From d0ea09d6636864384f04853c1ba9d308f5b9b290 Mon Sep 17 00:00:00 2001 From: chenxiaodong Date: Mon, 17 Feb 2025 10:18:29 +0800 Subject: [PATCH] refactor models --- models/env.py | 40 ++++++++++++++++++++-------------------- models/module.py | 28 ++++++++++++---------------- models/tools.py | 6 ++---- train.py | 5 +++-- 4 files changed, 37 insertions(+), 42 deletions(-) diff --git a/models/env.py b/models/env.py index d600c9f..880cbe7 100644 --- a/models/env.py +++ b/models/env.py @@ -1,9 +1,10 @@ import gym +import numpy as np import pandas as pd -from data_manager import * -from module import * -from parameters import * +from models.data_manager import * +from models.module import * +from models.parameters import * class WgzGym(gym.Env): @@ -29,18 +30,18 @@ class WgzGym(gym.Env): self.heat_a = 0.6 self.power_a = 0.4 self.EC_parameters = kwargs.get('EC_parameters', EC_parameters) # 电解水制氢器 - self.HST_parameters = kwargs.get('dg_parameters', dg_parameters) # 储氢罐 + self.HST_parameters = kwargs.get('HST_parameters', HST_parameters) # 储氢罐 self.grid = Grid() self.EC = EC(self.EC_parameters) self.HST = HST(self.HST_parameters) - self.action_space = gym.spaces.Box(low=-1, high=1, shape=(3,), dtype=np.float32) + self.action_space = gym.spaces.Box(low=-1, high=1, shape=(2,), dtype=np.float32) ''' 时间 光伏 温度（湿度暂未考虑） 电需 热需（转化为对应热水所需瓦数） 人数 电价 7 - 电解水制氢功率 储氢罐容量占比 市电功率（注意标准化） 3 + 电解水制氢功率 储氢罐容量占比 2 市电功率（注意标准化）->舍(由供需控制) ''' - self.state_space = gym.spaces.Box(low=0, high=1, shape=(10,), dtype=np.float32) + self.state_space = gym.spaces.Box(low=0, high=1, shape=(9,), dtype=np.float32) def reset(self, *args): self.month = np.random.randint(1, 13) # choose 12 month @@ -56,12 +57,12 @@ class WgzGym(gym.Env): def _build_state(self): hst_soc = self.HST.current_soc ec_out = self.EC.get_hydrogen() - grid_ex = self.grid + grid_ex = self.grid.trade_energy time_step = self.current_time if self.TRAIN: price = self.data_manager.get_price_data(self.month, self.day, self.current_time) - temper = self.data_manager.get_temperature_data(self.month, self.day, self.current_time) + temper = self.data_manager.get_temper_data(self.month, self.day, self.current_time) solar = self.data_manager.get_solar_data(self.month, self.day, self.current_time) load = self.data_manager.get_load_data(self.month, self.day, self.current_time) heat = self.data_manager.get_heat_data(self.month, self.day, self.current_time) @@ -76,8 +77,7 @@ class WgzGym(gym.Env): obs = np.concatenate((np.float32(time_step), np.float32(price), np.float32(temper), np.float32(solar), np.float32(load), np.float32(heat), - np.float32(people), np.float32(ec_out), np.float32(hst_soc), np.float32(grid_ex)), - axis=None) + np.float32(people), np.float32(ec_out), np.float32(hst_soc)), axis=None) return obs def step(self, action): @@ -85,7 +85,7 @@ class WgzGym(gym.Env): current_obs = self._build_state() self.EC.step(action[0]) self.HST.step(action[1]) - self.grid.step(action[2]) + # self.grid.step(action[2], self.EC.power_max) price = current_obs[1] temper = current_obs[2] # 用途待补充 solar = current_obs[3] @@ -120,11 +120,11 @@ class WgzGym(gym.Env): economic_cost = hst_cost + ec_cost + solar_cost - sell_benefit + buy_cost demand_cost = self.heat_a * heat_penalty + self.power_a * power_penalty - eco_benifit = self.EC.less_carbon() - self.grid.get_carbon() + eco_benifit = self.EC.less_carbon() - self.grid.get_carbon(power_gap) reward = - self.a * demand_cost - self.b * economic_cost + self.c * eco_benifit self.unbalance = power_gap + heat_gap - final_step_outputs = [self.HST.current_soc, self.HST.get_power(), self.EC.current_power, self.grid.current_power] + final_step_outputs = [self.HST.current_soc, self.HST.get_power(), self.EC.current_power] self.current_time += 1 finish = (self.current_time == self.episode_length) if finish: @@ -140,7 +140,7 @@ class WgzGym(gym.Env): solar = data_df['solar_power'].to_numpy(dtype=float) temper = data_df['temper'].to_numpy(dtype=float) energy = data_df['energy_demand'].to_numpy(dtype=float) - water = data_df['water_demand'].to_numpy(dtype=float) + heat = data_df['water_demand'].to_numpy(dtype=float) people = data_df['people_count'].to_numpy(dtype=float) price = data_df['price'].to_numpy(dtype=float) @@ -151,9 +151,9 @@ class WgzGym(gym.Env): transformed_e = transform_function(e) add_function(transformed_e) - process_elements(solar, lambda x: x, self.data_manager.add_load_element) - process_elements(temper, lambda x: x, self.data_manager.add_load_element) - process_elements(energy, lambda x: x, self.data_manager.add_irradiance_element) - process_elements(water, lambda x: x, self.data_manager.add_temperature_element) - process_elements(people, lambda x: x, self.data_manager.add_wind_element) + process_elements(solar, lambda x: x, self.data_manager.add_solar_element) + process_elements(temper, lambda x: x, self.data_manager.add_temper_element) + process_elements(energy, lambda x: x, self.data_manager.add_electricity_element) + process_elements(heat, lambda x: x, self.data_manager.add_heat_element) + process_elements(people, lambda x: x, self.data_manager.add_people_element) process_elements(price, lambda x: x, self.data_manager.add_price_element) diff --git a/models/module.py b/models/module.py index 638dcc2..f1ca9a3 100644 --- a/models/module.py +++ b/models/module.py @@ -7,7 +7,7 @@ class EC: self.ramp = params['ramp'] self.lifetime = params['lifetime'] self.equipment_cost = params['equipment_cost'] - self.electricity_efficiency = params['electricity_efficiency'] + self.electrolysis_efficiency = params['electrolysis_efficiency'] self.carbon_reduce = params['carbon_reduce'] def step(self, action_ec): @@ -20,17 +20,14 @@ class EC: return self.equipment_cost / self.lifetime * price * self.current_power / self.power_max def get_hydrogen(self): - return self.current_power * self.electricity_efficiency * self.hydrogen_produce + return self.current_power * self.electrolysis_efficiency * self.hydrogen_produce def get_heat(self): - return self.current_power * (1 - self.electricity_efficiency) + return self.current_power * (1 - self.electrolysis_efficiency) def less_carbon(self): return self.current_power * self.carbon_reduce - def get_power_max(self): - return self.power_max - def reset(self): self.current_power = 0 @@ -42,7 +39,6 @@ class HST: self.capacity = params['capacity'] self.min_soc = params['min_soc'] self.max_soc = params['max_soc'] - self.ramp = params['ramp'] self.lifetime = params['lifetime'] self.equipment_cost = params['equipment_cost'] self.charge_efficiency = params['charge_efficiency'] @@ -51,12 +47,12 @@ class HST: ''' 储氢罐的充气速率 = 电解水制氢速率 （电解水制氢放的热会满足热水需求?） - + 如何控制上述待补充 储氢罐的放气速率 = 供电 （电价低时多电解，电价高时释放） ''' def step(self, action_hst): - energy = action_hst * self.ramp + energy = action_hst * self.capacity updated_soc = max(self.min_soc, min(self.max_soc, (self.current_soc * self.capacity + energy) / self.capacity)) self.hydrogen_charge = (updated_soc - self.current_soc) * self.capacity self.current_soc = updated_soc @@ -85,16 +81,16 @@ class Grid: def __init__(self): self.delta = 1 self.carbon_increace = 0.9 - self.trade_energy = None + # self.trade_energy = None - def step(self, action_grid): - self.trade_energy = (action_grid + 1) / 2 * EC.get_power_max() # 反标准化 + # def step(self, action_grid, ec_power_max): + # self.trade_energy = (action_grid + 1) / 2 * ec_power_max # 反标准化 - def get_cost(self, price): - return price * self.trade_energy * self.delta + def get_cost(self, price, trade_energy): + return price * trade_energy * self.delta - def get_carbon(self): - return self.trade_energy * self.carbon_increace + def get_carbon(self, trade_energy): + return trade_energy * self.carbon_increace def retrieve_past_price(self): result = [] diff --git a/models/tools.py b/models/tools.py index 9a5acfd..703e011 100644 --- a/models/tools.py +++ b/models/tools.py @@ -15,12 +15,10 @@ def test_one_episode(env, act, device): action = a_tensor.detach().cpu().numpy()[0] state, next_state, reward, done = env.step(action) record_system_info.append([state[1], state[2], env.HST.current_soc(), env.HST.get_power(), - env.EC.current_power, env.grid.current_power, action, reward]) + env.EC.current_power, action, reward]) state = next_state # add information of last step EC, HST.current_soc, HST.power, grid - final_step_outputs = [self.HST.current_soc, self.HST.get_power(), self.EC.current_power, self.grid.current_power] - record_system_info[-1][2:6] = [env.final_step_outputs[0], env.final_step_outputs[1], env.final_step_outputs[2], - env.final_step_outputs[3]] + record_system_info[-1][2:5] = [env.final_step_outputs[0], env.final_step_outputs[1], env.final_step_outputs[2]] record = {'init_info': record_init_info, 'system_info': record_system_info} return record diff --git a/train.py b/train.py index e10d732..ea3ae0d 100644 --- a/train.py +++ b/train.py @@ -3,11 +3,12 @@ import pickle os.environ['OMP_WAIT_POLICY'] = 'PASSIVE' # 确保在pytorch前设置 from copy import deepcopy -import pandas as pd +import numpy as np +import torch import torch.nn.functional as F from models.env import WgzGym from models.net import ActorPPO, CriticAdv -from models.tools import get_episode_return, test_one_episode +from models.tools import get_episode_return def smooth_rewards(rewards, window=10):