The results presented demonstrate that all prediction methods , when integrated with the optimization model , can offer benefits to prosumers and save electricity expenses nearly the same as with the case using ideal prediction values . This allows prosumers to take advantage of optimization benefits effectively .
VI . CONCLUSION
The methodology employed in the study includes various phases such as load and PV yield forecasting , and optimization of battery charge / discharge control . Several forecasting models were utilized and compared objectively using a model comparison framework . This ensured equal testing and prevention of data leakage . Conventional evaluation metrics like MSE and MAE were used , and two novel metrics , ACDE and PWMSE , were introduced to cater to specific project needs . Authentic load profiles from the Open Fluvius dataset were used , which required a pre-processing algorithm to address missing data , duplicates , and inaccurate time intervals . The study investigated the effectiveness of an optimal battery management system ( BMS ) in reducing prosumers ’ electricity bills by employing predicted PV output and load data . The economic evaluation of a PV panel system with battery storage while considering different tariff structures was a primary goal . The study examined the impact of PV systems and batteries on consumer ’ s electricity bills , revealing that employing a suitable control system and integrating batteries could lower the monthly electricity cost by 44 %.
The optimal charging / discharging of the battery using load and PV yield predictions from artificial intelligence was also analyzed . The results showed that incorporating PV predicted values into the optimization model could lead to an error of approximately 9 %, but when both PV and load predictions were added , the error ranged from 10-14 %, which is still considered acceptable . These findings emphasize the significant impact of PV yield predictions on consumers ’ electricity savings and the importance of selecting the prediction method carefully . Overall , the study demonstrated that all prediction methods , when integrated with the optimization model , could provide benefits to prosumers , and save electricity expenses nearly the same as using ideal prediction values , with Elastic Net emerging as the most effective method for predicting peaks and offering the best overall performance .
REFERENCES
[ 1 ] E . Tsioumas , N . Jabbour , M . Koseoglou , D . Papagiannis , and C . Mademlis , " Enhanced sizing methodology for the renewable energy sources and the battery storage system in a nearly zero energy building ," IEEE Transactions on Power Electronics , vol . 36 , no . 9 , pp . 10142-10156 , 2021 .
[ 2 ] Y . Wu , Z . Liu , B . Li , J . Liu , and L . Zhang , " Energy management strategy and optimal battery capacity for flexible PV-battery system under timeof-use tariff ," Renewable Energy , vol . 200 , pp . 558-570 , 2022 .
[ 3 ] J . Van Mierlo et al ., " Beyond the state of the art of electric vehicles : A fact-based paper of the current and prospective electric vehicle technologies ," World Electric Vehicle Journal , vol . 12 , no . 1 , p . 20 , 2021 .
[ 4 ] V . Azarova , D . Engel , C . Ferner , A . Kollmann , and J . Reichl , " Exploring the impact of network tariffs on household electricity expenditures using load profiles and socio-economic characteristics ," Nature Energy , vol . 3 , no . 4 , pp . 317-325 , 2018 .
[ 5 ] N . R . Darghouth , R . H . Wiser , and G . Barbose , " Customer economics of residential photovoltaic systems : Sensitivities to changes in wholesale market design and rate structures ," Renewable and Sustainable Energy Reviews , vol . 54 , pp . 1459-1469 , 2016 .
[ 6 ] Z . Ren , G . Grozev , and A . Higgins , " Modelling impact of PV battery systems on energy consumption and bill savings of Australian houses under alternative tariff structures ," Renewable Energy , vol . 89 , pp . 317- 330 , 2016 .
[ 7 ] L . Bloch , J . Holweger , C . Ballif , and N . Wyrsch , " Impact of advanced electricity tariff structures on the optimal design , operation and profitability of a grid-connected PV system with energy storage ," Energy Informatics , vol . 2 , pp . 1-19 , 2019 .
[ 8 ] W . F . Holmgren , C . W . Hansen , and M . A . Mikofski , " pvlib python : A python package for modeling solar energy systems ," Journal of Open Source Software , vol . 3 , no . 29 , p . 884 , 2018 .
[ 9 ] S . Hochreiter and J . Schmidhuber , " Long short-term memory ," Neural computation , vol . 9 , no . 8 , pp . 1735-1780 , 1997 .
[ 10 ] K . Cho et al ., " Learning phrase representations using RNN encoderdecoder for statistical machine translation ," arXiv preprint arXiv : 1406.1078 , 2014 .
[ 11 ] [ M . Alhussein , K . Aurangzeb , and S . I . Haider , " Hybrid CNN-LSTM model for short-term individual household load forecasting ," Ieee Access , vol . 8 , pp . 180544-180557 , 2020 .
[ 12 ] B . N . Oreshkin , G . Dudek , P . Pełka , and E . Turkina , " N-BEATS neural network for mid-term electricity load forecasting ," Applied Energy , vol . 293 , p . 116918 , 2021 .
[ 13 ] B . Lim , S . Ö . Arık , N . Loeff , and T . Pfister , " Temporal fusion transformers for interpretable multi-horizon time series forecasting ," International Journal of Forecasting , vol . 37 , no . 4 , pp . 1748-1764 , 2021 .
[ 14 ] T . Chen and C . Guestrin , " Xgboost : A scalable tree boosting system ," in Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining , 2016 , pp . 785-794 .
[ 15 ] H . Zou and T . Hastie , " Regularization and variable selection via the elastic net ," Journal of the royal statistical society : series B ( statistical methodology ), vol . 67 , no . 2 , pp . 301-320 , 2005 .
[ 16 ] [ A . E . Hoerl and R . W . Kennard , " Ridge regression : applications to nonorthogonal problems ," Technometrics , vol . 12 , no . 1 , pp . 69-82 , 1970 .
[ 17 ] R . Tibshirani , " Regression shrinkage and selection via the lasso ," Journal of the Royal Statistical Society : Series B ( Methodological ), vol . 58 , no . 1 , pp . 267-288 , 1996 .
[ 18 ] P . C . Young , D . J . Pedregal , and W . Tych , " Dynamic harmonic regression ," Journal of forecasting , vol . 18 , no . 6 , pp . 369-394 , 1999 .
[ 19 ] P . R . Winters , " Forecasting sales by exponentially weighted moving averages ," Management science , vol . 6 , no . 3 , pp . 324-342 , 1960 .
[ 20 ] T . Hastie and R . Tibshirani , " Generalized additive models : some applications ," Journal of the American Statistical Association , vol . 82 , no . 398 , pp . 371-386 , 1987 .
[ 21 ] " Fluvius Open Data Stream ." https :// opendata . fluvius . be ( accessed 25 April 2023 .
[ 22 ] G . Molenberghs , G . Fitzmaurice , M . G . Kenward , A . Tsiatis , and G . Verbeke , Handbook of missing data methodology . CRC Press , 2014 .
[ 23 ] O . Alavi , J . Despeghel , W . De Ceuninck , M . Meuris , J . Driesen , and M . Daenen , " Economic study of battery profitability in residential solar panel systems : A case study of Belgium ," in 2020 IEEE 14th International Conference on Compatibility , Power Electronics and Power Engineering ( CPE-POWERENG ), 2020 , vol . 1 : IEEE , pp . 358-363 .