# A Deep Learning-Based Approach for Generation Expansion Planning Considering Power Plants Lifetime

^{1}

^{2}

^{3}

^{*}

## Abstract

**:**

## 1. Introduction

_{2}emission.

- Investigating the effects of power plants’ lifetime constrain on new and existing plants. This constraint affects the GEP problem due to two practical reasons: 1-Some power plants have less lifetime than the planning horizon. This fact may increase the costs, and the GEP might have more cost than the case with a longer lifetime. 2-Some power plants may have derated efficiency due to aging, or out of date technologies in comparison with newer ones with less fuel consumption. Therefore, they should be replaced by new ones.
- Using a new version of LSTM networks known as Bi-directional LSTM (BLSTM) networks for forecasting the annual peak load. The advantages of BLSTM networks compared to LSTM networks are its two feedforward and feedback loops, which lead to the use of the whole temporal horizon. This feature of BLSTM networks can increase accuracy in time series forecasting tasks.
- Considering the carbon tax policy as a carbon emission reduction method in order to prevent the release of carbon into the environment

## 2. Objective Function

#### 2.1. Investment, Operation, and Maintenance Cost

#### 2.2. Carbon Emission Cost

#### 2.3. Constraints

#### 2.3.1. The Lifetime Constraint

#### 2.3.2. The Reserve Margin Constraint

#### 2.3.3. Maximum Number of New Plants Constraint

#### 2.3.4. Mix Capacity Constraint

#### 2.3.5. The LOLP Constraint

## 3. Deep Learning-Based Approach for Annual Peak Load Forecasting

_{t}), forget (f

_{t}), and output (o

_{t}) gates are calculated, respectively. In addition, Equation (11) shows the cell state, and S

_{t}is the output of LSTM block.:

## 4. Case Studies

#### 4.1. Case 1: Test System

#### 4.2. Forecasting Annual Peak Load

#### 4.3. Case 2: Iran Power System

#### 4.4. Carbon Reduction

## 5. Conclusions

## Author Contributions

## Funding

## Institutional Review Board Statement

## Informed Consent Statement

## Conflicts of Interest

## Nomenclature

Parameters | |

c_{1} | Cognitive component |

c_{2} | Social component |

$J$ | Fuel type number |

${\underset{\_}{M}}_{t}^{j}$ | Lower bound of j-th fuel type in a year t |

${\overline{M}}_{t}^{j}$ | Upper bound of j-th fuel type in a year t |

$\underset{\_}{R}$ | Lower bound of reserve margin |

$\overline{R}\text{}$ | Upper bound of reserve margin |

$T$ | Time period numbers (years) in the planning horizon |

${\overline{U}}_{t}$ | Maximum manufactural capacity vector (MW) of generation unit types in a year t |

w | Inertia weight |

${\mathrm{\Omega}}_{j}$ | Type indicator set of the j-th generation unit |

$n$ | Total number of input data |

$nh$ | Total number of hidden units |

$no$ | Total number of outputs |

$r$ | Dimension of each input data sequence |

Variables | |

${L}_{t}$ | Retired capacity vector (MW) of generation unit types in a year t |

$LOLP({X}_{t})$ | loss of load probability with ${X}_{t}$, in a year t |

${U}_{t}$ | Added capacity vector (MW) of generation unit types in a year t |

${v}_{a}(k)$ | Velocity of the a-th particle at iteration k |

${x}_{t}^{i}$ | Added capacity (MW) of the i-th unit in a year t |

${X}_{t}$ | Cumulative capacity vector (MW) of generation unit types in a year t |

${y}_{a}(k)$ | Position of the a-th particle at iteration k |

${f}_{t}^{3}\left({L}_{t}\right)$ | Discounted salvage value ($) due to retired capacity ${L}_{t}$ in a year t |

${f}_{t}^{1}\left({U}_{t}\right)$ | Discounted construction cost ($) due to added capacity ${U}_{t}$ in a year t |

${f}_{t}^{2}\left({X}_{t}\right)$ | Discounted operation and maintenance cost due to cumulative capacity ${X}_{t}$ in a year t |

${f}_{t}^{3}\left({X}_{t}\right)$ | Discounted carbon emission cost due to cumulative capacity ${X}_{t}$ in a year t |

$R\left({X}_{t}\right)$ | Capacity reserve margin of ${X}_{t}$ in a year t |

$bc,bf,bi,bo$ | Bias vector for cell block, forget gate, input gate, and output gate, respectively |

$b{h}^{(b)},b{h}^{(f)}$ | Bias vector for backward and forward hidden layer, respectively |

${c}_{t},{f}_{t},{i}_{t}$ | Data vector of cell block, forget gate, and input gate at a time t, respectively |

$c{h}_{t},f{h}_{t},i{h}_{t}$ | Data vector of cell block, forget gate, and input gate at a time t in hidden layer, respectively |

${H}_{t}$ | Total hidden vector layers |

${\overrightarrow{H}}_{t},{\overleftarrow{H}}_{t}$ | Hidden vector for forward and backward layer at a time t, respectively |

${o}_{t}$ | Data vector of output gate at a time t |

$Ofn$ | Output vector of final layer |

$o{h}_{t}$ | Data vector of output gate at a time t in hidden layer |

${S}_{t}$ | State vector of current layer at a state t |

${S}_{t}^{l}$ | State vector of a layer l at a state t |

$S{h}_{t}^{l}$ | State vector of a hidden layer l at a state t |

$\begin{array}{l}Wh{i}_{\hspace{0.17em}},Wh\phi ,\hspace{0.17em}\\ Wh\gamma ,\hspace{0.17em}Who\end{array}$ | Weight vector for output of previous state input gate, forget gate, cell block, and output gate, respectively |

$\begin{array}{l}W{i}_{\hspace{0.17em}},Wi{\phi}_{\hspace{0.17em}},\\ Wi\gamma ,Wio\end{array}$ | Weight vector for input of current state input gate, forget gate, cell block, and output gate, respectively |

$Wh{h}^{(b)},Wh{h}^{(f)}$ | Weight vector of backward and forward layer output data, respectively |

$Wo$ | Weight vector of output layer |

$Wx{h}^{(b)},Wx{h}^{(f)}$ | Weight vector of backward and forward layer input data, respectively |

$\text{}{X}_{t}$ | Input data vector at a time t |

Indices | |

a | Index for particle number |

$i$ | Index for power plant type |

$j$ | Index for fuel type |

$k$ | Index for iteration number |

$t$ | Index for time period |

$l$ | Index for hidden layer |

$t$ | Index for time |

## References

- Hemmati, R.; Saboori, H.; Jirdehi, M.A. Multistage generation expansion planning incorporating large scale energy storage systems and environmental pollution. Renew. Energy
**2016**, 97, 636–645. [Google Scholar] [CrossRef] - Rajesh, K.; Bhuvanesh, A.; Kannan, S.; Thangaraj, C. Least cost generation expansion planning with solar power plant using differential evolution algorithm. Renew. Energy
**2016**, 85, 677–686. [Google Scholar] [CrossRef] - Valinejad, J.; Marzband, M.; Akorede, M.F.; Barforoshi, T.; Jovanović, M. Generation expansion planning in electricity market considering uncertainty in load demand and presence of strategic GENCOs. Electr. Power Syst. Res.
**2017**, 152, 92–104. [Google Scholar] [CrossRef] [Green Version] - Jadidoleslam, M.; Ebrahimi, A. Reliability constrained generation expansion planning by a modified shuffled frog leaping algorithm. Int. J. Electr. Power Energy Syst.
**2015**, 64, 743–751. [Google Scholar] [CrossRef] - Karimyan, P.; Gharehpetian, G.; Abedi, M.; Gavili, A. Long term scheduling for optimal allocation and sizing of DG unit considering load variations and DG type. Int. J. Electr. Power Energy Syst.
**2014**, 54, 277–287. [Google Scholar] [CrossRef] - Luz, T.; Moura, P.; de Almeida, A. Multi-objective power generation expansion planning with high penetration of renewables. Renew. Sustain. Energy Rev.
**2017**, 81, 2637–2643. [Google Scholar] [CrossRef] - Flores-Quiroz, A.; Palma-Behnke, R.; Zakeri, G.; Moreno, R. A column generation approach for solving generation expansion planning problems with high renewable energy penetration. Electr. Power Syst. Res.
**2016**, 136, 232–241. [Google Scholar] [CrossRef] - Maluenda, B.; Negrete-Pincetic, M.; Olivares, D.E.; Lorca, Á. Expansion planning under uncertainty for hydrothermal systems with variable resources. Int. J. Electr. Power Energy Syst.
**2018**, 103, 644–651. [Google Scholar] [CrossRef] - Kong, X.; Yao, J.; Wang, X. Generation Expansion Planning Based on Dynamic Bayesian Network Considering the Uncertainty of Renewable Energy Resources. Energies
**2019**, 12, 2492. [Google Scholar] [CrossRef] [Green Version] - Micheli, G.; Vespucci, M.T.; Stabile, M.; Puglisi, C.; Ramos, A. A two-stage stochastic MILP model for generation and transmission expansion planning with high shares of renewables. Energy Syst.
**2020**, 1–43. [Google Scholar] [CrossRef] - Wang, P.; Wang, C.; Hu, Y.; Varga, L.; Wang, W. Power generation expansion optimization model considering multi-scenario electricity demand constraints: A case study of Zhejiang province, China. Energies
**2018**, 11, 1498. [Google Scholar] [CrossRef] [Green Version] - Park, H. Generation capacity expansion planning considering hourly dynamics of renewable resources. Energies
**2020**, 13, 5626. [Google Scholar] [CrossRef] - Haghighi, R.; Yektamoghadam, H.; Dehghani, M.; Nikoofard, A. Generation Expansion Planning Using Game Theory Approach to Reduce Carbon Emission: A Case Study of Iran. Comput. Ind. Eng.
**2021**, 162, 107713. [Google Scholar] [CrossRef] - Babatunde, O.M.; Munda, J.L.; Hamam, Y. A comprehensive state-of-the-art survey on power generation expansion planning with intermittent renewable energy source and energy storage. Int. J. Energy Res.
**2019**, 43, 6078–6107. [Google Scholar] [CrossRef] - Oree, V.; Hassen, S.Z.S.; Fleming, P.J. Generation expansion planning optimisation with renewable energy integration: A review. Renew. Sustain. Energy Rev.
**2017**, 69, 790–803. [Google Scholar] [CrossRef] - Diewvilai, R.; Audomvongseree, K. Generation Expansion Planning with Energy Storage Systems Considering Renewable Energy Generation Profiles and Full-Year Hourly Power Balance Constraints. Energies
**2021**, 14, 5733. [Google Scholar] [CrossRef] - Dagoumas, A.S.; Koltsaklis, N.E. Review of models for integrating renewable energy in the generation expansion planning. Appl. Energy
**2019**, 242, 1573–1587. [Google Scholar] [CrossRef] - Rajesh, K.; Kannan, S.; Thangaraj, C. Least cost generation expansion planning with wind power plant incorporating emission using differential evolution algorithm. Int. J. Electr. Power Energy Syst.
**2016**, 80, 275–286. [Google Scholar] [CrossRef] - Jin, S.; Ryan, S.M.; Watson, J.-P.; Woodruff, D.L. Modeling and solving a large-scale generation expansion planning problem under uncertainty. Energy Syst.
**2011**, 2, 209–242. [Google Scholar] [CrossRef] - Gitizadeh, M.; Kaji, M.; Aghaei, J. Risk based multiobjective generation expansion planning considering renewable energy sources. Energy
**2013**, 50, 74–82. [Google Scholar] [CrossRef] - Sun, D.; Xie, X.; Wang, J.; Li, Q.; Wei, C. Integrated generation-transmission expansion planning for offshore oilfield power systems based on genetic Tabu hybrid algorithm. J. Mod. Power Syst. Clean Energy
**2017**, 5, 117–125. [Google Scholar] [CrossRef] [Green Version] - Park, J.-B.; Park, Y.-M.; Won, J.-R.; Lee, K.Y. An improved genetic algorithm for generation expansion planning. IEEE Trans. Power Syst.
**2000**, 15, 916–922. [Google Scholar] [CrossRef] [Green Version] - Foley, A.; Gallachóir, B.Ó. Analysis of electric vehicle charging using the traditional generation expansion planning analysis tool WASP-IV. J. Mod. Power Syst. Clean Energy
**2015**, 3, 240–248. [Google Scholar] [CrossRef] [Green Version] - Koltsaklis, N.E.; Georgiadis, M.C. A multi-period, multi-regional generation expansion planning model incorporating unit commitment constraints. Appl. Energy
**2015**, 158, 310–331. [Google Scholar] [CrossRef] - Palmintier, B.; Webster, M. Impact of unit commitment constraints on generation expansion planning with renewables. In Proceedings of the 2011 IEEE Power and Energy Society General Meeting, Detroit, MI, USA, 24–28 July 2011; pp. 1–7. [Google Scholar]
- Palmintier, B.S.; Webster, M.D. Impact of operational flexibility on electricity generation planning with renewable and carbon targets. IEEE Trans. Sustain. Energy
**2015**, 7, 672–684. [Google Scholar] [CrossRef] - Tohidi, Y.; Aminifar, F.; Fotuhi-Firuzabad, M. Generation expansion and retirement planning based on the stochastic programming. Electr. Power Syst. Res.
**2013**, 104, 138–145. [Google Scholar] [CrossRef] - Mavalizadeh, H.; Ahmadi, A.; Gandoman, F.H.; Siano, P.; Shayanfar, H.A. Multiobjective robust power system expansion planning considering generation units retirement. IEEE Syst. J.
**2017**, 12, 2664–2675. [Google Scholar] [CrossRef] - Mejía Giraldo, D.A.; López Lezama, J.M.; Gallego Pareja, L.A. Power system capacity expansion planning model considering carbon emissions constraints. Rev. Fac. Ing. Univ. Antioq.
**2012**, 62, 114–125. [Google Scholar] - Doagou-Mojarrad, H.; Rastegar, H.; Gharehpetian, G.B. Probabilistic interactive fuzzy satisfying generation and transmission expansion planning using fuzzy adaptive chaotic binary PSO algorithm. J. Intell. Fuzzy Syst.
**2016**, 30, 1629–1641. [Google Scholar] [CrossRef] - Yao, W.; Chung, C.; Wen, F.; Qin, M.; Xue, Y. Scenario-based comprehensive expansion planning for distribution systems considering integration of plug-in electric vehicles. IEEE Trans. Power Syst.
**2015**, 31, 317–328. [Google Scholar] [CrossRef] - Suriya, P.; Subramanian, S.; Ganesan, S.; Hariprasath, M. Multi-objective generation expansion and retirement planning using chaotic grasshopper optimisation algorithm. Aust. J. Electr. Electron. Eng.
**2019**, 16, 136–148. [Google Scholar] [CrossRef] - Jahangir, H.; Gougheri, S.S.; Vatandoust, B.; Golkar, M.A.; Ahmadian, A.; Hajizadeh, A. Plug-in Electric Vehicle Behavior Modeling in Energy Market: A Novel Deep Learning-Based Approach with Clustering Technique. IEEE Trans. Smart Grid
**2020**, 11, 4738–4748. [Google Scholar] [CrossRef] - Mishra, M.; Nayak, J.; Naik, B.; Abraham, A. Deep learning in electrical utility industry: A comprehensive review of a decade of research. Eng. Appl. Artif. Intell.
**2020**, 96, 104000. [Google Scholar] [CrossRef] - Jahangir, H.; Tayarani, H.; Gougheri, S.S.; Golkar, M.A.; Ahmadian, A.; Elkamel, A. Deep Learning-based Forecasting Approach in Smart Grids with Micro-Clustering and Bi-directional LSTM Network. IEEE Trans. Ind. Electron.
**2020**, 68, 8298–8309. [Google Scholar] [CrossRef] - Rhode, S.; Van Vaerenbergh, S.; Pfriem, M. Power prediction for electric vehicles using online machine learning. Eng. Appl. Artif. Intell.
**2020**, 87, 103278. [Google Scholar] [CrossRef] - Chen, Q.; Kang, C.; Xia, Q.; Zhong, J. Power generation expansion planning model towards low-carbon economy and its application in China. IEEE Trans. Power Syst.
**2010**, 25, 1117–1125. [Google Scholar] [CrossRef] [Green Version] - Valinejad, J.; Marzband, M.; Elsdon, M.; Saad Al-Sumaiti, A.; Barforoushi, T. Dynamic carbon-constrained EPEC model for strategic generation investment incentives with the aim of reducing CO
_{2}emissions. Energies**2019**, 12, 4813. [Google Scholar] [CrossRef] [Green Version] - Sun, J.; Liu, L.; Liu, Y.; Shi, F. Low-Carbon Generation Expansion Planning Based on the Global Energy Interconnection Construction Plan. In Proceedings of the 2020 IEEE/IAS Industrial and Commercial Power System Asia (I&CPS Asia), Weihai, China, 13–15 July 2020; pp. 805–809. [Google Scholar]
- Hu, Y.; Ding, T.; Bie, Z.; Lian, H. Integrated generation and transmission expansion planning with carbon capture operating constraints. In Proceedings of the 2016 IEEE Power and Energy Society General Meeting (PESGM), Boston, MA, USA, 17–21 July 2016; pp. 1–5. [Google Scholar]
- Pourmoosavi, M.-A.; Amraee, T. Low carbon generation expansion planning with carbon capture technology and coal phase-out under renewable integration. Int. J. Electr. Power Energy Syst.
**2021**, 128, 106715. [Google Scholar] [CrossRef] - Asgharian, V.; Abdelaziz, M. A low-carbon market-based multi-area power system expansion planning model. Electr. Power Syst. Res.
**2020**, 187, 106500. [Google Scholar] [CrossRef] - Jahangir, H.; Tayarani, H.; Ahmadian, A.; Golkar, M.A.; Miret, J.; Tayarani, M.; Gao, H.O. Charging demand of plug-in electric vehicles: Forecasting travel behavior based on a novel rough artificial neural network approach. J. Clean. Prod.
**2019**, 229, 1029–1044. [Google Scholar] [CrossRef] - Makarenkov, V.; Rokach, L.; Shapira, B. Choosing the right word: Using bidirectional LSTM tagger for writing support systems. Eng. Appl. Artif. Intell.
**2019**, 84, 1–10. [Google Scholar] [CrossRef] [Green Version] - Huang, C.-G.; Huang, H.-Z.; Li, Y.-F. A bidirectional LSTM prognostics method under multiple operational conditions. IEEE Trans. Ind. Electron.
**2019**, 66, 8792–8802. [Google Scholar] [CrossRef] - Lin, J.C.-W.; Shao, Y.; Zhou, Y.; Pirouz, M.; Chen, H.-C. A Bi-LSTM mention hypergraph model with encoding schema for mention extraction. Eng. Appl. Artif. Intell.
**2019**, 85, 175–181. [Google Scholar] [CrossRef] - Liu, J.; Wang, Z.; Xu, M. DeepMTT: A deep learning maneuvering target-tracking algorithm based on bidirectional LSTM network. Inf. Fusion
**2020**, 53, 289–304. [Google Scholar] [CrossRef] - Neshat, N.; Amin-Naseri, M. Cleaner power generation through market-driven generation expansion planning: An agent-based hybrid framework of game theory and particle swarm optimization. J. Clean. Prod.
**2015**, 105, 206–217. [Google Scholar] [CrossRef]

**Figure 8.**Capacity installed (blue bars) or retired (red bars) in each year for LNG-fired power plants.

**Figure 9.**Capacity installed (blue bars) or retired (red bars) in each year for coal-fired power plants.

**Figure 10.**Capacity installed (blue bars) or retired (red bars) in each year for nuclear power plants (PHWR).

**Figure 11.**Capacity installed (blue bars) or retired (red bars) in each year for oil-fired power plants.

**Figure 12.**Capacity installed (blue bars) or retired (red bars) in each year for nuclear power plants (PWR).

**Figure 13.**Daily forecasted peak load for July to September 2020 by different methods and their yearly peak loads.

Name | No. of Units | Unit Capacity (MW) | Operating Cost ($/kWh) | Fixed O&M Cost ($/kW-mon) |
---|---|---|---|---|

Oil 1 | 1 | 200 | 0.024 | 2.25 |

Oil 2 | 1 | 200 | 0.027 | 2.25 |

Oil 3 | 1 | 150 | 0.030 | 2.13 |

LNG G/T | 3 | 50 | 0.043 | 4.52 |

LNG C/C 1 | 1 | 400 | 0.038 | 1.63 |

LNG C/C 2 | 1 | 400 | 0.040 | 1.63 |

LNG C/C 3 | 1 | 450 | 0.035 | 2.00 |

Coal 1 | 2 | 250 | 0.023 | 6.65 |

Coal 2 | 1 | 500 | 0.019 | 2.81 |

Coal 3 | 1 | 500 | 0.015 | 2.81 |

PWR 1 | 1 | 1000 | 0.005 | 4.94 |

PWR 2 | 1 | 1000 | 0.005 | 4.63 |

Year | Peak (MW) | Year | Peak (MW) |
---|---|---|---|

0 | 5000 | 16 | 17,000 |

2 | 7000 | 18 | 18,000 |

4 | 9000 | 20 | 20,000 |

6 | 10,000 | 22 | 22,000 |

8 | 12,000 | 24 | 24,000 |

10 | 13,000 | 26 | 26,000 |

12 | 14,000 | 28 | 27,000 |

14 | 15,000 | 30 | 30,000 |

Candidate Type | Oil | LNG | Coal | PWR | PHWR |
---|---|---|---|---|---|

Construction upper limit | 5 | 4 | 3 | 3 | 3 |

Capacity (MW) | 200 | 450 | 500 | 1000 | 700 |

Operating cost ($/kWh) | 0.021 | 0.035 | 0.014 | 0.004 | 0.003 |

Fixed O&M cost ($/kW-mon) | 2.20 | 0.90 | 2.75 | 4.60 | 5.50 |

Capital cost ($/kW) | 812.5 | 500.0 | 1062.5 | 1625.0 | 1750.0 |

Lifetime (years) | 20 | 22 | 24 | 26 | 28 |

Name (Fuel Type) | Lifetime (years) | Name (Fuel Type) | Lifetime (years) |
---|---|---|---|

Oil 1 | 6 | LNG C/C 3 | 20 |

Oil 2 | 10 | Coal 1 | 8 |

Oil 3 | 14 | Coal 2 | 12 |

LNG G/T | 4 | Coal 3 | 16 |

LNG C/C 1 | 10 | PWR 1 | 12 |

LNG C/C 2 | 16 | PWR 2 | 16 |

Year | Oil | LNG | PWR | Coal | ||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|

New | Retired | Total | New | Retired | Total | New | Retired | Total | New | Retired | Total | |

2 | 1 | 0 | 1 | 0 | 0 | 0 | 2 | 0 | 2 | 2 | 0 | 2 |

4 | 2 | 0 | 3 | 0 | 0 | 0 | 0 | 0 | 2 | 0 | 0 | 2 |

6 | 2 | 0 | 5 | 1 | 0 | 1 | 0 | 0 | 2 | 0 | 0 | 2 |

8 | 0 | 0 | 5 | 0 | 0 | 1 | 2 | 0 | 4 | 0 | 0 | 2 |

10 | 0 | 0 | 5 | 0 | 0 | 1 | 0 | 0 | 4 | 1 | 0 | 3 |

12 | 1 | 0 | 6 | 0 | 0 | 1 | 1 | 0 | 5 | 0 | 0 | 3 |

14 | 4 | 0 | 10 | 0 | 0 | 1 | 1 | 0 | 6 | 1 | 0 | 4 |

16 | 2 | 0 | 12 | 2 | 0 | 3 | 0 | 0 | 6 | 2 | 0 | 6 |

18 | 0 | 0 | 12 | 2 | 0 | 5 | 1 | 0 | 7 | 0 | 0 | 6 |

20 | 4 | 1 | 15 | 2 | 0 | 7 | 2 | 0 | 9 | 0 | 0 | 6 |

22 | 0 | 2 | 13 | 4 | 0 | 11 | 0 | 0 | 9 | 0 | 0 | 6 |

24 | 5 | 2 | 16 | 3 | 0 | 14 | 3 | 0 | 12 | 3 | 2 | 7 |

26 | 1 | 0 | 17 | 0 | 0 | 14 | 1 | 2 | 11 | 2 | 0 | 9 |

28 | 1 | 0 | 18 | 0 | 1 | 13 | 2 | 0 | 13 | 2 | 0 | 11 |

30 | 3 | 1 | 20 | 0 | 0 | 13 | 2 | 0 | 15 | 0 | 0 | 11 |

Method | Total Cost (M $) |
---|---|

Without considering lifetime | 40,248 |

With considering lifetime | 38,231 |

Error Criterion | |||
---|---|---|---|

MAPE (%) | MAE (MW) | RMSE (MW) | |

BLSTM | 1.90 | 1031.74 | 1276.69 |

LSTM | 2.29 | 1243.79 | 1515.57 |

MLP | 3.57 | 1942.65 | 2437.11 |

Year | Peak (MW) | Year | Peak (MW) |
---|---|---|---|

1 | 60,479 | 16 | 80,180 |

2 | 62,613 | 17 | 80,685 |

3 | 64,644 | 18 | 82,143 |

4 | 66,560 | 19 | 82,812 |

5 | 68,354 | 20 | 83,446 |

6 | 70,021 | 21 | 85,632 |

7 | 71,558 | 22 | 86,143 |

8 | 72,967 | 23 | 89,231 |

9 | 74,248 | 24 | 91,968 |

10 | 75,408 | 25 | 92,457 |

11 | 76,451 | 26 | 92,967 |

12 | 77,384 | 27 | 92,692 |

13 | 78,216 | 28 | 93,619 |

14 | 78,954 | 29 | 94,276 |

15 | 79,606 | 30 | 95,889 |

Type | Investment (1000 Rial/kW) | O&M Cost (Rial/kWh) | CO_{2} Generation Rate (ton CO^{2}/MWh) | Existing Capacity (MW) | Plant Life (year) | Unit Size (MW) |
---|---|---|---|---|---|---|

Nuclear | 87,990 | 3150 | 0 | 0 | 60 | 1000 |

Coal based | 80,700 | 2925 | 0.4 | 0 | 40 | 320 |

Combined cycle | 20,411 | 293 | 0.34 | 14,632 | 20 | 480 |

Natural gas | 12,750 | 390 | 0.5 | 21,617 | 15 | 162 |

Steam based | 24,450 | 450 | 0.71 | 15,704 | 30 | 320 |

Hydroelectric | 48,920 | 494 | 0 | 9542 | 50 | 100 |

Wind | 56,430 | 103.2 | 0 | 90 | 22 | 25 |

Solar | 92,700 | 171.9 | 0 | 0 | 20 | 100 |

Photovoltaic | 135,000 | 27.3 | 0 | 0 | 15 | 100 |

Biomass | 121,500 | 1350 | 0 | 0 | 20 | 25 |

Method | Total Cost (M Rial) |
---|---|

Without considering lifetime | 9.54 × 10^{9} |

With considering lifetime | 8.84 × 10^{9} |

Biomass | Natural | Wind | Photovoltaic | |||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|

Year | New | Retired | Total | New | Retired | Total | New | Retired | Total | New | Retired | Total |

16 | 0 | 0 | 39 | 0 | 6 | 26 | 1 | 0 | 49 | 0 | 6 | 34 |

17 | 2 | 0 | 41 | 1 | 3 | 24 | 0 | 0 | 49 | 0 | 0 | 34 |

18 | 0 | 0 | 41 | 0 | 0 | 24 | 0 | 0 | 49 | 0 | 4 | 30 |

19 | 0 | 0 | 41 | 2 | 6 | 20 | 0 | 0 | 49 | 3 | 0 | 33 |

20 | 1 | 0 | 42 | 5 | 3 | 22 | 5 | 0 | 54 | 3 | 6 | 30 |

21 | 1 | 6 | 37 | 3 | 0 | 25 | 3 | 0 | 57 | 5 | 6 | 29 |

22 | 3 | 0 | 40 | 5 | 5 | 25 | 1 | 0 | 58 | 0 | 5 | 24 |

23 | 5 | 4 | 41 | 1 | 4 | 22 | 5 | 6 | 57 | 4 | 4 | 24 |

24 | 6 | 6 | 41 | 6 | 0 | 28 | 6 | 6 | 57 | 6 | 0 | 30 |

25 | 3 | 6 | 38 | 3 | 0 | 31 | 3 | 6 | 54 | 1 | 2 | 29 |

26 | 3 | 6 | 35 | 2 | 1 | 32 | 1 | 3 | 52 | 1 | 1 | 29 |

27 | 6 | 3 | 38 | 6 | 1 | 37 | 6 | 0 | 58 | 6 | 2 | 33 |

28 | 0 | 1 | 37 | 1 | 1 | 37 | 2 | 6 | 54 | 0 | 0 | 33 |

29 | 5 | 0 | 42 | 0 | 1 | 36 | 5 | 5 | 54 | 3 | 0 | 36 |

30 | 3 | 2 | 43 | 4 | 1 | 39 | 3 | 4 | 53 | 3 | 4 | 35 |

**Table 13.**Total carbon produced by Iran power system with and without considering carbon emissions constraint.

Method | Total Carbon (Ton) |
---|---|

Without considering the carbon emission constraint | 1.5492 × 10^{6} |

With considering the carbon emission constraint | 1.2731 × 10^{6} |

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |

© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Dehghani, M.; Taghipour, M.; Sadeghi Gougheri, S.; Nikoofard, A.; Gharehpetian, G.B.; Khosravy, M.
A Deep Learning-Based Approach for Generation Expansion Planning Considering Power Plants Lifetime. *Energies* **2021**, *14*, 8035.
https://doi.org/10.3390/en14238035

**AMA Style**

Dehghani M, Taghipour M, Sadeghi Gougheri S, Nikoofard A, Gharehpetian GB, Khosravy M.
A Deep Learning-Based Approach for Generation Expansion Planning Considering Power Plants Lifetime. *Energies*. 2021; 14(23):8035.
https://doi.org/10.3390/en14238035

**Chicago/Turabian Style**

Dehghani, Majid, Mohammad Taghipour, Saleh Sadeghi Gougheri, Amirhossein Nikoofard, Gevork B. Gharehpetian, and Mahdi Khosravy.
2021. "A Deep Learning-Based Approach for Generation Expansion Planning Considering Power Plants Lifetime" *Energies* 14, no. 23: 8035.
https://doi.org/10.3390/en14238035