Sebastian Fredriksson, Lackis Eleftheriadis, Rickard Brännvall, Nils Bäckman, Jonas Gustafsson
As the demand for data privacy and low latency grows, edge computation carried out at edge data center nodes is believed to become increasingly important for future telecom applications. Providers must consider various factors, including power consumption, thermal dynamics, and the ability to maintain high-quality service, in addition to deployment and service orchestration. This paper presents a detailed description of two different prototype edge data centers designed to investigate the power performance and thermal dynamics of edge nodes under various applied services. The prototypes were developed and tested at the RISE ICE Datacenter research facility. We present the results of power flow experiments in which input current from the grid was limited while the computational load was maintained using the energy stored in batteries. We further discuss implications for placing edge data center nodes in locations with temporal power constraints and opportunities for participation in support services at the grid level.
{"title":"ANIARA: Experimental Investigation of Micro Edge Data Centers with Battery Support on Power-Constrained Grids","authors":"Sebastian Fredriksson, Lackis Eleftheriadis, Rickard Brännvall, Nils Bäckman, Jonas Gustafsson","doi":"10.1145/3599733.3600252","DOIUrl":"https://doi.org/10.1145/3599733.3600252","url":null,"abstract":"As the demand for data privacy and low latency grows, edge computation carried out at edge data center nodes is believed to become increasingly important for future telecom applications. Providers must consider various factors, including power consumption, thermal dynamics, and the ability to maintain high-quality service, in addition to deployment and service orchestration. This paper presents a detailed description of two different prototype edge data centers designed to investigate the power performance and thermal dynamics of edge nodes under various applied services. The prototypes were developed and tested at the RISE ICE Datacenter research facility. We present the results of power flow experiments in which input current from the grid was limited while the computational load was maintained using the energy stored in batteries. We further discuss implications for placing edge data center nodes in locations with temporal power constraints and opportunities for participation in support services at the grid level.","PeriodicalId":114998,"journal":{"name":"Companion Proceedings of the 14th ACM International Conference on Future Energy Systems","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131262787","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
P2P energy trading often utilizes a permissionless blockchain platform for energy credit tokenization and trading. However, permissionless blockchain suffers from slow transaction confirmation time, poor scalability, high transaction fees for micro-payment, and the need for persistent online connections. Therefore, we develop a cost-effective off-chain micro-payment solution to support offline transactions of energy credit tokens without persistent connections to blockchain, in a similar vein as off-chain payment channels for cryptocurrencies (e.g., Lightning Network). But unlike cryptocurrencies, off-chain trading of energy credit tokens faces a new challenge. Since energy credit tokens are usually generated ex-post from delayed smart meter reporting, real-time P2P energy applications would need to cope with yet-to-be-realized energy credit tokens at the moment of trading, which significantly increases the counterparty risks among untrusted users. Therefore, we propose a secure off-chain payment channel protocol to effectively mitigate the counterparty risks in P2P energy applications.
{"title":"Efficient Off-chain Micro-payment Systems for Blockchain-based P2P Energy Trading","authors":"Nan Wang, S. Chau","doi":"10.1145/3599733.3606299","DOIUrl":"https://doi.org/10.1145/3599733.3606299","url":null,"abstract":"P2P energy trading often utilizes a permissionless blockchain platform for energy credit tokenization and trading. However, permissionless blockchain suffers from slow transaction confirmation time, poor scalability, high transaction fees for micro-payment, and the need for persistent online connections. Therefore, we develop a cost-effective off-chain micro-payment solution to support offline transactions of energy credit tokens without persistent connections to blockchain, in a similar vein as off-chain payment channels for cryptocurrencies (e.g., Lightning Network). But unlike cryptocurrencies, off-chain trading of energy credit tokens faces a new challenge. Since energy credit tokens are usually generated ex-post from delayed smart meter reporting, real-time P2P energy applications would need to cope with yet-to-be-realized energy credit tokens at the moment of trading, which significantly increases the counterparty risks among untrusted users. Therefore, we propose a secure off-chain payment channel protocol to effectively mitigate the counterparty risks in P2P energy applications.","PeriodicalId":114998,"journal":{"name":"Companion Proceedings of the 14th ACM International Conference on Future Energy Systems","volume":"137 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133731713","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Improving our ability to model, predict, and understand power system dynamics is becoming increasingly important as we face the challenges of transitioning to a carbon-neutral energy system. The power grid frequency is central to power system control as it is the primary observable for balancing generation and demand on short time scales. By facilitating frequency control actions, accurate prediction of grid frequency can improve system stability. In recent years, promising new deep learning techniques for time series forecasting tasks have emerged. Here, we explore the application of structured state space models (S4) to high-resolution power system frequency time series. S4 models have previously demonstrated good performance for long-term dependence tasks, but how useful are they for high-resolution energy time series?
{"title":"Forecasting Power Grid Frequency Trajectories with Structured State Space Models","authors":"Sebastian Pütz, Benjamin Shäfer","doi":"10.1145/3599733.3606298","DOIUrl":"https://doi.org/10.1145/3599733.3606298","url":null,"abstract":"Improving our ability to model, predict, and understand power system dynamics is becoming increasingly important as we face the challenges of transitioning to a carbon-neutral energy system. The power grid frequency is central to power system control as it is the primary observable for balancing generation and demand on short time scales. By facilitating frequency control actions, accurate prediction of grid frequency can improve system stability. In recent years, promising new deep learning techniques for time series forecasting tasks have emerged. Here, we explore the application of structured state space models (S4) to high-resolution power system frequency time series. S4 models have previously demonstrated good performance for long-term dependence tasks, but how useful are they for high-resolution energy time series?","PeriodicalId":114998,"journal":{"name":"Companion Proceedings of the 14th ACM International Conference on Future Energy Systems","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126014593","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A. Golovin, Robert Basmadjian, S. Astafiev, A. Rumyantsev
Data centers can participate in demand-response schemes by reducing their demand, however, at the expense of the agreed-upon performance of their IT services defined by the SLAs. The successful application of such schemes necessitates a careful analysis so that the amount of degradation of the SLAs with respect to power savings can be quantified helping the data center operators to set up the optimal configuration. In this paper, we study and analyze a system consisting of a data center, its operator, and IT clients under the consideration of relaxed SLAs. For this purpose, we consider a data center system consisting of two heterogeneous pools of servers, where each server is modeled using the single-server system with a power-saving inactive state, non-zero (random) activation/deactivation times, and hot standby state. Making use of the distributional Little’s Law, derive the steady-state performance (in terms of response time distribution) and average power demand and study the power-performance trade-off in an explicit way. Numerical results illustrate the model’s theoretical properties, under different considerations of low, medium, and high workload utilization rates.
{"title":"Little’s Law in a Single-Server System with Inactive State for Demand-Response in Data Centers with Green SLAs","authors":"A. Golovin, Robert Basmadjian, S. Astafiev, A. Rumyantsev","doi":"10.1145/3599733.3600255","DOIUrl":"https://doi.org/10.1145/3599733.3600255","url":null,"abstract":"Data centers can participate in demand-response schemes by reducing their demand, however, at the expense of the agreed-upon performance of their IT services defined by the SLAs. The successful application of such schemes necessitates a careful analysis so that the amount of degradation of the SLAs with respect to power savings can be quantified helping the data center operators to set up the optimal configuration. In this paper, we study and analyze a system consisting of a data center, its operator, and IT clients under the consideration of relaxed SLAs. For this purpose, we consider a data center system consisting of two heterogeneous pools of servers, where each server is modeled using the single-server system with a power-saving inactive state, non-zero (random) activation/deactivation times, and hot standby state. Making use of the distributional Little’s Law, derive the steady-state performance (in terms of response time distribution) and average power demand and study the power-performance trade-off in an explicit way. Numerical results illustrate the model’s theoretical properties, under different considerations of low, medium, and high workload utilization rates.","PeriodicalId":114998,"journal":{"name":"Companion Proceedings of the 14th ACM International Conference on Future Energy Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130648359","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Natural gas is one of Europe’s main sources of energy and Europe is heavily dependent on imports from foreign countries. Since the imports from the main energy supplier Russia decreased massively due to the war in 2022, European authorities called for savings. Therefore the German Bundesnetzagentur publishes a temperature-adjusted reference consumption to measure these savings in Germany. However, the temperature adjustment is only done by looking for previous days with a similar temperature and using their consumption as a reference value. In this paper, we investigate the natural gas savings of private households for the example of Germany in 2022. We study several alternative filtering and a machine-learning approach to calculate the temperature-adjusted reference consumption. Besides the pure temperature information, we propose to further enrich the data with integral and derivative elements inspired by PID controllers originally stemming from electrical engineering. Our developed framework adaptively adjusting for temperature is new in the literature and may be easily applied to other use cases, such as individual buildings’ consumption, or transferred to variables other than gas consumption.
{"title":"Realtime temperature-adjusted natural gas savings of European private households: A study on the German gas market in 2022","authors":"Fabian Kächele, O. Grothe","doi":"10.1145/3599733.3600246","DOIUrl":"https://doi.org/10.1145/3599733.3600246","url":null,"abstract":"Natural gas is one of Europe’s main sources of energy and Europe is heavily dependent on imports from foreign countries. Since the imports from the main energy supplier Russia decreased massively due to the war in 2022, European authorities called for savings. Therefore the German Bundesnetzagentur publishes a temperature-adjusted reference consumption to measure these savings in Germany. However, the temperature adjustment is only done by looking for previous days with a similar temperature and using their consumption as a reference value. In this paper, we investigate the natural gas savings of private households for the example of Germany in 2022. We study several alternative filtering and a machine-learning approach to calculate the temperature-adjusted reference consumption. Besides the pure temperature information, we propose to further enrich the data with integral and derivative elements inspired by PID controllers originally stemming from electrical engineering. Our developed framework adaptively adjusting for temperature is new in the literature and may be easily applied to other use cases, such as individual buildings’ consumption, or transferred to variables other than gas consumption.","PeriodicalId":114998,"journal":{"name":"Companion Proceedings of the 14th ACM International Conference on Future Energy Systems","volume":"146 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130661341","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Forecasting electricity demand plays a critical role in ensuring reliable and cost-efficient operation of the electricity supply. With the global transition to distributed renewable energy sources and the electrification of heating and transportation, accurate load forecasts become even more important. While numerous empirical studies and a handful of review articles exist, there is surprisingly little quantitative analysis of the literature, most notably none that identifies the impact of factors on forecasting performance across the entirety of empirical studies. In this article, we therefore present a Meta-Regression Analysis (MRA) that examines factors that influence the accuracy of short-term electricity load forecasts. We use data from 421 forecast models published in 59 studies. While the grid level (esp. individual vs. aggregated vs. system), the forecast granularity, and the algorithms used seem to have a significant impact on the MAPE, bibliometric data, dataset sizes, and prediction horizon show no significant effect. We found the LSTM approach and a combination of neural networks with other approaches to be the best forecasting methods. The results help practitioners and researchers to make meaningful model choices. Yet, this paper calls for further MRA in the field of load forecasting to close the blind spots in research and practice of load forecasting.
{"title":"Meta-Regression Analysis of Errors in Short-Term Electricity Load Forecasting","authors":"K. Hopf, Hannah Hartstang, T. Staake","doi":"10.1145/3599733.3600248","DOIUrl":"https://doi.org/10.1145/3599733.3600248","url":null,"abstract":"Forecasting electricity demand plays a critical role in ensuring reliable and cost-efficient operation of the electricity supply. With the global transition to distributed renewable energy sources and the electrification of heating and transportation, accurate load forecasts become even more important. While numerous empirical studies and a handful of review articles exist, there is surprisingly little quantitative analysis of the literature, most notably none that identifies the impact of factors on forecasting performance across the entirety of empirical studies. In this article, we therefore present a Meta-Regression Analysis (MRA) that examines factors that influence the accuracy of short-term electricity load forecasts. We use data from 421 forecast models published in 59 studies. While the grid level (esp. individual vs. aggregated vs. system), the forecast granularity, and the algorithms used seem to have a significant impact on the MAPE, bibliometric data, dataset sizes, and prediction horizon show no significant effect. We found the LSTM approach and a combination of neural networks with other approaches to be the best forecasting methods. The results help practitioners and researchers to make meaningful model choices. Yet, this paper calls for further MRA in the field of load forecasting to close the blind spots in research and practice of load forecasting.","PeriodicalId":114998,"journal":{"name":"Companion Proceedings of the 14th ACM International Conference on Future Energy Systems","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129469338","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Recent years have seen a rich literature of data-driven approaches designed for power grid applications. However, insufficient consideration of domain knowledge can impose a high risk to the practicality of the methods. Specifically, ignoring the grid-specific spatiotemporal patterns (in load, generation, and topology, etc.) can lead to outputting infeasible, unrealizable, or completely meaningless predictions on new inputs. To address this concern, this paper investigates real-world operational data to provide insights into power grid behavioral patterns, including the time-varying topology, load, and generation, as well as the spatial differences (in peak hours, diverse styles) between individual loads and generations. Then based on these observations, we evaluate the generalization risks in some existing ML works caused by ignoring these grid-specific patterns in model design and training.
{"title":"Power Grid Behavioral Patterns and Risks of Generalization in Applied Machine Learning","authors":"Shimiao Li, Ján Drgoňa, S. Abhyankar, L. Pileggi","doi":"10.1145/3599733.3600257","DOIUrl":"https://doi.org/10.1145/3599733.3600257","url":null,"abstract":"Recent years have seen a rich literature of data-driven approaches designed for power grid applications. However, insufficient consideration of domain knowledge can impose a high risk to the practicality of the methods. Specifically, ignoring the grid-specific spatiotemporal patterns (in load, generation, and topology, etc.) can lead to outputting infeasible, unrealizable, or completely meaningless predictions on new inputs. To address this concern, this paper investigates real-world operational data to provide insights into power grid behavioral patterns, including the time-varying topology, load, and generation, as well as the spatial differences (in peak hours, diverse styles) between individual loads and generations. Then based on these observations, we evaluate the generalization risks in some existing ML works caused by ignoring these grid-specific patterns in model design and training.","PeriodicalId":114998,"journal":{"name":"Companion Proceedings of the 14th ACM International Conference on Future Energy Systems","volume":"2506 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131283180","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sebastian Pütz, Johannes Kruse, D. Witthaut, V. Hagenmeyer, B. Schäfer
A stable supply of electrical energy is essential for the functioning of our society. Therefore, energy and balancing markets of power grids are strictly regulated. With changes in technology, the economy and society, these regulations are also constantly adapted. However, whether these regulatory changes lead to the intended results is not easy to assess. Could eXplainable Artificial Intelligence (XAI) models distinguish regulatory settings and support the understanding of the effects of these changes? In this article, we explore two examples of regulatory changes: The splitting of the German-Austrian bidding zone and changes in the pricing schemes of the German balancing energy market. We find that boosted tree models and feedforward neural networks before and after a regulatory change differ in their respective parametrizations. Using Shapley additive explanations, we reveal model differences, e.g., in terms of feature importance, and identify key features of these distinct models. With this study, we demonstrate how XAI can be applied to investigate system changes in power systems.
{"title":"Regulatory Changes in German and Austrian Power Systems Explored with Explainable Artificial Intelligence","authors":"Sebastian Pütz, Johannes Kruse, D. Witthaut, V. Hagenmeyer, B. Schäfer","doi":"10.1145/3599733.3600247","DOIUrl":"https://doi.org/10.1145/3599733.3600247","url":null,"abstract":"A stable supply of electrical energy is essential for the functioning of our society. Therefore, energy and balancing markets of power grids are strictly regulated. With changes in technology, the economy and society, these regulations are also constantly adapted. However, whether these regulatory changes lead to the intended results is not easy to assess. Could eXplainable Artificial Intelligence (XAI) models distinguish regulatory settings and support the understanding of the effects of these changes? In this article, we explore two examples of regulatory changes: The splitting of the German-Austrian bidding zone and changes in the pricing schemes of the German balancing energy market. We find that boosted tree models and feedforward neural networks before and after a regulatory change differ in their respective parametrizations. Using Shapley additive explanations, we reveal model differences, e.g., in terms of feature importance, and identify key features of these distinct models. With this study, we demonstrate how XAI can be applied to investigate system changes in power systems.","PeriodicalId":114998,"journal":{"name":"Companion Proceedings of the 14th ACM International Conference on Future Energy Systems","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126615237","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Companion Proceedings of the 14th ACM International Conference on Future Energy Systems","authors":"","doi":"10.1145/3599733","DOIUrl":"https://doi.org/10.1145/3599733","url":null,"abstract":"","PeriodicalId":114998,"journal":{"name":"Companion Proceedings of the 14th ACM International Conference on Future Energy Systems","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122715047","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：