The electric power grid is evolving in terms of generation, transmission and distribution network architecture. On the generation side, distributed energy resources (DER) are participating at a much larger scale. Transmission and distribution networks are transforming to a decentralized architecture from a centralized one. Residential and commercial buildings are now considered as active elements of the electric grid which can participate in grid operation through applications such as the Demand Response (DR). DR is an application through which electric power consumption during the peak demand periods can be curtailed. DR applications ensure an economic and stable operation of the electric grid by eliminating grid stress conditions. In addition to that, DR can be utilized as a mechanism to increase the participation of green electricity in an electric grid. The DR applications, in general, are passive in nature. During the peak demand periods, common practice is to shut down the operation of pre-selected electrical equipment i.e., heating, ventilation and air conditioning (HVAC) and lights to reduce power consumption. This approach, however, is not optimal and does not take into consideration any user preference. Furthermore, this does not provide any information related to demand flexibility beforehand. Under the broad concept of grid modernization, the focus is now on the applications of data analytics in grid operation to ensure an economic, stable and resilient operation of the electric grid. The work presented here utilizes data analytics in DR application that will transform the DR application from a static, look-up-based reactive function to a dynamic, context-aware proactive solution. The dynamic demand response framework presented in this dissertation performs three major functionalities: electrical load forecast, electrical load disaggregation and peak load reduction during DR periods. The building-level electrical load forecasting quantifies required peak load reduction during DR periods. The electrical load disaggregation provides equipment-level power consumption. This will quantify the available building-level demand flexibility. The peak load reduction methodology provides optimal HVAC setpoint and brightness during DR periods to reduce the peak demand of a building. The control scheme takes user preference and context into consideration. A detailed methodology with relevant case studies regarding the design process of the network architecture of a deep learning algorithm for electrical load forecasting and load disaggregation is presented. A case study regarding peak load reduction through HVAC setpoint and brightness adjustment is also presented. To ensure the scalability and interoperability of the proposed framework, a layer-based software architecture to replicate the framework within a cloud environment is demonstrated. / Doctor of Philosophy / The modern power grid, known as the smart grid, is transforming how electricity is generated, transmitted and distributed across the US. In a legacy power grid, the utilities are the suppliers and the residential or commercial buildings are the consumers of electricity. However, the smart grid considers these buildings as active grid elements which can contribute to the economic, stable and resilient operation of an electric grid. Demand Response (DR) is a grid application that reduces electrical power consumption during peak demand periods. The objective of DR application is to reduce stress conditions of the electric grid. The current DR practice is to shut down pre-selected electrical equipment i.e., HVAC, lights during peak demand periods. However, this approach is static, pre-fixed and does not consider any consumer preference. The proposed framework in this dissertation transforms the DR application from a look-up-based function to a dynamic context-aware solution. The proposed dynamic demand response framework performs three major functionalities: electrical load forecasting, electrical load disaggregation and peak load reduction. The electrical load forecasting quantifies building-level power consumption that needs to be curtailed during the DR periods. The electrical load disaggregation quantifies demand flexibility through equipment-level power consumption disaggregation. The peak load reduction methodology provides actionable intelligence that can be utilized to reduce the peak demand during DR periods. The work leverages functionalities of a deep learning algorithm to increase forecasting accuracy. An interoperable and scalable software implementation is presented to allow integration of the framework with existing energy management systems.

Submitted by Renata Lopes (renatasil82@gmail.com) on 2017-03-02T12:24:39Z No. of bitstreams: 1 annaclaudiamancinidasilvacarneiro.pdf: 1333903 bytes, checksum: a7b3819bb5b0e1adb8efd07bca0f9aa2 (MD5) / Approved for entry into archive by Adriana Oliveira (adriana.oliveira@ufjf.edu.br) on 2017-03-06T19:35:55Z (GMT) No. of bitstreams: 1 annaclaudiamancinidasilvacarneiro.pdf: 1333903 bytes, checksum: a7b3819bb5b0e1adb8efd07bca0f9aa2 (MD5) / Made available in DSpace on 2017-03-06T19:35:55Z (GMT). No. of bitstreams: 1 annaclaudiamancinidasilvacarneiro.pdf: 1333903 bytes, checksum: a7b3819bb5b0e1adb8efd07bca0f9aa2 (MD5) Previous issue date: 2014-09-26 / CAPES - Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / A previsão de cargas elétricas é fundamental para o planejamento das empresas de energia. O foco deste estudo são as previsões a curto prazo; assim, aplicamos métodos univariados de previsão de séries temporais a uma série real de cargas elétricas de 104 semanas no Rio de Janeiro, nos anos de 1996 e 1997, e experimentamos várias combinações dos métodos de melhor desempenho. As combinações foram feitas pelo método outperformance, uma combinação linear simples, com pesos fixos. Os resultados das combinações foram comparados ao de simulações de redes neurais artificiais que solucionam o mesmo problema, e ao resultado de um método de amortecimento de dupla sazonalidade aditiva. No geral, este método de amortecimento obteve os melhores resultados, e talvez seja o mais adequado e confiável para aplicações práticas, embora necessite de melhorias para garantir a extração completa da informação contida nos dados. / Forecasting the demand for electric power is crucial for the production planning in energy utilities. The focus of this study are the short-term forecasts. We apply univariate time series methods to the forecasting of a series containing observations of the energy consumption of 104 weeks in Rio de Janeiro, in 1996 and 1997, and experiment with several combinations of the methods which have the best performance. These combinations are done by the outperformance method, a simple linear combination with fixed weights. The results were compared to those obtained by neural networks on the same problem, and with the results of a exponential smoothing method for dual additive seasonality. Overall, the exponential smoothing method achieved the best results, and was shown to be perhaps the most reliable and suitable for practical applications, even though it needs improvements to ensure complete extraction of the information contained in the data.

In the last 10 years, no significant increase in the peak electricity consumption of the region of Stockholm has been observed, despite new customers being connected to the grid. But, as urbanization continues and with electrification being a decisive step of decarbonization pathways, more growth is expected in the future. However, the Swedish Transmission System Operator (TSO), Svenska Kraftnat, can only supply a limited power to Stockholm region. Distribution System Operators (DSOs) such as Vattenfall Eldistribution, which operates two thirds Stockholm region's distribution grid, need to find solutions to satisfy an increasing demand with a limited power supply. In these times, forecasting the worst-case scenarios, i.e., the highest possible loads, becomes a critical question. In Sweden, peak loads are usually triggered by the coldest temperatures, but the recent winters have been mild: this brings uncertainty about a possible underlying temperature adjusted growth that would be masked by relatively warm winters. Answering the question 'What would be the highest loads in 2022 with -20°C in Stockholm region ?' could help Vattenfall Eldistribution estimating the flexibility needed nowadays and designing the future grid with the necessary grid reinforcements. This master thesis uses a data-driven approach based on eleven years of hourly data on the period 2010-2021 to investigate the temperature sensitivity of aggregated electricity load in Stockholm region. First, an exploratory analysis aims at quantifying how large the growth has been in the past ten years and at understanding how and when peak loads occur. The insights obtained help design two innovative regression techniques that investigate the evolution of the loads across years and provide first estimates of peak loads. Then, a Seasonal Autoregressive Integrated Moving Average with eXogenous regressors (SARIMAX) process is used to model a full winter of load as a function of temperatures. This third method provides new and more reliable estimates of peak loads in 2022 at e.g. -20°C. Eventually, the SARIMAX estimates are kept and a synthesis of the global outlooks of the three methods and possible extensions of the SARIMAX method is presented in a final section. The results conclude on a significant increase in the load levels in southern Stockholm ('Stockholm Sodra') between 2010 and 2015 and stable evolution onwards, while the electric consumption in Northern Stockholm remained stable during the period 2010-2021. During a very cold winter, the electricity demand is expected to exceed the subscription levels during about 300h in Stockholm Sodra and 200h in Stockholm Norra. However, this will be a rare occurrence, which suggests that short-term solutions could be privileged rather than costly grid extension work. Many questions arise, and the capability of local heat & power production and electricity prices signals to regulate today's demand are yet to investigate. Additional work exploring future demand scenarios at a smaller scale could also be contemplated. / Under den senaste årtionden har Stockholms toppkonsumtion av el inte ökat markant trots nya elkunder som ansluter till elnätet. Med en snabb urbanisering, är ökad elektrifiering en huvudlösning för att uppnå ett fossilfritt samhälle och denna trend förväntas fortsätta under kommande årtionden. Samtidigt börjar den svenska transmissionsnätoperatören (TSO) Svenska kraftnät få problem med att leverera elkraft till Stockholmsregionen, på grund av en begränsad överföringskapacitet. Därför måste lokala eldistributörer (DSO), liksom Vattenfall Eldistribution, som är Sveriges största DSO med systemansvar för distributionssystem, undersöka nya lösningar för att uppfylla den ökande efterfrågan på el. Det blir dessutom mycket viktigt att identifiera de värsta tänkbara scenario, som att göra prognos av högsta möjliga elförbrukning. Stockholm konsumerar exempelvis mest el när det är som kallast – men de senaste vintrarna har varit milda jämfört med till exempel vintrarna 2010 – 2011 eller 2012 – 2013 då temperaturer i Stockholmsregion mättes till under -20°C grader för flera dagar i sträck. Detta resulterar i en relevant frågeställning: ” Vad skulle Stockholms elkonsumtion vid -20°C bli 2021 eller 2022?”. Att kvantitativt kunna besvara denna fråga skulle hjälpa Vattenfall med att designa framtidens elnät samt se till att det finns rätt mängd flexibilitet i reserv i nuvarande Stockholm Flex elmarknad. Detta examensarbete utgår från att kvantitativt analysera denna frågeställning. Utgångsläget är ett datadrivet tillvägagångssätt baserat på tio års tidseriedata för att undersöka temperaturkänsligheten för det aggregerade elbehovet i Stockholmsregionen, och dra slutsatser om dess utveckling genom åren. I första hand, utförs en explorativ analys för att förstå när och hur toppbelastning kan hända. Då hjälper dessa insikter till att utforma två innovativa regressionsmetoder för att undersöka utvecklingen av elförbrukning under det senaste decenniet och uppskatta värdet på toppbelastningen. Därefter används ett säsongmässigt autoregressivt integrerat rörligt genomsnitt med exogena faktorer (SARIMAX) för att modellera en vinter som en funktion av temperaturerna. Denna tredje metod behandlar nya och mer tillförlitliga beräkningar av toppbelastning värden i 2022 på -20°C. Huvudslutsatser från examensarbetet är att elförbrukningen skulle öka i området Stockholm Södra speciellt mellan 2010 och 2015, medan elförbrukningen skulle vara stabil under hela perioden i området Stockholm Norra. Det finns en risk för att under ett antal timmar vid riktigt kall vinter, ha ett elbehov högre än Vattenfall Eldistributions summa av abonnemang. Dock är det väldigt låg sannolikhet att detta händer, vilket innebär att det förmodligen finns andra sätt att hantera denna efterfråga på el än att öka överföringskapaciteten i elnätet. Examensarbetet resulterar i flera frågor. Exempelvis att utreda möjligheter i att utnyttja lokala el och värmekraftverk och använda elprissignaler. Ytterligare arbete kan också undersöka scenarier av den framtida elförbrukning i en mindre skala.