programs. However, building energy segmentation methodologies may present oversimplified representations of load shapes, which do not properly capture the realistic energy consumption patterns, in terms of temporal shapes and magnitude. In this thesis, we introduce a clustering technique that is capable of preserving both temporal patterns and total consumption of load shapes from customers’ energy data. The proposed approach first overpopulates clusters as the initial stage to preserve the accuracy and merges the similar ones to reduce redundancy in the second stage by integrating time-series similarity techniques. For such a purpose, different time-series similarity measures based on Dynamic Time Warping (DTW) are employed. Furthermore, evaluations of different unsupervised clustering methods such as k-means, hierarchical clustering, fuzzy c-means, and self-organizing map were presented on building load shape portfolios, and their performance were quantitatively and qualitatively compared. The evaluation was carried out on real energy data of ~250 households. The comparative assessment (both qualitatively and quantitatively) demonstrated the applicability of the proposed approach compared to benchmark techniques for power time-series clustering of household load shapes. The contribution of this thesis is to: (1) present a comparative assessment of clustering techniques on household electricity load shapes and highlighting the inadequacy of conventional validation indices for choosing the cluster number and (2) propose a two-stage clustering approach to improve the representation of temporal patterns and magnitude of household load shapes.
  • Thumbnail Image
    Data-driven customer energy behavior characterization for distributed energy management
    Afzalan, Milad (Virginia Tech, 2020-07-01)
    With the ever-growing concerns of environmental and climate concerns for energy consumption in our society, it is crucial to develop novel solutions that improve the efficient utilization of distributed energy resources for energy efficiency and demand response (DR). As such, there is a need to develop targeted energy programs, which not only meet the requirement of energy goals for a community but also take the energy use patterns of individual households into account. To this end, a sound understanding of the energy behavior of customers at the neighborhood level is needed, which requires operational analytics on the wealth of energy data from customers and devices. In this dissertation, we focus on data-driven solutions for customer energy behavior characterization with applications to distributed energy management and flexibility provision. To do so, the following problems were studied: (1) how different customers can be segmented for DR events based on their energy-saving potential and balancing peak and off-peak demand, (2) what are the opportunities for extracting Time-of-Use of specific loads for automated DR applications from the whole-house energy data without in-situ training, and (3) how flexibility in customer demand adoption of renewable and distributed resources (e.g., solar panels, battery, and smart loads) can improve the demand-supply problem. In the first study, a segmentation methodology form historical energy data of households is proposed to estimate the energy-saving potential for DR programs at a community level. The proposed approach characterizes certain attributes in time-series data such as frequency, consistency, and peak time usage. The empirical evaluation of real energy data of 400 households shows the successful ranking of different subsets of consumers according to their peak energy reduction potential for the DR event. Specifically, it was shown that the proposed approach could successfully identify the 20-30% of customers who could achieve 50-70% total possible demand reduction for DR. Furthermore, the rebound effect problem (creating undesired peak demand after a DR event) was studied, and it was shown that the proposed approach has the potential of identifying a subset of consumers (~5%-40% with specific loads like AC and electric vehicle) who contribute to balance the peak and off-peak demand. A projection on Austin, TX showed 16MWh reduction during a 2-h event can be achieved by a justified selection of 20% of residential customers. In the second study, the feasibility of inferring time-of-use (ToU) operation of flexible loads for DR applications was investigated. Unlike several efforts that required considerable model parameter selection or training, we sought to infer ToU from machine learning models without in-situ training. As the first part of this study, the ToU inference from low-resolution 15-minute data (smart meter data) was investigated. A framework was introduced which leveraged the smart meter data from a set of neighbor buildings (equipped with plug meters) with similar energy use behavior for training. Through identifying similar buildings in energy use behavior, the machine learning classification models (including neural network, SVM, and random forest) were employed for inference of appliance ToU in buildings by accounting for resident behavior reflected in their energy load shapes from smart meter data. Investigation on electric vehicle (EV) and dryer for 10 buildings over 20 days showed an average F-score of 83% and 71%. As the second part of this study, the ToU inference from high-resolution data (60Hz) was investigated. A self-configuring framework, based on the concept of spectral clustering, was introduced that automatically extracts the appliance signature from historical data in the environment to avoid the problem of model parameter selection. Using the framework, appliance signatures are matched with new events in the electricity signal to identify the ToU of major loads. The results on ~1500 events showed an F-score of >80% for major loads like AC, washing machine, and dishwasher. In the third study, the problem of demand-supply balance, in the presence of varying levels of small-scale distributed resources (solar panel, battery, and smart load) was investigated. The concept of load complementarity between consumers and prosumers for load balancing among a community of ~250 households was investigated. The impact of different scenarios such as varying levels of solar penetration, battery integration level, in addition to users' flexibility for balancing the supply and demand were quantitatively measured. It was shown that (1) even with 100% adoption of solar panels, the renewable supply cannot cover the demand of the network during afternoon times (e.g., after 3 pm), (2) integrating battery for individual households could improve the self-sufficiency by more than 15% during solar generation time, and (3) without any battery, smart loads are also capable of improving the self-sufficiency as an alternative, by providing ~60% of what commercial battery systems would offer. The contribution of this dissertation is through introducing data-driven solutions/investigations for characterizing the energy behavior of households, which could increase the flexibility of the aggregate daily energy load profiles for a community. When combined, the findings of this research can serve to the field of utility-scale energy analytics for the integration of DR and improved reshaping of network energy profiles (i.e., mitigating the peaks and valleys in daily demand profiles).
  • Thumbnail Image
    A Machine Learning Framework to Infer Time-of-Use of Flexible Loads: Resident Behavior Learning for Demand Response
    Afzalan, Milad; Jazizadeh, Farrokh (IEEE, 2020-06-26)
    Load shapes obtained from smart meter data are commonly utilized to understand daily energy use patterns for adaptive operations in applications such as Demand Response (DR). However, they do not provide information on the underlying causes of specic energy use patterns i.e., inference on appliances' time-of-use (ToU) as actionable information. In this paper, we investigated a scalable machine learning framework to infer the appliances' ToU from energy load shapes in a collection of residential buildings. A scalable and generalized inference model obviates the need for model training in each building to facilitate its adoption by relying on training data from a set of previously observed buildings with available appliance- level data. To this end, we demonstrated the feasibility of using load shape segmentation to boost ToU inference in buildings by learning from their nearest matches that share similar energy use patterns. To infer an appliance ToU for a building, classication models are trained for inference on subintervals of load shapes from matched buildings with known ToU. The framework was evaluated using real-world energy data from Pecan Street Dataport. The results for a case study on electric vehicles (EV) and dryers showed promising performance by using 15-min smart meter load shape data with 83% and 71% F-score values, respectively, and without in-situ training.
  • Thumbnail Image
    Quantification of Demand-Supply Balancing Capacity among Prosumers and Consumers: Community Self-Sufficiency Assessment for Energy Trading
    Afzalan, Milad; Jazizadeh, Farrokh (MDPI, 2021-07-17)
    With the increased adoption of distributed energy resources (DERs) and renewables, such as solar panels at the building level, consumers turn into prosumers with generation capability to supply their on-site demand. The temporal complementarity between supply and demand at the building level provides opportunities for energy exchange between prosumers and consumers towards community-level self-sufficiency. Investigating different aspects of community-level energy exchange in cyber and physical layers has received attention in recent years with the increase in renewables adoption. In this study, we have presented an in-depth investigation into the impact of energy exchange through the quantification of temporal energy deficit–surplus complementarity and its associated self-sufficiency capacities by considering the impact of variations in community infrastructure configurations, variations in household energy use patterns, and the potential for user adaptation for load flexibility. To this end, we have adopted a data-driven simulation using real-world data from a case-study neighborhood consisting of ~250 residential buildings in Austin, TX with a mix of prosumers and consumers and detailed data on decentralized DERs. By accounting for the uncertainties in energy consumption patterns across households, different levels of PV and energy storage integration, and different modalities of user adaptation, various scenarios of operations were simulated. The analysis showed that with PV integration of more than 75%, energy exchange could result in self-sufficiency for the entire community during peak generation hours from 11 a.m. to 3 p.m. However, there are limited opportunities for energy exchange during later times with PV-standalone systems. As a potential solution, leveraging building-level storage or user adaptation for load shedding/shifting during the 2-h low-generation timeframe (i.e., 5–7 p.m.) was shown to increase community self-sufficiency during generation hours by 17% and 5–10%, respectively, to 83% and 71–76%.
  • Thumbnail Image
    Two-Stage Clustering of Household Electricity Load Shapes for Improved Temporal Pattern Representation
    Afzalan, Milad; Jazizadeh, Farrokh; Eldardiry, Hoda (IEEE, 2021-11-16)
    With the widespread adoption of smart meters in buildings, an unprecedented amount of high-resolution energy data is released, which provides opportunities to understand building consumption patterns. Accordingly, research efforts have employed data analytics and machine learning methods to segment customers based on their load profiles, which help utilities and energy providers promote customized/ personalized targeting for energy programs. Existing energy consumption segmentation techniques use assumptions that could reduce clusters' quality in representing their members. Therefore, in this paper, we investigated a two-stage clustering method for capturing more representative load shape temporal patterns and peak demands through a cluster merging approach. In the first stage, load shapes are clustered (using classical clustering algorithms) by allowing a large number of clusters to accurately capture variations in energy use patterns, and cluster centroids are extracted by accounting for limited shape misalignment within the range of Demand Response (DR) timeframes. In the second stage, clusters with similar centroids and power magnitude ranges are merged using Complexity-Invariant Dynamic Time Warping. We used three datasets consisting of ~250 households (~15000 profiles) to demonstrate the efficacy of the framework, compared to baseline methods, and discuss the impact on energy management. The proposed investigated merging-based clustering also increased correlation between cluster centroids and the corresponding members by 3-9% for different datasets.