Load Forecasting in an Office Building with Different Data Structure and Learning Parameters

Energy efficiency topics have been covered by several energy management approaches in the literature, including participation in demand response programs where the consumers provide load reduction upon request or price signals. In such approaches, it is very important to know in advance the electricity consumption for the future to adequately perform the energy management. In the present paper, a load forecasting service designed for office buildings is implemented. In the building, using several available sensors, different learning parameters and structures are tested for artificial neural networks and the K-nearest neighbor algorithm. Deep focus is given to the individual period errors. In the case study, the forecasting of one week of electricity consumption is tested. It has been concluded that it is impossible to identify a single combination of learning parameters as different parts of the day have different consumption patterns.

[1]  Omid Abrishambaf,et al.  Application of an optimization-based curtailment service provider in real-time simulation , 2018 .

[2]  Ali P. Yunus,et al.  Machine learning methods for landslide susceptibility studies: A comparative overview of algorithm performance , 2020 .

[3]  Abdulkadir Sengür,et al.  Machine learning methods for cyber security intrusion detection: Datasets and comparative study , 2021, Comput. Networks.

[4]  Xiaofeng Guo,et al.  Modeling and forecasting building energy consumption: A review of data-driven techniques , 2019, Sustainable Cities and Society.

[5]  Shrawan Kumar Trivedi.  A study on credit scoring modeling with different feature selection and machine learning approaches , 2020 .

[6]  Marimuthu Palaniswami,et al.  Demand Response Architectures and Load Management Algorithms for Energy-Efficient Power Grids: A Survey , 2012, 2012 Seventh International Conference on Knowledge, Information and Creativity Support Systems.

[7]  Terry Jones,et al.  Modeling and validation of an unbalanced LV network using Smart Meter and SCADA inputs , 2013, IEEE 2013 Tencon - Spring.

[8]  B. Kuri,et al.  Allocation of emission allowances to effectively reduce emissions in electricity generation , 2009, 2009 IEEE Power & Energy Society General Meeting.

[9]  Z. Vale,et al.  Demand response in electrical energy supply: An optimal real time pricing approach , 2011 .

[10]  Tanveer Ahmad,et al.  A review on renewable energy and electricity requirement forecasting models for smart grid and buildings , 2020 .

[11]  Pedro Faria,et al.  Demonstration of an Energy Consumption Forecasting System for Energy Management in Buildings , 2019, EPIA.

[12]  Antonio F. Gómez-Skarmeta,et al.  A methodology for energy multivariate time series forecasting in smart buildings based on feature selection , 2019, Energy and Buildings.

[13]  Michela Longo,et al.  Internet of Things for Power and Energy Systems Applications in Buildings: An Overview , 2020, 2020 IEEE International Conference on Environment and Electrical Engineering and 2020 IEEE Industrial and Commercial Power Systems Europe (EEEIC / I&CPS Europe).

[14]  Ismail Shah,et al.  Modeling and Forecasting Medium-Term Electricity Consumption Using Component Estimation Technique , 2020 .

[15]  Zita Vale,et al.  Distribution system operation supported by contextual energy resource management based on intelligent SCADA , 2013 .

[16]  Emanuele Ogliari,et al.  Electrical Load Forecast by Means of LSTM: The Impact of Data Quality , 2021, Forecasting.

[17]  Chen Huanxin,et al.  Smart energy forecasting strategy with four machine learning models for climate-sensitive and non-climate sensitive conditions , 2020 .

[18]  Haris Ch. Doukas,et al.  An Advanced IoT-based System for Intelligent Energy Management in Buildings , 2018, Sensors.

[19]  Pedro Faria,et al.  Use of Sensors and Analyzers Data for Load Forecasting: A Two Stage Approach , 2020, Sensors.

[20]  Luis Gomes,et al.  An Intelligent Smart Plug with Shared Knowledge Capabilities , 2018, Sensors.

[21]  E. Snitkin,et al.  Forest and Trees: Exploring Bacterial Virulence with Genome-wide Association Studies and Machine Learning. , 2021, Trends in microbiology.

[22]  Zita Vale,et al.  Constrained consumption shifting management in the distributed energy resources scheduling considering demand response , 2015 .

[23]  Zita Vale,et al.  A Demand Response Approach to Scheduling Constrained Load Shifting , 2019, Energies.

[24]  Marcel Antal,et al.  Blockchain Based Decentralized Management of Demand Response Programs in Smart Energy Grids , 2018, Sensors.

[25]  Y. Ueki,et al.  Short-term load forecasting by artificial neural networks using individual and collective data of preceding years , 1993, [1993] Proceedings of the Second International Forum on Applications of Neural Networks to Power Systems.

[26]  Jiang Du,et al.  Model predictive control of commercial buildings in demand response programs in the presence of thermal storage , 2019, Journal of Cleaner Production.

[27]  Mousa Marzband,et al.  A real-time evaluation of energy management systems for smart hybrid home Microgrids , 2017 .