Wind power forecasting considering data privacy protection: A federated deep reinforcement learning approach

In a modern power system with an increasing proportion of renewable energy, wind power prediction is crucial to the arrangement of power grid dispatching plans due to the volatility of wind power. However, traditional centralized forecasting methods raise concerns regarding data privacy-preserving a...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Applied energy Jg. 329; S. 120291
Hauptverfasser: Li, Yang, Wang, Ruinong, Li, Yuanzheng, Zhang, Meng, Long, Chao
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Ltd 01.01.2023
Schlagworte:
ISSN:0306-2619, 1872-9118
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract In a modern power system with an increasing proportion of renewable energy, wind power prediction is crucial to the arrangement of power grid dispatching plans due to the volatility of wind power. However, traditional centralized forecasting methods raise concerns regarding data privacy-preserving and data islands problem. To handle the data privacy and openness, we propose a forecasting scheme that combines federated learning and deep reinforcement learning (DRL) for ultra-short-term wind power forecasting, called federated deep reinforcement learning (FedDRL). Firstly, this paper uses the deep deterministic policy gradient (DDPG) algorithm as the basic forecasting model to improve prediction accuracy. Secondly, we integrate the DDPG forecasting model into the framework of federated learning. The designed FedDRL can obtain an accurate prediction model in a decentralized way by sharing model parameters instead of sharing private data which can avoid sensitive privacy issues. The simulation results show that the proposed FedDRL outperforms the traditional prediction methods in terms of forecasting accuracy. More importantly, while ensuring the forecasting performance, FedDRL can effectively protect the data privacy and relieve the communication pressure compared with the traditional centralized forecasting method. In addition, a simulation with different federated learning parameters is conducted to confirm the robustness of the proposed scheme. •A DDPG-based prediction model is built for ultra-short-term wind power forecasting.•Propose a FedDRL forecasting scheme to handle the data privacy and openness.•Combine automatic machine learning with DRL for hyperparameters selection.•Simulation tests were carried out on real-world historical data to examine the proposal.
AbstractList In a modern power system with an increasing proportion of renewable energy, wind power prediction is crucial to the arrangement of power grid dispatching plans due to the volatility of wind power. However, traditional centralized forecasting methods raise concerns regarding data privacy-preserving and data islands problem. To handle the data privacy and openness, we propose a forecasting scheme that combines federated learning and deep reinforcement learning (DRL) for ultra-short-term wind power forecasting, called federated deep reinforcement learning (FedDRL). Firstly, this paper uses the deep deterministic policy gradient (DDPG) algorithm as the basic forecasting model to improve prediction accuracy. Secondly, we integrate the DDPG forecasting model into the framework of federated learning. The designed FedDRL can obtain an accurate prediction model in a decentralized way by sharing model parameters instead of sharing private data which can avoid sensitive privacy issues. The simulation results show that the proposed FedDRL outperforms the traditional prediction methods in terms of forecasting accuracy. More importantly, while ensuring the forecasting performance, FedDRL can effectively protect the data privacy and relieve the communication pressure compared with the traditional centralized forecasting method. In addition, a simulation with different federated learning parameters is conducted to confirm the robustness of the proposed scheme.
In a modern power system with an increasing proportion of renewable energy, wind power prediction is crucial to the arrangement of power grid dispatching plans due to the volatility of wind power. However, traditional centralized forecasting methods raise concerns regarding data privacy-preserving and data islands problem. To handle the data privacy and openness, we propose a forecasting scheme that combines federated learning and deep reinforcement learning (DRL) for ultra-short-term wind power forecasting, called federated deep reinforcement learning (FedDRL). Firstly, this paper uses the deep deterministic policy gradient (DDPG) algorithm as the basic forecasting model to improve prediction accuracy. Secondly, we integrate the DDPG forecasting model into the framework of federated learning. The designed FedDRL can obtain an accurate prediction model in a decentralized way by sharing model parameters instead of sharing private data which can avoid sensitive privacy issues. The simulation results show that the proposed FedDRL outperforms the traditional prediction methods in terms of forecasting accuracy. More importantly, while ensuring the forecasting performance, FedDRL can effectively protect the data privacy and relieve the communication pressure compared with the traditional centralized forecasting method. In addition, a simulation with different federated learning parameters is conducted to confirm the robustness of the proposed scheme. •A DDPG-based prediction model is built for ultra-short-term wind power forecasting.•Propose a FedDRL forecasting scheme to handle the data privacy and openness.•Combine automatic machine learning with DRL for hyperparameters selection.•Simulation tests were carried out on real-world historical data to examine the proposal.
ArticleNumber 120291
Author Li, Yang
Wang, Ruinong
Li, Yuanzheng
Zhang, Meng
Long, Chao
Author_xml – sequence: 1
  givenname: Yang
  surname: Li
  fullname: Li, Yang
  email: liyang@neepu.edu.cn
  organization: Key Laboratory of Modern Power System Simulation and Control and Renewable Energy Technology, Ministry of Education, Northeast Electric Power University, Jilin 132012, China
– sequence: 2
  givenname: Ruinong
  surname: Wang
  fullname: Wang, Ruinong
  email: 624895223@qq.com
  organization: State Grid Jilin Power Supply Company, Jilin 132001, China
– sequence: 3
  givenname: Yuanzheng
  surname: Li
  fullname: Li, Yuanzheng
  email: Yuanzheng_Li@hust.edu.cn
  organization: School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, China
– sequence: 4
  givenname: Meng
  surname: Zhang
  fullname: Zhang, Meng
  email: 964285846@qq.com
  organization: School of National Key Laboratory of Science and Technology on Vessel Integrated Power System, Naval University of Engineering, Wuhan 430033, China
– sequence: 5
  givenname: Chao
  surname: Long
  fullname: Long, Chao
  email: Chao.Long@cranfield.ac.uk
  organization: School of Water, Energy and Environment, Cranfield University, UK
BookMark eNqFkcFuGyEURVGVSHWS_kLFsptxeTDGnqqLRFHaRLKUTaou0Rt4k2KNYQIklf8-jNxsusmGh9A9F3E4YychBmLsM4glCNBfd0ucKFB6PCylkHIJde3gA1vAZi2bDmBzwhZCCd1IDd1HdpbzTggha27Bxt8-OD7Fv5T4EBNZzMWHR25jyN5RmvcOC_Ip-Re0hzpjIVt8DN_4FR-oZrCQ445o4ol8qC2W9hQKHwlTmAtwqhTaPxfsdMAx06d_85z9-nHzcH3bbO9_3l1fbRurOlWaFlZdr4Z-sFI7SwpIr2UrV73VUq2lQ2xbaKVe9QPUc-U63XcoWxjkuteuV-fsy7G3Xvv0TLmYvc-WxhEDxedsFKzURoHSqka_H6M2xZwTDcb6gvPzSkI_GhBmlmx25k2ymSWbo-SK6__w6mmP6fA-eHkEqXp48ZRMtp6CJefrJxTjon-v4hVPfZ76
CitedBy_id crossref_primary_10_1016_j_jclepro_2024_141415
crossref_primary_10_1109_TNSE_2025_3547227
crossref_primary_10_1007_s00202_024_02759_0
crossref_primary_10_1007_s13042_024_02116_4
crossref_primary_10_1016_j_energy_2023_128406
crossref_primary_10_1002_acs_4053
crossref_primary_10_1016_j_apenergy_2025_126468
crossref_primary_10_1016_j_egyr_2024_07_030
crossref_primary_10_1002_acs_4050
crossref_primary_10_1007_s11227_025_07376_7
crossref_primary_10_1109_ACCESS_2023_3344029
crossref_primary_10_1016_j_epsr_2023_109461
crossref_primary_10_1007_s00521_025_11230_5
crossref_primary_10_1016_j_ref_2023_100520
crossref_primary_10_1109_JPROC_2023_3303358
crossref_primary_10_1016_j_energy_2024_132188
crossref_primary_10_3390_en17051053
crossref_primary_10_1016_j_egyr_2024_05_021
crossref_primary_10_1038_s41598_024_68339_1
crossref_primary_10_1016_j_egyr_2022_12_050
crossref_primary_10_1007_s40436_025_00552_1
crossref_primary_10_1016_j_egyr_2024_01_002
crossref_primary_10_1080_15435075_2024_2399189
crossref_primary_10_1007_s11227_024_06845_9
crossref_primary_10_1016_j_apenergy_2023_121468
crossref_primary_10_1049_rpg2_13110
crossref_primary_10_1109_ACCESS_2024_3507154
crossref_primary_10_1007_s12667_023_00590_3
crossref_primary_10_1016_j_apenergy_2023_121503
crossref_primary_10_3390_electricity4040020
crossref_primary_10_3390_en16227610
crossref_primary_10_1016_j_energy_2023_129847
crossref_primary_10_1016_j_energy_2023_130076
crossref_primary_10_1016_j_egyr_2022_12_002
crossref_primary_10_1109_ACCESS_2024_3407121
crossref_primary_10_1016_j_energy_2024_133023
crossref_primary_10_1016_j_egyr_2022_12_083
crossref_primary_10_1016_j_epsr_2025_111952
crossref_primary_10_1016_j_egyr_2023_01_078
crossref_primary_10_1016_j_egyr_2024_01_036
crossref_primary_10_1016_j_egyr_2023_01_079
crossref_primary_10_1016_j_apenergy_2024_124302
crossref_primary_10_1016_j_apenergy_2024_123611
crossref_primary_10_1016_j_eswa_2023_122226
crossref_primary_10_1016_j_jclepro_2023_139944
crossref_primary_10_1016_j_energy_2025_135055
crossref_primary_10_1049_gtd2_13299
crossref_primary_10_1016_j_apenergy_2023_121638
crossref_primary_10_1109_ACCESS_2024_3415781
crossref_primary_10_1109_TIM_2024_3522628
crossref_primary_10_1016_j_enconman_2025_119673
crossref_primary_10_1016_j_eswa_2025_127725
crossref_primary_10_1016_j_engappai_2024_108952
crossref_primary_10_1016_j_apenergy_2022_120540
crossref_primary_10_1016_j_apenergy_2025_126177
crossref_primary_10_1016_j_egyr_2024_03_016
crossref_primary_10_3390_electronics12214443
crossref_primary_10_1016_j_egyr_2024_07_007
crossref_primary_10_1016_j_energy_2025_136391
crossref_primary_10_1038_s41598_024_82585_3
crossref_primary_10_1007_s42524_023_0271_3
crossref_primary_10_1109_TIA_2024_3430264
crossref_primary_10_32604_cmc_2024_046797
crossref_primary_10_3390_en18143745
crossref_primary_10_1016_j_egyr_2022_11_165
crossref_primary_10_1016_j_egyr_2024_01_056
crossref_primary_10_1016_j_eswa_2025_127218
crossref_primary_10_1016_j_renene_2025_123550
crossref_primary_10_1016_j_cie_2024_110477
crossref_primary_10_1049_gtd2_13034
crossref_primary_10_3389_fenrg_2024_1401978
crossref_primary_10_3390_en16196889
crossref_primary_10_1016_j_egyr_2022_12_149
crossref_primary_10_1063_5_0250465
crossref_primary_10_1016_j_apenergy_2024_125053
crossref_primary_10_3233_JIFS_219428
crossref_primary_10_1080_23307706_2024_2434610
crossref_primary_10_1016_j_rser_2024_114648
crossref_primary_10_1016_j_apenergy_2023_122185
crossref_primary_10_3390_su151712914
crossref_primary_10_1109_TFUZZ_2024_3419559
crossref_primary_10_3390_en16176236
crossref_primary_10_1080_15435075_2023_2281329
crossref_primary_10_1016_j_measurement_2025_117541
crossref_primary_10_1016_j_apenergy_2024_122626
crossref_primary_10_1016_j_jclepro_2023_138676
crossref_primary_10_1016_j_energy_2024_134180
crossref_primary_10_1016_j_energy_2023_127914
crossref_primary_10_1016_j_epsr_2024_110534
crossref_primary_10_1049_rpg2_12736
crossref_primary_10_1016_j_egyr_2024_02_009
crossref_primary_10_1016_j_egyr_2024_05_061
crossref_primary_10_1038_s41598_024_63384_2
crossref_primary_10_1016_j_epsr_2024_110495
crossref_primary_10_1109_JIOT_2023_3293800
crossref_primary_10_1016_j_jobe_2024_110726
crossref_primary_10_1109_TSG_2024_3466768
crossref_primary_10_1016_j_epsr_2024_110771
crossref_primary_10_1109_JIOT_2024_3450433
crossref_primary_10_3390_en16073248
crossref_primary_10_1155_er_7215655
crossref_primary_10_3390_en16124773
crossref_primary_10_1007_s00704_025_05450_x
crossref_primary_10_1016_j_egyr_2023_11_040
crossref_primary_10_1109_ACCESS_2025_3543594
crossref_primary_10_2298_CSIS241123038L
crossref_primary_10_3389_fenrg_2023_1340639
crossref_primary_10_1016_j_egyr_2023_12_046
crossref_primary_10_3390_en17051124
crossref_primary_10_1016_j_energy_2025_134711
crossref_primary_10_1016_j_eswa_2025_128729
crossref_primary_10_1016_j_egyr_2024_01_074
crossref_primary_10_1016_j_egyr_2025_05_051
crossref_primary_10_1016_j_egyr_2022_12_049
crossref_primary_10_1016_j_energy_2024_130751
crossref_primary_10_7717_peerj_cs_2819
crossref_primary_10_29109_gujsc_1627535
crossref_primary_10_1016_j_seta_2024_103830
crossref_primary_10_1155_2023_5514460
crossref_primary_10_1016_j_energy_2023_128947
crossref_primary_10_1016_j_egyr_2025_02_034
crossref_primary_10_1038_s41598_023_48943_3
crossref_primary_10_3389_fenrg_2023_1211360
crossref_primary_10_3390_electronics13071281
crossref_primary_10_1016_j_segan_2024_101376
crossref_primary_10_1016_j_est_2024_114153
crossref_primary_10_1016_j_energy_2025_136344
crossref_primary_10_3390_fi17070308
crossref_primary_10_1016_j_egyr_2022_11_194
crossref_primary_10_1109_COMST_2024_3365076
crossref_primary_10_1016_j_energy_2024_134044
crossref_primary_10_1080_19942060_2024_2305318
crossref_primary_10_1016_j_apenergy_2023_120749
crossref_primary_10_1016_j_energy_2023_129639
crossref_primary_10_1016_j_energy_2024_133072
crossref_primary_10_1016_j_heliyon_2024_e31873
crossref_primary_10_1080_21642583_2024_2448626
crossref_primary_10_1007_s40747_023_01066_8
crossref_primary_10_1016_j_rser_2025_115407
crossref_primary_10_1109_TIA_2024_3371966
crossref_primary_10_1109_ACCESS_2025_3599360
crossref_primary_10_1016_j_egyr_2024_03_056
crossref_primary_10_1016_j_egyr_2023_12_055
crossref_primary_10_1016_j_apenergy_2024_124699
crossref_primary_10_4018_JOEUC_370005
crossref_primary_10_1016_j_egyr_2023_02_001
crossref_primary_10_3390_en18102515
crossref_primary_10_1016_j_apenergy_2024_122838
crossref_primary_10_1016_j_eswa_2023_121185
crossref_primary_10_1109_TIA_2024_3430229
Cites_doi 10.1145/3298981
10.1016/j.renene.2016.03.103
10.1109/MSP.2020.2975749
10.1109/TII.2015.2431642
10.1016/j.apenergy.2018.09.211
10.1016/j.apenergy.2021.118347
10.1109/TIFS.2016.2607691
10.1016/j.energy.2021.121492
10.1109/TSG.2022.3204796
10.1109/TII.2017.2730846
10.1016/j.energy.2018.07.200
10.1007/s11277-012-0939-1
10.1016/j.ijforecast.2020.06.003
10.1109/TPWRS.2018.2822784
10.1016/j.jclepro.2022.134540
10.1016/j.energy.2020.117794
10.1109/TIA.2021.3106573
10.1016/j.apenergy.2021.118392
10.1038/nature14236
10.1016/j.energy.2021.120492
10.1016/j.energy.2018.09.118
10.1109/TII.2021.3098259
10.1016/j.apenergy.2012.03.054
10.1016/j.apenergy.2016.03.096
10.1109/TSTE.2015.2480245
10.1109/JIOT.2020.2991401
10.29012/jpc.v1i2.570
10.1109/TSTE.2021.3105529
10.1016/j.energy.2022.123226
ContentType Journal Article
Copyright 2022 Elsevier Ltd
Copyright_xml – notice: 2022 Elsevier Ltd
DBID AAYXX
CITATION
7S9
L.6
DOI 10.1016/j.apenergy.2022.120291
DatabaseName CrossRef
AGRICOLA
AGRICOLA - Academic
DatabaseTitle CrossRef
AGRICOLA
AGRICOLA - Academic
DatabaseTitleList AGRICOLA

DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Environmental Sciences
EISSN 1872-9118
ExternalDocumentID 10_1016_j_apenergy_2022_120291
S0306261922015483
GroupedDBID --K
--M
.~1
0R~
1B1
1~.
1~5
23M
4.4
457
4G.
5GY
5VS
7-5
71M
8P~
9JN
AABNK
AACTN
AAEDT
AAEDW
AAHCO
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AARJD
AAXUO
ABJNI
ABMAC
ABYKQ
ACDAQ
ACGFS
ACRLP
ADBBV
ADEZE
ADTZH
AEBSH
AECPX
AEKER
AENEX
AFKWA
AFTJW
AGHFR
AGUBO
AGYEJ
AHHHB
AHIDL
AHJVU
AIEXJ
AIKHN
AITUG
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AXJTR
BELTK
BJAXD
BKOJK
BLXMC
CS3
EBS
EFJIC
EFLBG
EO8
EO9
EP2
EP3
FDB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
IHE
J1W
JARJE
JJJVA
KOM
LY6
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
ROL
RPZ
SDF
SDG
SES
SPC
SPCBC
SSR
SST
SSZ
T5K
TN5
~02
~G-
9DU
AAHBH
AAQXK
AATTM
AAXKI
AAYWO
AAYXX
ABEFU
ABFNM
ABWVN
ABXDB
ACLOT
ACNNM
ACRPL
ACVFH
ADCNI
ADMUD
ADNMO
AEIPS
AEUPX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
ASPBG
AVWKF
AZFZN
CITATION
EFKBS
EJD
FEDTE
FGOYB
G-2
HVGLF
HZ~
R2-
SAC
SEW
WUQ
ZY4
~HD
7S9
L.6
ID FETCH-LOGICAL-c393t-4159b3fbfc26dce31e672425bc62372daa4414265bf12423d96b9a241f27b6db3
ISICitedReferencesCount 183
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000890577800006&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0306-2619
IngestDate Sun Sep 28 10:49:40 EDT 2025
Tue Nov 18 21:59:16 EST 2025
Sat Nov 29 07:21:09 EST 2025
Fri Feb 23 02:39:58 EST 2024
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords Data openness and sharing
Privacy protection
Deep reinforcement learning
Federated learning
Wind power forecasting
Uncertainty modeling
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c393t-4159b3fbfc26dce31e672425bc62372daa4414265bf12423d96b9a241f27b6db3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
OpenAccessLink https://dspace.lib.cranfield.ac.uk/handle/1826/18727
PQID 3153831363
PQPubID 24069
ParticipantIDs proquest_miscellaneous_3153831363
crossref_citationtrail_10_1016_j_apenergy_2022_120291
crossref_primary_10_1016_j_apenergy_2022_120291
elsevier_sciencedirect_doi_10_1016_j_apenergy_2022_120291
PublicationCentury 2000
PublicationDate 2023-01-01
2023-01-00
20230101
PublicationDateYYYYMMDD 2023-01-01
PublicationDate_xml – month: 01
  year: 2023
  text: 2023-01-01
  day: 01
PublicationDecade 2020
PublicationTitle Applied energy
PublicationYear 2023
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References Hu, Zhang, Yu, Xie (b9) 2015; 7
Wang, Zhang, Wu, Wang (b10) 2016; 94
Li, Bu, Gao, Li (b37) 2022; 378
Li, Wang, Yang (b34) 2021; 13
Yang, Liu, Chen, Tong (b29) 2019; 10
Cassola, Burlando (b8) 2012; 99
Liu, Yu, Wu, Duan, Yan (b14) 2020; 202
Li ZL, Liang C-JM, He W, Zhu L, Dai W, Jiang J, et al. Metis: Robustly tuning tail latencies of cloud systems. In: 2018 {USENIX} Annual technical conference ({USENIX}{ATC} 18). 2018, p. 981–92.
Li, Feng, Wang, Sun (b38) 2022; 245
Zhao, Ye, Li, Song, Lang, Su (b33) 2016; 177
Zhang, Chen, Yan, Zhang, Xu (b13) 2021; 236
Li, Wang, Yang, Li, Chen (b36) 2022; 308
Li, Wei, Li, Dong, Shahidehpour (b26) 2022; 13
Mnih, Kavukcuoglu, Silver, Rusu, Veness, Bellemare (b23) 2015; 518
Li, Sahu, Talwalkar, Smith (b25) 2020; 37
Sweeney, Bessa, Browell, Pinson (b5) 2020; 9
Zhang, Zhu (b19) 2016; 12
Kuremoto, Hirata, Obayashi, Mabu, Kobayashi (b30) 2019
Wang, Qi, Liu, Song (b12) 2018; 165
Dwork, Smith (b18) 2010; 1
McMahan, Moore, Ramage, Hampson, y Arcas (b32) 2017
Gonçalves, Bessa, Pinson (b20) 2021; 37
Li, Zhang, Chen (b21) 2022; 308
Zhang, Wang (b17) 2018; 33
Liu, Lin, Feng (b7) 2021; 227
Buhan, Çadırcı (b3) 2015; 11
Li, Wang, Zhao, Li, Chen (b1) 2018; 162
Zeadally, Pathan, Alcaraz, Badra (b4) 2013; 73
Li, Ding, Liu, Yang, Wang, Wang, Yao (b35) 2022
Li, Wang, Yang, Li, Li (b22) 2022; 58
Arora, Jalali, Ahmadian, Panigrahi, Suganthan, Khosravi (b2) 2022
Silver, Lever, Heess, Degris, Wierstra, Riedmiller (b24) 2014
Voigt, Von dem Bussche (b16) 2017
Li, Yang, Li, Mu, Zhao, Chen (b15) 2018; 232
Rajagopalan, Santoso (b6) 2009
Khodayar, Kaynak, Khodayar (b11) 2017; 13
Li, Li, Wang (b28) 2022; 18
Liu, James, Kang, Niyato, Zhang (b27) 2020; 7
Zhang (10.1016/j.apenergy.2022.120291_b13) 2021; 236
Sweeney (10.1016/j.apenergy.2022.120291_b5) 2020; 9
10.1016/j.apenergy.2022.120291_b31
Li (10.1016/j.apenergy.2022.120291_b1) 2018; 162
Cassola (10.1016/j.apenergy.2022.120291_b8) 2012; 99
Li (10.1016/j.apenergy.2022.120291_b26) 2022; 13
Kuremoto (10.1016/j.apenergy.2022.120291_b30) 2019
Dwork (10.1016/j.apenergy.2022.120291_b18) 2010; 1
Li (10.1016/j.apenergy.2022.120291_b34) 2021; 13
Rajagopalan (10.1016/j.apenergy.2022.120291_b6) 2009
Li (10.1016/j.apenergy.2022.120291_b37) 2022; 378
Li (10.1016/j.apenergy.2022.120291_b25) 2020; 37
Liu (10.1016/j.apenergy.2022.120291_b14) 2020; 202
Gonçalves (10.1016/j.apenergy.2022.120291_b20) 2021; 37
Liu (10.1016/j.apenergy.2022.120291_b27) 2020; 7
Li (10.1016/j.apenergy.2022.120291_b21) 2022; 308
Zhao (10.1016/j.apenergy.2022.120291_b33) 2016; 177
Zhang (10.1016/j.apenergy.2022.120291_b17) 2018; 33
Wang (10.1016/j.apenergy.2022.120291_b10) 2016; 94
Mnih (10.1016/j.apenergy.2022.120291_b23) 2015; 518
Hu (10.1016/j.apenergy.2022.120291_b9) 2015; 7
Khodayar (10.1016/j.apenergy.2022.120291_b11) 2017; 13
Li (10.1016/j.apenergy.2022.120291_b38) 2022; 245
Buhan (10.1016/j.apenergy.2022.120291_b3) 2015; 11
Li (10.1016/j.apenergy.2022.120291_b22) 2022; 58
Li (10.1016/j.apenergy.2022.120291_b15) 2018; 232
Liu (10.1016/j.apenergy.2022.120291_b7) 2021; 227
Voigt (10.1016/j.apenergy.2022.120291_b16) 2017
Wang (10.1016/j.apenergy.2022.120291_b12) 2018; 165
Zhang (10.1016/j.apenergy.2022.120291_b19) 2016; 12
Silver (10.1016/j.apenergy.2022.120291_b24) 2014
McMahan (10.1016/j.apenergy.2022.120291_b32) 2017
Li (10.1016/j.apenergy.2022.120291_b36) 2022; 308
Li (10.1016/j.apenergy.2022.120291_b35) 2022
Arora (10.1016/j.apenergy.2022.120291_b2) 2022
Yang (10.1016/j.apenergy.2022.120291_b29) 2019; 10
Zeadally (10.1016/j.apenergy.2022.120291_b4) 2013; 73
Li (10.1016/j.apenergy.2022.120291_b28) 2022; 18
References_xml – volume: 94
  start-page: 629
  year: 2016
  end-page: 636
  ident: b10
  article-title: Wind speed forecasting based on the hybrid ensemble empirical mode decomposition and GA-BP neural network method
  publication-title: Renew Energy
– volume: 37
  start-page: 322
  year: 2021
  end-page: 342
  ident: b20
  article-title: A critical overview of privacy-preserving approaches for collaborative forecasting
  publication-title: Int J Forecast
– volume: 378
  year: 2022
  ident: b37
  article-title: Optimal dispatch of low-carbon integrated energy system considering nuclear heating and carbon trading
  publication-title: J Cleaner Prod
– volume: 9
  year: 2020
  ident: b5
  article-title: The future of forecasting for renewable energy
  publication-title: Wiley Interdiscip Rev Energy Environ
– volume: 308
  year: 2022
  ident: b21
  article-title: A deep-learning intelligent system incorporating data augmentation for short-term voltage stability assessment of power systems
  publication-title: Appl Energy
– volume: 13
  start-page: 4862
  year: 2022
  end-page: 4872
  ident: b26
  article-title: Detection of false data injection attacks in smart grid: A secure federated deep learning approach
  publication-title: IEEE Trans Smart Grid
– volume: 165
  start-page: 840
  year: 2018
  end-page: 852
  ident: b12
  article-title: Deep belief network based k-means cluster approach for short-term wind power forecasting
  publication-title: Energy
– volume: 245
  year: 2022
  ident: b38
  article-title: Joint planning of distributed generations and energy storage in active distribution networks: A Bi-Level programming approach
  publication-title: Energy
– volume: 13
  start-page: 2770
  year: 2017
  end-page: 2779
  ident: b11
  article-title: Rough deep neural architecture for short-term wind speed forecasting
  publication-title: IEEE Trans Ind Inf
– volume: 13
  start-page: 159
  year: 2021
  end-page: 169
  ident: b34
  article-title: Optimal scheduling of isolated microgrids using automated reinforcement learning-based multi-period forecasting
  publication-title: IEEE Trans Sustain Energy
– year: 2022
  ident: b2
  article-title: Probabilistic wind power forecasting using optimised deep auto-regressive recurrent neural networks
  publication-title: IEEE Trans Ind Inf
– volume: 58
  start-page: 2640
  year: 2022
  end-page: 2651
  ident: b22
  article-title: Optimal scheduling of integrated demand response-enabled community-integrated energy systems in uncertain environments
  publication-title: IEEE Trans Ind Appl
– start-page: 1273
  year: 2017
  end-page: 1282
  ident: b32
  article-title: Communication-efficient learning of deep networks from decentralized data
  publication-title: Artificial intelligence and statistics
– volume: 99
  start-page: 154
  year: 2012
  end-page: 166
  ident: b8
  article-title: Wind speed and wind energy forecast through Kalman filtering of Numerical Weather Prediction model output
  publication-title: Appl Energy
– volume: 11
  start-page: 1231
  year: 2015
  end-page: 1242
  ident: b3
  article-title: Multistage wind-electric power forecast by using a combination of advanced statistical methods
  publication-title: IEEE Trans Ind Inf
– volume: 33
  start-page: 5714
  year: 2018
  end-page: 5726
  ident: b17
  article-title: A distributed approach for wind power probabilistic forecasting considering spatio-temporal correlation without direct access to off-site information
  publication-title: IEEE Trans Power Syst
– volume: 202
  year: 2020
  ident: b14
  article-title: A new hybrid ensemble deep reinforcement learning model for wind speed short term forecasting
  publication-title: Energy
– volume: 518
  start-page: 529
  year: 2015
  end-page: 533
  ident: b23
  article-title: Human-level control through deep reinforcement learning
  publication-title: Nature
– volume: 177
  start-page: 793
  year: 2016
  end-page: 803
  ident: b33
  article-title: A novel bidirectional mechanism based on time series model for wind power forecasting
  publication-title: Appl Energy
– volume: 232
  start-page: 54
  year: 2018
  end-page: 68
  ident: b15
  article-title: Optimal scheduling of isolated microgrid with an electric vehicle battery swapping station in multi-stakeholder scenarios: A bi-level programming approach via real-time pricing
  publication-title: Appl Energy
– volume: 7
  start-page: 241
  year: 2015
  end-page: 249
  ident: b9
  article-title: Short-term wind speed or power forecasting with heteroscedastic support vector regression
  publication-title: IEEE Trans Sustain Energy
– volume: 7
  start-page: 7751
  year: 2020
  end-page: 7763
  ident: b27
  article-title: Privacy-preserving traffic flow prediction: A federated learning approach
  publication-title: IEEE Internet Things J
– start-page: 1
  year: 2009
  end-page: 6
  ident: b6
  article-title: Wind power forecasting and error analysis using the autoregressive moving average modeling
  publication-title: 2009 IEEE power & energy society general meeting
– volume: 227
  year: 2021
  ident: b7
  article-title: Short-term offshore wind speed forecast by seasonal ARIMA-A comparison against GRU and LSTM
  publication-title: Energy
– year: 2022
  ident: b35
  article-title: Dense skip attention based deep learning for day-ahead electricity price forecasting
  publication-title: IEEE Trans Power Syst
– volume: 1
  year: 2010
  ident: b18
  article-title: Differential privacy for statistics: What we know and what we want to learn
  publication-title: J Privacy Confident
– year: 2017
  ident: b16
  article-title: The EU general data protection regulation (GDPR)
  publication-title: A Practical Guide, vol. 10
– volume: 37
  start-page: 50
  year: 2020
  end-page: 60
  ident: b25
  article-title: Federated learning: Challenges, methods, and future directions
  publication-title: IEEE Signal Process Mag
– volume: 10
  start-page: 1
  year: 2019
  end-page: 19
  ident: b29
  article-title: Federated machine learning: Concept and applications
  publication-title: ACM Trans Intell Syst Technol
– start-page: 387
  year: 2014
  end-page: 395
  ident: b24
  article-title: Deterministic policy gradient algorithms
  publication-title: International conference on machine learning
– volume: 308
  year: 2022
  ident: b36
  article-title: Hierarchical stochastic scheduling of multi-community integrated energy systems in uncertain environments via Stackelberg game
  publication-title: Appl Energy
– year: 2019
  ident: b30
  article-title: Training deep neural networks with reinforcement learning for time series forecasting
  publication-title: Time series analysis-data, methods, and applications
– volume: 18
  start-page: 2310
  year: 2022
  end-page: 2320
  ident: b28
  article-title: Privacy-preserving spatiotemporal scenario generation of renewable energies: A federated deep generative learning approach
  publication-title: IEEE Trans Ind Inf
– volume: 73
  start-page: 23
  year: 2013
  end-page: 50
  ident: b4
  article-title: Towards privacy protection in smart grid
  publication-title: Wirel Pers Commun
– volume: 12
  start-page: 172
  year: 2016
  end-page: 187
  ident: b19
  article-title: Dynamic differential privacy for ADMM-based distributed classification learning
  publication-title: IEEE Trans Inf Forensics Secur
– reference: Li ZL, Liang C-JM, He W, Zhu L, Dai W, Jiang J, et al. Metis: Robustly tuning tail latencies of cloud systems. In: 2018 {USENIX} Annual technical conference ({USENIX}{ATC} 18). 2018, p. 981–92.
– volume: 162
  start-page: 237
  year: 2018
  end-page: 254
  ident: b1
  article-title: A two-stage approach for combined heat and power economic emission dispatch: Combining multi-objective optimization with integrated decision making
  publication-title: Energy
– volume: 236
  year: 2021
  ident: b13
  article-title: A novel asynchronous deep reinforcement learning model with adaptive early forecasting method and reward incentive mechanism for short-term load forecasting
  publication-title: Energy
– volume: 10
  start-page: 1
  issue: 2
  year: 2019
  ident: 10.1016/j.apenergy.2022.120291_b29
  article-title: Federated machine learning: Concept and applications
  publication-title: ACM Trans Intell Syst Technol
  doi: 10.1145/3298981
– year: 2022
  ident: 10.1016/j.apenergy.2022.120291_b35
  article-title: Dense skip attention based deep learning for day-ahead electricity price forecasting
  publication-title: IEEE Trans Power Syst
– volume: 94
  start-page: 629
  year: 2016
  ident: 10.1016/j.apenergy.2022.120291_b10
  article-title: Wind speed forecasting based on the hybrid ensemble empirical mode decomposition and GA-BP neural network method
  publication-title: Renew Energy
  doi: 10.1016/j.renene.2016.03.103
– volume: 37
  start-page: 50
  issue: 3
  year: 2020
  ident: 10.1016/j.apenergy.2022.120291_b25
  article-title: Federated learning: Challenges, methods, and future directions
  publication-title: IEEE Signal Process Mag
  doi: 10.1109/MSP.2020.2975749
– volume: 11
  start-page: 1231
  issue: 5
  year: 2015
  ident: 10.1016/j.apenergy.2022.120291_b3
  article-title: Multistage wind-electric power forecast by using a combination of advanced statistical methods
  publication-title: IEEE Trans Ind Inf
  doi: 10.1109/TII.2015.2431642
– volume: 232
  start-page: 54
  year: 2018
  ident: 10.1016/j.apenergy.2022.120291_b15
  article-title: Optimal scheduling of isolated microgrid with an electric vehicle battery swapping station in multi-stakeholder scenarios: A bi-level programming approach via real-time pricing
  publication-title: Appl Energy
  doi: 10.1016/j.apenergy.2018.09.211
– volume: 308
  year: 2022
  ident: 10.1016/j.apenergy.2022.120291_b21
  article-title: A deep-learning intelligent system incorporating data augmentation for short-term voltage stability assessment of power systems
  publication-title: Appl Energy
  doi: 10.1016/j.apenergy.2021.118347
– volume: 12
  start-page: 172
  issue: 1
  year: 2016
  ident: 10.1016/j.apenergy.2022.120291_b19
  article-title: Dynamic differential privacy for ADMM-based distributed classification learning
  publication-title: IEEE Trans Inf Forensics Secur
  doi: 10.1109/TIFS.2016.2607691
– start-page: 1
  year: 2009
  ident: 10.1016/j.apenergy.2022.120291_b6
  article-title: Wind power forecasting and error analysis using the autoregressive moving average modeling
– volume: 236
  year: 2021
  ident: 10.1016/j.apenergy.2022.120291_b13
  article-title: A novel asynchronous deep reinforcement learning model with adaptive early forecasting method and reward incentive mechanism for short-term load forecasting
  publication-title: Energy
  doi: 10.1016/j.energy.2021.121492
– ident: 10.1016/j.apenergy.2022.120291_b31
– volume: 13
  start-page: 4862
  issue: 6
  year: 2022
  ident: 10.1016/j.apenergy.2022.120291_b26
  article-title: Detection of false data injection attacks in smart grid: A secure federated deep learning approach
  publication-title: IEEE Trans Smart Grid
  doi: 10.1109/TSG.2022.3204796
– volume: 13
  start-page: 2770
  issue: 6
  year: 2017
  ident: 10.1016/j.apenergy.2022.120291_b11
  article-title: Rough deep neural architecture for short-term wind speed forecasting
  publication-title: IEEE Trans Ind Inf
  doi: 10.1109/TII.2017.2730846
– volume: 162
  start-page: 237
  year: 2018
  ident: 10.1016/j.apenergy.2022.120291_b1
  article-title: A two-stage approach for combined heat and power economic emission dispatch: Combining multi-objective optimization with integrated decision making
  publication-title: Energy
  doi: 10.1016/j.energy.2018.07.200
– start-page: 1273
  year: 2017
  ident: 10.1016/j.apenergy.2022.120291_b32
  article-title: Communication-efficient learning of deep networks from decentralized data
– volume: 73
  start-page: 23
  issue: 1
  year: 2013
  ident: 10.1016/j.apenergy.2022.120291_b4
  article-title: Towards privacy protection in smart grid
  publication-title: Wirel Pers Commun
  doi: 10.1007/s11277-012-0939-1
– volume: 37
  start-page: 322
  issue: 1
  year: 2021
  ident: 10.1016/j.apenergy.2022.120291_b20
  article-title: A critical overview of privacy-preserving approaches for collaborative forecasting
  publication-title: Int J Forecast
  doi: 10.1016/j.ijforecast.2020.06.003
– year: 2019
  ident: 10.1016/j.apenergy.2022.120291_b30
  article-title: Training deep neural networks with reinforcement learning for time series forecasting
– volume: 33
  start-page: 5714
  issue: 5
  year: 2018
  ident: 10.1016/j.apenergy.2022.120291_b17
  article-title: A distributed approach for wind power probabilistic forecasting considering spatio-temporal correlation without direct access to off-site information
  publication-title: IEEE Trans Power Syst
  doi: 10.1109/TPWRS.2018.2822784
– volume: 378
  year: 2022
  ident: 10.1016/j.apenergy.2022.120291_b37
  article-title: Optimal dispatch of low-carbon integrated energy system considering nuclear heating and carbon trading
  publication-title: J Cleaner Prod
  doi: 10.1016/j.jclepro.2022.134540
– volume: 202
  year: 2020
  ident: 10.1016/j.apenergy.2022.120291_b14
  article-title: A new hybrid ensemble deep reinforcement learning model for wind speed short term forecasting
  publication-title: Energy
  doi: 10.1016/j.energy.2020.117794
– volume: 58
  start-page: 2640
  issue: 2
  year: 2022
  ident: 10.1016/j.apenergy.2022.120291_b22
  article-title: Optimal scheduling of integrated demand response-enabled community-integrated energy systems in uncertain environments
  publication-title: IEEE Trans Ind Appl
  doi: 10.1109/TIA.2021.3106573
– volume: 308
  year: 2022
  ident: 10.1016/j.apenergy.2022.120291_b36
  article-title: Hierarchical stochastic scheduling of multi-community integrated energy systems in uncertain environments via Stackelberg game
  publication-title: Appl Energy
  doi: 10.1016/j.apenergy.2021.118392
– volume: 518
  start-page: 529
  issue: 7540
  year: 2015
  ident: 10.1016/j.apenergy.2022.120291_b23
  article-title: Human-level control through deep reinforcement learning
  publication-title: Nature
  doi: 10.1038/nature14236
– year: 2022
  ident: 10.1016/j.apenergy.2022.120291_b2
  article-title: Probabilistic wind power forecasting using optimised deep auto-regressive recurrent neural networks
  publication-title: IEEE Trans Ind Inf
– volume: 9
  issue: 2
  year: 2020
  ident: 10.1016/j.apenergy.2022.120291_b5
  article-title: The future of forecasting for renewable energy
  publication-title: Wiley Interdiscip Rev Energy Environ
– volume: 227
  year: 2021
  ident: 10.1016/j.apenergy.2022.120291_b7
  article-title: Short-term offshore wind speed forecast by seasonal ARIMA-A comparison against GRU and LSTM
  publication-title: Energy
  doi: 10.1016/j.energy.2021.120492
– volume: 165
  start-page: 840
  year: 2018
  ident: 10.1016/j.apenergy.2022.120291_b12
  article-title: Deep belief network based k-means cluster approach for short-term wind power forecasting
  publication-title: Energy
  doi: 10.1016/j.energy.2018.09.118
– volume: 18
  start-page: 2310
  issue: 4
  year: 2022
  ident: 10.1016/j.apenergy.2022.120291_b28
  article-title: Privacy-preserving spatiotemporal scenario generation of renewable energies: A federated deep generative learning approach
  publication-title: IEEE Trans Ind Inf
  doi: 10.1109/TII.2021.3098259
– volume: 99
  start-page: 154
  year: 2012
  ident: 10.1016/j.apenergy.2022.120291_b8
  article-title: Wind speed and wind energy forecast through Kalman filtering of Numerical Weather Prediction model output
  publication-title: Appl Energy
  doi: 10.1016/j.apenergy.2012.03.054
– volume: 177
  start-page: 793
  year: 2016
  ident: 10.1016/j.apenergy.2022.120291_b33
  article-title: A novel bidirectional mechanism based on time series model for wind power forecasting
  publication-title: Appl Energy
  doi: 10.1016/j.apenergy.2016.03.096
– volume: 7
  start-page: 241
  issue: 1
  year: 2015
  ident: 10.1016/j.apenergy.2022.120291_b9
  article-title: Short-term wind speed or power forecasting with heteroscedastic support vector regression
  publication-title: IEEE Trans Sustain Energy
  doi: 10.1109/TSTE.2015.2480245
– start-page: 387
  year: 2014
  ident: 10.1016/j.apenergy.2022.120291_b24
  article-title: Deterministic policy gradient algorithms
– volume: 7
  start-page: 7751
  issue: 8
  year: 2020
  ident: 10.1016/j.apenergy.2022.120291_b27
  article-title: Privacy-preserving traffic flow prediction: A federated learning approach
  publication-title: IEEE Internet Things J
  doi: 10.1109/JIOT.2020.2991401
– volume: 1
  issue: 2
  year: 2010
  ident: 10.1016/j.apenergy.2022.120291_b18
  article-title: Differential privacy for statistics: What we know and what we want to learn
  publication-title: J Privacy Confident
  doi: 10.29012/jpc.v1i2.570
– year: 2017
  ident: 10.1016/j.apenergy.2022.120291_b16
  article-title: The EU general data protection regulation (GDPR)
– volume: 13
  start-page: 159
  issue: 1
  year: 2021
  ident: 10.1016/j.apenergy.2022.120291_b34
  article-title: Optimal scheduling of isolated microgrids using automated reinforcement learning-based multi-period forecasting
  publication-title: IEEE Trans Sustain Energy
  doi: 10.1109/TSTE.2021.3105529
– volume: 245
  year: 2022
  ident: 10.1016/j.apenergy.2022.120291_b38
  article-title: Joint planning of distributed generations and energy storage in active distribution networks: A Bi-Level programming approach
  publication-title: Energy
  doi: 10.1016/j.energy.2022.123226
SSID ssj0002120
Score 2.7057123
Snippet In a modern power system with an increasing proportion of renewable energy, wind power prediction is crucial to the arrangement of power grid dispatching plans...
SourceID proquest
crossref
elsevier
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 120291
SubjectTerms algorithms
Data openness and sharing
Deep reinforcement learning
energy
Federated learning
issues and policy
prediction
Privacy protection
Uncertainty modeling
wind power
Wind power forecasting
Title Wind power forecasting considering data privacy protection: A federated deep reinforcement learning approach
URI https://dx.doi.org/10.1016/j.apenergy.2022.120291
https://www.proquest.com/docview/3153831363
Volume 329
WOSCitedRecordID wos000890577800006&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  customDbUrl:
  eissn: 1872-9118
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002120
  issn: 0306-2619
  databaseCode: AIEXJ
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9QwELaWlgMcEBQqSgEZidsqZWNvHua2QosAiQqhIpaT5Tg2bLVKo32pV_55Z2I7Scuj9MAliiyPlex8GX-enQchLxOdA88tbBRbUMM4NipSRRJHmdJJLkawAaq8aTaRHR_ns5n4NBj8DLkw20VWVfn5uaj_q6phDJSNqbM3UHe7KAzAPSgdrqB2uP6T4r_OMfUfm59hCKHRarV2ibWuMyfeY1josF7Ot9jr3Vdq8DEek6HF8hIKiWhpTD1cmqa2qm7ciKHJxPe2Fnmf3AZGa5p8wjbUp4kX-Kb8Ftk4752B-byZV2fdsJ-4Abb6w3TDrUv7Yxj0TgrGe04Kn5w1SiM8rPUNL_e-Dmc6Y5Bzjbt-serOwXB6pGr3AnCsZ-yoE7hcRvvK9tYGHYZ4tlMZ1pG4jnTr3CK7LEsE2Pbdyfvp7EO7nTNf2zO8QS_N_PdP9CeGc2WvbwjMyX1yz5886MQh5gEZmGqP3O3Vo9wj-9Mu7RGmeru_ekgWCCragIr2QEV7oKIIKupBRTtQvaYT2kKKIqToJUjRACkaIPWIfHk7PXnzLvJ9OiLNBV_DF56IgtvCapaW2vDYpBmeZAsN3DpjpVLAuYEJJoWNkb6XIi2EAupoWVakZcH3yQ7AzTwmtOSpFXxkU8bMmHMttB2pbGwEh7mxSA5IEn5bqX0Re-ylspB_1-4BedXK1a6My7USIqhOejLqSKYEVF4r-yLoWoK1xr_gVGXONivJkWDwmKf8yY2f6JDc6T6tp2RnvdyYZ-S23q7nq-VzD9sL4tK-Pw
linkProvider Elsevier
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Wind+power+forecasting+considering+data+privacy+protection%3A+A+federated+deep+reinforcement+learning+approach&rft.jtitle=Applied+energy&rft.au=Li%2C+Yang&rft.au=Wang%2C+Ruinong&rft.au=Li%2C+Yuanzheng&rft.au=Zhang%2C+Meng&rft.date=2023-01-01&rft.issn=0306-2619&rft.volume=329&rft.spage=120291&rft_id=info:doi/10.1016%2Fj.apenergy.2022.120291&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_apenergy_2022_120291
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0306-2619&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0306-2619&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0306-2619&client=summon