Accurate prediction of solar irradiance is essential for the successful integration of solar power plants into electrical systems. Despite recent advancements in deep learning technology yielding impressive results in solar forecasting, their lack of interpretability has hindered their widespread adoption. In this paper, we propose a novel approach that integrates a Temporal Fusion Transformer (TFT) with a McClear model to achieve accurate and interpretable forecasting performance. The TFT is a deep learning model that provides transparency in its predictions through the use of interpretable self-attention layers for long-term dependencies, recurrent layers for local processing, specialized components for feature selection, and gating layers to suppress extraneous components. The model is capable of learning temporal associations between continuous time-series variables, namely, historical global horizontal irradiance (GHI) and clear sky GHI, accounting for cloud cover variability and clear sky conditions that are often ignored by most machine learning solar forecasters. Additionally, it minimizes a quantile loss during training to produce accurate probabilistic forecasts. In this study, we evaluate the performance of hourly GHI forecasts on eight diverse datasets with varying climates: temperate, cold, arid, and equatorial, for multiple temporal horizons of 2, 3, 6, 12, and 24 h. The model is benchmarked against both climatological persistence for deterministic forecasting and Complete History Persistence Ensemble for probabilistic forecasting. To prove that our model is not location locked, it has been blind tested on four completely different datasets. The results demonstrate that the proposed model outperforms its counterparts across all forecast horizons.

1.
N.
El-Amarty
,
M.
Marzouq
,
H.
El Fadili
,
S. D.
Bennani
, and
A.
Ruano
, “
A comprehensive review of solar irradiation estimation and forecasting using artificial neural networks: Data, models and trends
,”
Environ. Sci. Pollut. Res.
30
(
3
),
5407
5439
(
2023
).
2.
O.
Morton
, “
Solar energy: A new day dawning?: Silicon Valley sunrise
,”
Nature
443
(
7107
),
19
23
(
2006
).
3.
D.
Yang
,
S.
Alessandrini
,
J.
Antonanzas
,
F.
Antonanzas-Torres
,
V.
Badescu
,
H. G.
Beyer
,
R.
Blaga
,
J.
Boland
,
J. M.
Bright
, and
C. F.
Coimbra
, “
Verification of deterministic solar forecasts
,”
Sol. Energy
210
,
20
37
(
2020
).
4.
P.
Kumari
and
D.
Toshniwal
, “
Extreme gradient boosting and deep neural network based ensemble learning approach to forecast hourly solar irradiance
,”
J. Cleaner Prod.
279
,
123285
(
2021
).
5.
C. S.
Lai
,
C.
Zhong
,
K.
Pan
,
W. W.
Ng
, and
L. L.
Lai
, “
A deep learning based hybrid method for hourly solar radiation forecasting
,”
Expert Syst. Appl.
177
,
114941
(
2021
).
6.
J.
Jung
and
R.
Broadwater
, “
Current status and future advances for wind speed and power forecasting
,”
Renewable Sustainable Energy Rev.
31
,
762
777
(
2014
).
7.
P.
Kumari
and
D.
Toshniwal
, “
Deep learning models for solar irradiance forecasting: A comprehensive review
,”
J. Cleaner Prod.
318
,
128566
(
2021
).
8.
P.
Li
,
K.
Zhou
,
X.
Lu
, and
S.
Yang
, “
A hybrid deep learning model for short-term PV power forecasting
,”
Appl. Energy
259
,
114216
(
2020
).
9.
H.
Zang
,
L.
Liu
,
L.
Sun
,
L.
Cheng
,
Z.
Wei
, and
G.
Sun
, “
Short-term global horizontal irradiance forecasting based on a hybrid CNN-LSTM model with spatiotemporal correlations
,”
Renewable Energy
160
,
26
41
(
2020
).
10.
S. M. J.
Jalali
,
S.
Ahmadian
,
A.
Kavousi-Fard
, and
A.
Khosravi
, “
Automated deep CNN-LSTM architecture design for solar irradiance forecasting
,”
Trans. Syst., Man, Cybern.: Syst.
52
(
1
),
54
65
(
2021
).
11.
S.
Aslam
,
H.
Herodotou
,
S. M.
Mohsin
,
N.
Javaid
, and
N.
Ashraf
, “
A survey on deep learning methods for power load and renewable energy forecasting in smart microgrids
,”
Renewable Sustainable Energy Rev.
144
,
110992
(
2021
).
12.
A.
Vaswani
,
N.
Shazeer
,
N.
Parmar
,
J.
Uszkoreit
,
L.
Jones
,
A. N.
Gomez
,
Ł.
Kaiser
, and
I.
Polosukhin
, “
Attention is all you need
,” in
31st Conference on Neural Information Processing Systems (NIPS 2017)
, Long Beach, CA,
2017
.
13.
F.-H.
Yu
and
K.-Y.
Chen
, “
Non-autoregressive transformer-based end-to-end ASR using BERT
,” arXiv:2104.04805 (
2021
).
14.
A.
Zeng
,
M.
Chen
,
L.
Zhang
, and
Q.
Xu
, “
Are transformers effective for time series forecasting?
,”
Proc. AAAI Conf. Artif. Intell.
37
(
9
),
11121
11128
(
2023
).
15.
B.
Lim
,
S. Ö.
Arık
,
N.
Loeff
, and
T.
Pfister
, “
Temporal fusion transformers for interpretable multi-horizon time series forecasting
,”
Int. J. Forecasting
37
(
4
),
1748
1764
(
2021
).
16.
E.
Giacomazzi
,
F.
Haag
, and
K.
Hopf
, “
Short-term electricity load forecasting using the temporal fusion transformer: Effect of grid hierarchies and data sources
,” arXiv:2305.10559 (
2023
).
17.
B.
Wu
,
L.
Wang
, and
Y.-R.
Zeng
, “
Interpretable wind speed prediction with multivariate time series and temporal fusion transformers
,”
Energy
252
,
123990
(
2022
).
18.
A.
Driemel
,
J.
Augustine
,
K.
Behrens
,
S.
Colle
,
C.
Cox
,
E.
Cuevas-Agulló
,
F. M.
Denn
,
T.
Duprat
,
M.
Fukuda
, and
H.
Grobe
, “
Baseline surface radiation network (BSRN): Structure and data description (1992–2017)
,”
Earth Syst. Sci. Data
10
(
3
),
1491
1501
(
2018
).
19.
D.
Yang
, “
Choice of clear-sky model in solar forecasting
,”
J. Renewable Sustainable Energy
12
(
2
),
026101
(
2020
).
20.
D.
Yang
, “
A universal benchmarking method for probabilistic solar irradiance forecasting
,”
Sol. Energy
184
,
410
416
(
2019
).
21.
J. F.
Jønler
,
F. B.
Lottrup
,
B.
Berg
,
D.
Zhang
, and
K.
Chen
, “
Probabilistic forecasts of global horizontal irradiance for solar systems
,”
IEEE Sens. Lett.
7
(
1
),
7000104
(
2022
).
22.
D.
Yang
, “
Making reference solar forecasts with climatology, persistence, and their optimal convex combination
,”
Sol. Energy
193
,
981
985
(
2019
).
23.
D.
Yang
, “
A guideline to solar forecasting research practice: Reproducible, operational, probabilistic or physically-based, ensemble, and skill (ROPES)
,”
J. Renewable Sustainable Energy
11
(
2
),
022701
(
2019
).
24.
J.
Bright
, “
The impact of globally diverse GHI training data: Evaluation through application of a simple Markov chain downscaling methodology
,”
J. Renewable Sustainable Energy
11
(
2
),
023703
(
2019
).
25.
F.
Xu
,
H.
Uszkoreit
,
Y.
Du
,
W.
Fan
,
D.
Zhao
, and
J.
Zhu
, “
Explainable AI: A brief survey on history, research areas, approaches and challenges
,” in
Natural Language Processing and Chinese Computing
(
Springer
,
2019
), pp.
563
574
.
26.
W.
Samek
and
K.-R.
Müller
, “
Towards explainable artificial intelligence
,” in
Explainable AI: Interpreting, Explaining Visualizing Deep Learning
(
Springer
,
2019
).

Supplementary Material

You do not currently have access to this content.