Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM69227
Volume:
10 |
11 |
Nov 2026
Pages:
1-7
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Information Science and Engineering
Jawaharlal Nehru New College of Engineering Shivamogga
Information Science and Engineering
Jawaharlal Nehru New College of Engineering Shivamogga
Information Science and Engineering
Jawaharlal Nehru New College of Engineering Shivamogga
Information Science and Engineering
Jawaharlal Nehru New College of Engineering Shivamogga
Information Science and Engineering
Jawaharlal Nehru New College of Engineering Shivamogga
Accurate forecasting of electricity load and electricity price supports grid operation, market bidding, demand response and household energy management, yet both series are volatile, non-linear and strongly seasonal. This paper presents the project implementation of a deep-learning system, Smart Energy Forecasting, that predicts electricity load with a Long Short-Term Memory (LSTM) network and electricity market price with a Gated Recurrent Unit (GRU) network. Each model takes a 24-step sequence of 17 input features covering calendar, weather, economic, generation-capacity, lagged load and price, and rolling-average variables. Four recurrent architectures (LSTM, GRU, BiLSTM and CNN-LSTM) were compared on the test set. LSTM gave the best load forecast, with MAE 39.6754, RMSE 48.7313 and RZ 0.8882, while GRU gave the best price forecast, with MAE 2.6210, RMSE 3.3600 and RZ 0.6548. The trained models are deployed in a Streamlit dashboard that provides single-point prediction, 24-hour forecasts, peak-demand alerts, appliance-shifting recommendations and a slab-based electricity bill generator with PDF output. The evaluated dataset is [electricity load data.csv].
KEYWORDS
This paper presented Smart Energy Forecasting, a deep-learning system for electricity load and price forecasting deployed as a Streamlit dashboard. Using 24-step sequences of 17 features, LSTM gave the best load forecast (MAE 39.6754, RMSE 48.7313, RZ 0.8882) and GRU gave the best price forecast (MAE 2.6210, RMSE 3.3600, RZ 0.6548) among LSTM, GRU, BiLSTM and CNN-LSTM. Future work includes adding MAPE and prediction intervals [2], [3], fuel-price and supply-side inputs for price, attention and decomposition components [6], [14], hyperparameter optimization [4], online adaptation to concept drift [17], repeated runs and external validation on other markets, and generating the dashboard forecast directly from live data instead of a stored forecast file.
[1] K. Mustafa, S. Khan, S. Aslam, H. Herodotou, N. Ashraf, A. Daraz, and T. Alkhalifah, “Toward holistic energy management by electricity load and price forecasting: A comprehensive survey,” IEEE Access, vol. 11, 2023, doi: 10.1109/ACCESS.2023.3334164. [2] R. Zhang, G. Li, and Z. Ma, “Adeep learningbased hybrid framework for day-ahead electricity price forecasting,” IEEE Access, vol. 8, 2020, doi: 10.1109/ACCESS.2020.3014241. [3] M. N. H. Mir, A. K. Biswas, M. S. A. Bhuiyan, M. G. R. Abir, M. F. Mridha, and M. J. Hossen, “ABMF-Net: An attentive Bayesian multi-stage deep learning model for robust forecasting of electricity price and demand,” IEEE Open J. Comput. Soc., 2025, doi: 10.1109/OJCS.2025.3579522. [4] Y. Mohamed, M. M. Fouda, Z. M. Fadlullah, R. Abdelfattah, and M. I. Ibrahem, “BOL-LPP: A Bayesian-optimized LSTM modelfor day-ahead load price forecasting in the ERCOT market,” IEEE Open J. Comput. Soc., 2025, doi: 10.1109/OJCS.2025.3580107. [5] I. M. Gaber and R. A. Ibrahim, “Hourly electricity price prediction applying deep learning for electricity market management,” in Proc. IEEE EEEIC / I&CPS Europe, 2023, doi: 10.1109/EEEIC/ICPSEUROPE57605.2023.10194867. [6] M. F. Azam and M. S. Younis, “Multi-horizon electricity load and price forecasting using an interpretable multi-head self-attention and EEMD-based framework,” IEEE Access, vol. 9, 2021, doi: 10.1109/ACCESS.2021.3086039. [7] Y.-Y. Hong, J. V. Taylar, and A. C. Fajardo, “Locational marginal price forecasting using deep learning network optimized by mapping-based genetic algorithm,” IEEE Access, vol. 8, 2020, doi: 10.1109/ACCESS.2020.2994444. [8] X. Cheng, I. Ilieva, B. Bremdal, S. Redhu, and S. Ø. Ottesen, “A novel spatial-temporal deep neural network for electricity price forecasting,” in Proc. Int. Conf. Applied Artificial Intelligence (ICAPAI), 2023, doi: 10.1109/ICAPAI58366.2023.10193970. [9] A. A. Almazroi and N. Ayub, “Multi-task learning for electricity price forecasting and resource management in cloud based industrial IoT systems,” IEEE Access, vol. 11, 2023, doi: 10.1109/ACCESS.2023.3280857. [10] R. Dash, A. Sinha, K. J. Reddy, C. Dhanamjayulu, and I. Kamwa, “Dynamic modeling and quantum-enhancedforecasting of multi-seasonal energy prices in simulated microgrid environments,” IEEE Access, vol. 13, 2025, doi: 10.1109/ACCESS.2025.3570719.
Publication Date
11/19/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
1
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...