{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T05:08:52Z","timestamp":1770268132503,"version":"3.49.0"},"reference-count":59,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2018,8,2]],"date-time":"2018-08-02T00:00:00Z","timestamp":1533168000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Existing works in photovoltaic (PV) power generation focus on accurately predicting the PV power output on a forecast horizon. As the solar power generation is heavily influenced by meteorological conditions such as solar radiation, the weather forecast is a critical input in the prediction performance. However, the weather forecast is traditionally considered to have coarse granularity, so many are compelled to use on-site meteorological sensors to complement it. However, the approach involving on-site sensors has several issues. First, it incurs the cost in the installation, operation, and management of the sensors. Second, the physical model of the sensor dynamics itself can be a source of forecast errors. Third, it requires an accumulation of sensory data that represent all seasonal variations, which takes time to collect. In this paper, we take an alternative approach to use a relatively large deep neural network (DNN) instead of the on-site sensors to cope with the coarse-grained weather forecast. With historical PV output power data from our grid-connected building with a rooftop PV power generation facility and the publicly available weather forecast history data, we demonstrate that we can train a six-layer feedforward DNN for the day-ahead forecast. It achieves the average mean absolute error (MAE) of 2.9%, comparable to that of the conventional model, but without involing the on-site sensors.<\/jats:p>","DOI":"10.3390\/s18082529","type":"journal-article","created":{"date-parts":[[2018,8,3]],"date-time":"2018-08-03T03:03:15Z","timestamp":1533265395000},"page":"2529","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":43,"title":["Sensorless PV Power Forecasting in Grid-Connected Buildings through Deep Learning"],"prefix":"10.3390","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4735-1353","authenticated-orcid":false,"given":"Junseo","family":"Son","sequence":"first","affiliation":[{"name":"B2B Solution R&amp;D Center, CTO, LG Electronics, 51, Gasan digital 1-ro, Geumcheon-gu, Seoul 08592, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongtae","family":"Park","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Korea University, Anam-Dong, Sungbuk-gu, Seoul 02841, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junu","family":"Lee","sequence":"additional","affiliation":[{"name":"B2B Solution R&amp;D Center, CTO, LG Electronics, 51, Gasan digital 1-ro, Geumcheon-gu, Seoul 08592, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9622-8469","authenticated-orcid":false,"given":"Hyogon","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Korea University, Anam-Dong, Sungbuk-gu, Seoul 02841, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2018,8,2]]},"reference":[{"key":"ref_1","unstructured":"Gaspar, R. (2018, August 01). How Solar PV is Winning over CSP. Renewable Energy World. Available online: https:\/\/www.renewableenergyworld.com\/ugc\/articles\/2013\/03\/how-solar-pv-is-winning-over-csp.html."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Sharma, N., Sharma, P., Irwin, D.E., and Shenoy, P.J. (2011, January 17\u201320). Predicting solar generation from weather forecasts using machine learning. Proceedings of the 2nd IEEE International Conference on Smart Grid Communications (SmartGridComm), Brussels, Belgium.","DOI":"10.1109\/SmartGridComm.2011.6102379"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"2856","DOI":"10.1016\/j.solener.2011.08.027","article-title":"Online 24-h solar power forecasting based on weather type classification using artificial neural network","volume":"85","author":"Chen","year":"2011","journal-title":"Sol. Energy"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1016\/j.pecs.2013.06.002","article-title":"Solar forecasting methods for renewable energy integration","volume":"39","author":"Inman","year":"2013","journal-title":"Prog. Energy Combust. Sci."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1016\/j.rser.2013.06.042","article-title":"Review of solar irradiance forecasting methods and a proposition for small-scale insular grids","volume":"27","author":"Diagne","year":"2013","journal-title":"Renew. Sustain. Energy Rev."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Monteiro, C., Fernandez-Jimenez, L., Ramirez-Rosado, I., Mun\u00f5z-Jimenez, A., and Lara-Santillan, P. (2013). Short-term forecasting models for photovoltaic plants: analytical versus soft-computing techniques. Math. Probl. Eng., 2013.","DOI":"10.1155\/2013\/767284"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1138","DOI":"10.3390\/en8021138","article-title":"A physical hybrid artificial neural network for short term forecasting of PV plant power output","volume":"8","author":"Dolara","year":"2015","journal-title":"Energies"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Soman, S., Zareipour, H., Malik, O., and Mandal, P. (2010, January 26\u201328). A review of wind power and wind speed forecasting methods with different time horizons. Proceedings of the IEEE North American Power Symposium (NAPS), Arlington, TX, USA.","DOI":"10.1109\/NAPS.2010.5619586"},{"key":"ref_9","unstructured":"Oudjana, S., Hellal, A., and Mahamed, I. (2012, January 18\u201325). Short term photovoltaic power generationn forecasting using neural network. Proceedings of the 11th international conference on environment and electrical engineering (EEEIC), Venice, Italy."},{"key":"ref_10","unstructured":"Brown, R.G. (1956). Exponential Smoothing for Predicting Demand, Arthur D. Little."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Huang, R., Huang, T., Gadh, R., and Li, N. (2012, January 5\u20138). Solar generation prediction using the ARMA model in a laboratory-level micro-grid. Proceedings of the 3rd IEEE International Conference on Smart Grid Communications (SmartGridComm), Tainan, Taiwan.","DOI":"10.1109\/SmartGridComm.2012.6486039"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Rajagopalan, S., and Santoso, S. (2009, January 26\u201330). Wind power forecasting and error analysis using the autoregressive moving average modeling. Proceedings of the IEEE Power & Energy Society General Meeting, Calgary, AB, Canada.","DOI":"10.1109\/PES.2009.5276019"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Badescu, V. (2008). Time Series Modelling of Solar Radiation. Modeling solar radiation at the earth\u2019s surface, Springer.","DOI":"10.1007\/978-3-540-77455-6"},{"key":"ref_14","unstructured":"Box, G., Jenkins, G., Reinsel, G., and Ljung, G. (2015). Time Series Analysis: Forecasting and Control, John Wiley & Sons. [5th ed.]."},{"key":"ref_15","unstructured":"Wan Ahmad, W., Ahmad, S., Ishak, A., Hashim, I., Ismail, E., and Nazar, R. (2012, January 18\u201320). Arima model and exponential smoothing method: A comparison. Proceedings of the 20th National Symposium on Mathematical Sciences: Research in Mathematical Sciences: A Catalyst for Creativity and Innovation, Putrajaya, Malaysia."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"342","DOI":"10.1016\/j.solener.2008.08.007","article-title":"Predicting solar radiation at high resolutions: A comparison of time series forecasts","volume":"83","author":"Reikard","year":"2009","journal-title":"Sol. Energy"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"342","DOI":"10.1016\/j.solener.2009.05.016","article-title":"Online short-term solar power forecasting","volume":"83","author":"Bacher","year":"2009","journal-title":"Sol. Energy"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Mori, H., and Takahashi, M. (2012, January 22\u201326). Development of GRBFN with global structure for PV generation output forecasting. Proceedings of the IEEE Power and Energy Society General Meeting, San Diego, CA, USA.","DOI":"10.1109\/PESGM.2012.6345673"},{"key":"ref_19","unstructured":"Piorno, J.R., Bergonzini, C., Atienza, D., and Rosing, T.S. (2009, January 17\u201320). Prediction and management in energy harvested wireless sensor nodes. Proceedings of the 1st International Conference on Wireless Communication, Vehicular Technology, Information Theory and Aerospace & Electronic Systems Technology (VITAE), Aalborg, Denmark."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"766","DOI":"10.1016\/j.mejo.2010.05.003","article-title":"Comparison of energy intake prediction algorithms for systems powered by photovoltaic harvesters","volume":"41","author":"Bergonzini","year":"2010","journal-title":"Microelectron. J."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1064","DOI":"10.1109\/TIA.2012.2190816","article-title":"Forecasting power output of photovoltaic systems based on weather classification and support vector machines","volume":"48","author":"Shi","year":"2012","journal-title":"IEEE Trans. Ind. Appl."},{"key":"ref_22","unstructured":"Yang, X., Ren, J., and Yue, H. (September, January 31). Photovoltaic power forecasting with a rough set combination method. Proceedings of the UKACC 11th international conference on control, Belfast, UK."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1016\/j.enbuild.2016.05.028","article-title":"Time series forecasting for building energy consumption using weighted Support Vector Regression with differential evolution optimization technique","volume":"126","author":"Zhang","year":"2016","journal-title":"Energy Build."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Cococcioni, M., D\u2019Andrea, E., and Lazzerini, B. (2011, January 22\u201324). 24-hour-ahead forecasting of energy production in solar PV systems. Proceedings of the 11th International Conference on Intelligent Systems Design and Applications (ISDA), Cordoba, Spain.","DOI":"10.1109\/ISDA.2011.6121835"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"332","DOI":"10.1016\/j.procs.2012.09.080","article-title":"Forecasting power output of solar photovoltaic system using wavelet transform and artificial intelligence techniques","volume":"12","author":"Mandal","year":"2012","journal-title":"Procedia Comput. Sci."},{"key":"ref_26","unstructured":"Mellit, A. (2009, January 26\u201329). Recurrent neural network-based forecasting of the daily electricity generation of a Photovoltaic power system. Proceedings of the 4th International Conference on Ecological Vehicle and Renewable Energy, Monte Carlo, Monaco."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1016\/j.solener.2014.11.017","article-title":"Short-term reforecasting of power output from a 48 MWe solar PV plant","volume":"112","author":"Chu","year":"2015","journal-title":"Sol. Energy"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Zhu, H., Li, X., Sun, Q., Nie, L., Yao, J., and Zhao, G. (2015). A Power Prediction Method for Photovoltaic Power Plant Based on Wavelet Decomposition and Artificial Neural Networks. Energies, 9.","DOI":"10.3390\/en9010011"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Zhu, H., Lian, W., Lu, L., Dai, S., and Hu, Y. (2017). An Improved Forecasting Method for Photovoltaic Power Based on Adaptive BP Neural Network with a Scrolling Time Window. Energies, 10.","DOI":"10.3390\/en10101542"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Yousif, J., Kazem, H.A., and Boland, J. (2017). Predictive Models for Photovoltaic Electricity Production in Hot Weather Conditions. Energies, 10.","DOI":"10.3390\/en10070971"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1016\/j.egypro.2011.09.024","article-title":"Forecasting power output of PV grid connected system in Thailand without using solar radiation measurement","volume":"9","author":"Chupong","year":"2011","journal-title":"Energy Procedia"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1016\/j.matcom.2015.05.010","article-title":"Analysis and validation of 24 hours ahead neural network forecasting of photovoltaic output power","volume":"131","author":"Leva","year":"2017","journal-title":"Math. Comput. Simul."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"406","DOI":"10.1016\/j.enconman.2015.02.052","article-title":"A hybrid method for forecasting the energy output of photovoltaic systems","volume":"95","author":"Ramsami","year":"2015","journal-title":"Energy Convers. Manag."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"527","DOI":"10.1109\/TSTE.2013.2246591","article-title":"Determination Method of Insolation Prediction With Fuzzy and Applying Neural Network for Long-Term Ahead PV Power Output Correction","volume":"4","author":"Yona","year":"2013","journal-title":"IEEE Trans. Sustain. Energy"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Gensler, A., Henze, J., Sick, B., and Raabe, N. (2016, January 9\u201312). Deep Learning for solar power forecasting\u2014An approach using AutoEncoder and LSTM Neural Networks. Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics (SMC), Budapest, Hungary.","DOI":"10.1109\/SMC.2016.7844673"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Grimaccia, F., Leva, S., Mussetta, M., and Ogliari, E. (2017). ANN Sizing Procedure for the Day-Ahead Output Power Forecast of a PV Plant. Appl. Sci., 7.","DOI":"10.3390\/app7060622"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Ogliari, E., Niccolai, A., Leva, S., and Zich, R.E. (2018). Computational Intelligence Techniques Applied to the Day Ahead PV Output Power Forecast: PHANN, SNO and Mixed. Energies, 11.","DOI":"10.3390\/en11061487"},{"key":"ref_38","unstructured":"Korea Meteorological Administration (2018, May 28). Meteorological Data Open Portal (in Korean), Available online: https:\/\/data.kma.go.kr\/cmmn\/main.do."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1109\/JSTARS.2009.2020300","article-title":"Irradiance Forecasting for the Power Prediction of Grid-Connected Photovoltaic Systems","volume":"2","author":"Lorenz","year":"2009","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Yona, A., Senjyu, T., and Funabashi, T. (2007, January 24\u201328). Application of recurrent neural network to short-term-ahead generating power forecasting for photovoltaic system. Proceedings of the IEEE Power Engineering Society General Meeting, Tampa, FL, USA.","DOI":"10.1109\/PES.2007.386072"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1016\/j.solener.2004.12.006","article-title":"A simplified model for generating sequences of global solar radiation data for isolated sites: Using artificial neural network and a library of Markov transition matrices approach","volume":"79","author":"Mellit","year":"2005","journal-title":"Sol. Energy"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Bousquet, O., von Luxburg, U., and R\u00e4tsch, G. (2004). Gaussian Processes in Machine Learning. Lecture Notes in Computer Science, vol 3176: Advanced Lectures on Machine Learning, Springer.","DOI":"10.1007\/b100712"},{"key":"ref_43","unstructured":"Lawrence Berkeley National Laboratory (2018, May 28). EnergyPlus Documentation Engineering Reference, Available online: https:\/\/energyplus.net\/sites\/default\/files\/pdfs_v8.3.0\/EngineeringReference.pdf."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"614","DOI":"10.1016\/j.solener.2008.10.008","article-title":"On the temperature dependence of photovoltaic module electrical performance: A review of efficiency\/power correlations","volume":"83","author":"Skoplaki","year":"2009","journal-title":"Sol. Energy"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"434","DOI":"10.1109\/TSTE.2014.2381224","article-title":"An Improved Photovoltaic Power Forecasting Model With the Assistance of Aerosol Index Data","volume":"6","author":"Liu","year":"2015","journal-title":"IEEE Trans. Sustain. Energy"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Achleitner, S., Kamthe, A., Liu, T., and Cerpa, A.E. (2014, January 15\u201317). SIPS: Solar Irradiance Prediction System. Proceedings of the 13th International Symposium on Information Processing in Sensor Networks, Berlin, Germany.","DOI":"10.1109\/IPSN.2014.6846755"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"651","DOI":"10.1016\/j.egypro.2017.08.293","article-title":"Forecasting of PV Power Generation using weather input data-preprocessing techniques","volume":"126","author":"Malvoni","year":"2017","journal-title":"Energy Procedia"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1049\/iet-smt.2013.0135","article-title":"Photovoltaic power forecasting using statistical methods: impact of weather data","volume":"8","author":"Congedo","year":"2014","journal-title":"IET Sci. Meas. Technol."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"808","DOI":"10.1016\/j.protcy.2016.01.053","article-title":"Solar Photovoltaic Energy Production Forecast Using Neural Networks","volume":"22","author":"Dumitru","year":"2016","journal-title":"Procedia Technol."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Yona, A., Senjyu, T., Saber, A., Funabashi, T., Sekine, H., and Kim, C.-H. (2007, January 5\u20138). Application of neural network to one-day-ahead 24h generating power forecasting for photovoltaic system. Proceedings of the IEEE International Conference on Intelligent Systems Applications to Power Systems, Niigata, Japan.","DOI":"10.1109\/ISAP.2007.4441657"},{"key":"ref_51","unstructured":"Kingma, D.P., and Ba, J. (2015, January 7\u20139). Adam: A Method for Stochastic Optimization. Proceedings of the 3rd International Conference for Learning Representations, San Diego, CA, USA."},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Abdel-Nasser, M., and Mahmoud, K. (2017). Accurate photovoltaic power forecasting models using deep LSTM-RNN. Neural Comput. Appl., 1\u201314.","DOI":"10.1007\/s00521-017-3225-z"},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"826","DOI":"10.1021\/ci00027a006","article-title":"Neural network studies. 1. Comparison of overfitting and overtraining","volume":"35","author":"Tetko","year":"1995","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"Priddy, K.L., and Keller, P.E. (2005). Artificial Neural Networks\u2014An Introduction. Tutorial Texts in Optical Engineering, vol. TT68, SPIE Press.","DOI":"10.1117\/3.633187"},{"key":"ref_55","unstructured":"Beyer, G.G., Martinez, J.P., Suri, M., Torres, J.L., Lorenz, E., Muller, S., Hoyer-Klick, C., and Ineichen, P. (2018, June 01). Benchmarking of radiation products. Mesor Report D.1.1.3. Available online: http:\/\/www.mesor.org\/docs\/MESoR_Benchmarking_of_radiation_products.pdf."},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1016\/S0038-092X(99)00064-X","article-title":"Univariate and multivariate forecasting of hourly solar radiation with artificial intelligence techniques","volume":"68","author":"Sfetsos","year":"2000","journal-title":"Sol. Energy"},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"746","DOI":"10.1016\/j.solener.2011.01.007","article-title":"Forecasting of global and direct solar irradiance using stochastic learning methods, ground experiments and the NWS database","volume":"85","author":"Marquez","year":"2011","journal-title":"Sol. Energy"},{"key":"ref_58","first-page":"1","article-title":"Photovoltaic and solar forecasting: State of the art","volume":"14","author":"Pelland","year":"2013","journal-title":"IEA PVPS Task"},{"key":"ref_59","unstructured":"Korea Meteorological Administration (2018, June 22). Climate of Korea, Available online: https:\/\/web.kma.go.kr\/eng\/biz\/climate_01.jsp."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/18\/8\/2529\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T15:16:11Z","timestamp":1760195771000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/18\/8\/2529"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,8,2]]},"references-count":59,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2018,8]]}},"alternative-id":["s18082529"],"URL":"https:\/\/doi.org\/10.3390\/s18082529","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,8,2]]}}}